Spaces:
Running
Running
David Pomerenke
commited on
Commit
·
5640508
1
Parent(s):
9aa08d7
Run 1 model through all benchmarks
Browse files- index.html +27 -21
- languagebench.py +23 -12
- results.json +1527 -447
- results_summary.json +935 -15
index.html
CHANGED
|
@@ -39,6 +39,7 @@
|
|
| 39 |
|
| 40 |
const summary = await fetch('results_summary.json');
|
| 41 |
const summaryData = await summary.json();
|
|
|
|
| 42 |
const formatTitle = d => d.target_language_name + "\n" + parseInt(d.speakers / 1_000_00) / 10 + "M speakers\nBLEU score: " + d.bleu.toFixed(1)
|
| 43 |
|
| 44 |
// Create summary plot
|
|
@@ -48,8 +49,8 @@
|
|
| 48 |
marginBottom: 100,
|
| 49 |
x: { label: "Number of speakers", axis: null },
|
| 50 |
y: { label: "BLEU Score (average across models)" },
|
|
|
|
| 51 |
marks: [
|
| 52 |
-
|
| 53 |
Plot.rectY(summaryData, Plot.stackX({
|
| 54 |
x: "speakers",
|
| 55 |
order: "bleu",
|
|
@@ -57,6 +58,7 @@
|
|
| 57 |
y2: "bleu", // y2 to avoid stacking by y
|
| 58 |
title: formatTitle,
|
| 59 |
tip: true,
|
|
|
|
| 60 |
})),
|
| 61 |
Plot.rectY(summaryData, Plot.pointerX(Plot.stackX({
|
| 62 |
x: "speakers",
|
|
@@ -66,7 +68,6 @@
|
|
| 66 |
fill: "grey",
|
| 67 |
}))),
|
| 68 |
Plot.text(summaryData, Plot.stackX({
|
| 69 |
-
filter: (d) => d.speakers > 5_000_000,
|
| 70 |
x: "speakers",
|
| 71 |
y2: "bleu",
|
| 72 |
order: "bleu",
|
|
@@ -76,6 +77,7 @@
|
|
| 76 |
textAnchor: "end",
|
| 77 |
dy: 10,
|
| 78 |
rotate: 270,
|
|
|
|
| 79 |
}))
|
| 80 |
]
|
| 81 |
});
|
|
@@ -100,7 +102,7 @@
|
|
| 100 |
.map(([lang]) => lang);
|
| 101 |
|
| 102 |
|
| 103 |
-
|
| 104 |
languages.forEach(language => {
|
| 105 |
const headerDiv = document.createElement('div');
|
| 106 |
headerDiv.className = 'language-header';
|
|
@@ -125,24 +127,28 @@
|
|
| 125 |
return model.split("-")[0]
|
| 126 |
}
|
| 127 |
|
| 128 |
-
//
|
| 129 |
-
|
| 130 |
-
|
| 131 |
-
|
| 132 |
-
|
| 133 |
-
|
| 134 |
-
|
| 135 |
-
|
| 136 |
-
|
| 137 |
-
|
| 138 |
-
|
| 139 |
-
|
| 140 |
-
|
| 141 |
-
|
| 142 |
-
|
| 143 |
-
|
| 144 |
-
|
| 145 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
| 146 |
});
|
| 147 |
}
|
| 148 |
|
|
|
|
| 39 |
|
| 40 |
const summary = await fetch('results_summary.json');
|
| 41 |
const summaryData = await summary.json();
|
| 42 |
+
// Format captions
|
| 43 |
const formatTitle = d => d.target_language_name + "\n" + parseInt(d.speakers / 1_000_00) / 10 + "M speakers\nBLEU score: " + d.bleu.toFixed(1)
|
| 44 |
|
| 45 |
// Create summary plot
|
|
|
|
| 49 |
marginBottom: 100,
|
| 50 |
x: { label: "Number of speakers", axis: null },
|
| 51 |
y: { label: "BLEU Score (average across models)" },
|
| 52 |
+
// color: { scheme: "BrBG" },
|
| 53 |
marks: [
|
|
|
|
| 54 |
Plot.rectY(summaryData, Plot.stackX({
|
| 55 |
x: "speakers",
|
| 56 |
order: "bleu",
|
|
|
|
| 58 |
y2: "bleu", // y2 to avoid stacking by y
|
| 59 |
title: formatTitle,
|
| 60 |
tip: true,
|
| 61 |
+
// fill: d => -d.bleu
|
| 62 |
})),
|
| 63 |
Plot.rectY(summaryData, Plot.pointerX(Plot.stackX({
|
| 64 |
x: "speakers",
|
|
|
|
| 68 |
fill: "grey",
|
| 69 |
}))),
|
| 70 |
Plot.text(summaryData, Plot.stackX({
|
|
|
|
| 71 |
x: "speakers",
|
| 72 |
y2: "bleu",
|
| 73 |
order: "bleu",
|
|
|
|
| 77 |
textAnchor: "end",
|
| 78 |
dy: 10,
|
| 79 |
rotate: 270,
|
| 80 |
+
opacity: (d) => d.speakers > 50_000_000 ? 1 : 0,
|
| 81 |
}))
|
| 82 |
]
|
| 83 |
});
|
|
|
|
| 102 |
.map(([lang]) => lang);
|
| 103 |
|
| 104 |
|
| 105 |
+
// Section for each language
|
| 106 |
languages.forEach(language => {
|
| 107 |
const headerDiv = document.createElement('div');
|
| 108 |
headerDiv.className = 'language-header';
|
|
|
|
| 127 |
return model.split("-")[0]
|
| 128 |
}
|
| 129 |
|
| 130 |
+
// Plot for how well the models perform on this language
|
| 131 |
+
if (languageData.length > 2) {
|
| 132 |
+
console.log(languageData);
|
| 133 |
+
const plot = Plot.plot({
|
| 134 |
+
width: 400,
|
| 135 |
+
height: 200,
|
| 136 |
+
margin: 30,
|
| 137 |
+
y: {
|
| 138 |
+
domain: [0, 100],
|
| 139 |
+
label: "BLEU"
|
| 140 |
+
},
|
| 141 |
+
marks: [
|
| 142 |
+
Plot.barY(languageData, {
|
| 143 |
+
x: d => descriptor(d.model),
|
| 144 |
+
y: "bleu"
|
| 145 |
+
})
|
| 146 |
+
]
|
| 147 |
+
});
|
| 148 |
+
chartsDiv.appendChild(plot);
|
| 149 |
+
}
|
| 150 |
+
|
| 151 |
+
|
| 152 |
});
|
| 153 |
}
|
| 154 |
|
languagebench.py
CHANGED
|
@@ -19,14 +19,15 @@ models = [
|
|
| 19 |
"anthropic/claude-3.5-sonnet",
|
| 20 |
"meta-llama/llama-3.1-70b-instruct", # lots of slow repetitions for LRLs
|
| 21 |
"mistralai/mistral-nemo",
|
| 22 |
-
"google/gemini-flash-1.5", # very fast
|
| 23 |
"qwen/qwen-2.5-72b-instruct", # somewhat slow
|
| 24 |
]
|
|
|
|
| 25 |
original_language = "eng_Latn"
|
| 26 |
dataset = "floresp-v2.0-rc.3/dev"
|
| 27 |
random.seed(42)
|
| 28 |
target_languages = [f.split(".")[1] for f in os.listdir(dataset)]
|
| 29 |
-
|
| 30 |
|
| 31 |
# setup
|
| 32 |
load_dotenv()
|
|
@@ -36,7 +37,7 @@ client = AsyncOpenAI(
|
|
| 36 |
)
|
| 37 |
cache = Memory(location=".cache", verbose=0).cache
|
| 38 |
bleu = evaluate.load("sacrebleu")
|
| 39 |
-
rate_limit = AsyncLimiter(max_rate=
|
| 40 |
|
| 41 |
|
| 42 |
def check_rate_limit():
|
|
@@ -46,18 +47,20 @@ def check_rate_limit():
|
|
| 46 |
headers={"Authorization": f"Bearer {getenv('OPENROUTER_API_KEY')}"},
|
| 47 |
).json()
|
| 48 |
)
|
| 49 |
-
|
| 50 |
-
|
| 51 |
-
|
| 52 |
-
|
| 53 |
-
|
| 54 |
-
)
|
| 55 |
|
| 56 |
|
| 57 |
@cache
|
| 58 |
async def complete(**kwargs):
|
| 59 |
async with rate_limit:
|
| 60 |
response = await client.chat.completions.create(**kwargs)
|
|
|
|
|
|
|
| 61 |
return response
|
| 62 |
|
| 63 |
|
|
@@ -83,14 +86,15 @@ async def translate(model, target_language, target_script, sentence):
|
|
| 83 |
"content": f"Translate the following text to the {target_language} language; use the {target_script} script; reply only with the translation:\n\n{sentence}",
|
| 84 |
}
|
| 85 |
],
|
| 86 |
-
temperature=0
|
| 87 |
max_tokens=1024,
|
| 88 |
)
|
| 89 |
return reply.choices[0].message.content
|
| 90 |
|
| 91 |
|
| 92 |
def get_language_stats(language_code):
|
| 93 |
-
lang, script = language_code.split("_")
|
|
|
|
| 94 |
stats = language_stats[language_stats["iso639_3"] == lang]
|
| 95 |
if not stats.empty:
|
| 96 |
stats = stats.iloc[0].to_dict()
|
|
@@ -99,7 +103,12 @@ def get_language_stats(language_code):
|
|
| 99 |
stats["script"] = script_names[script_names["Code"] == script]["English Name"].iloc[
|
| 100 |
0
|
| 101 |
]
|
| 102 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 103 |
return stats
|
| 104 |
|
| 105 |
|
|
@@ -112,6 +121,8 @@ async def main():
|
|
| 112 |
continue
|
| 113 |
target_sentences = open(f"{dataset}/dev.{target_language}").readlines()
|
| 114 |
for model in models:
|
|
|
|
|
|
|
| 115 |
stats = get_language_stats(target_language)
|
| 116 |
print(f"{model} -> {stats['name']}")
|
| 117 |
predictions = [
|
|
|
|
| 19 |
"anthropic/claude-3.5-sonnet",
|
| 20 |
"meta-llama/llama-3.1-70b-instruct", # lots of slow repetitions for LRLs
|
| 21 |
"mistralai/mistral-nemo",
|
| 22 |
+
# "google/gemini-flash-1.5", # very fast
|
| 23 |
"qwen/qwen-2.5-72b-instruct", # somewhat slow
|
| 24 |
]
|
| 25 |
+
fast_model = "anthropic/claude-3.5-sonnet"
|
| 26 |
original_language = "eng_Latn"
|
| 27 |
dataset = "floresp-v2.0-rc.3/dev"
|
| 28 |
random.seed(42)
|
| 29 |
target_languages = [f.split(".")[1] for f in os.listdir(dataset)]
|
| 30 |
+
detailed_target_languages = random.choices(target_languages, k=5)
|
| 31 |
|
| 32 |
# setup
|
| 33 |
load_dotenv()
|
|
|
|
| 37 |
)
|
| 38 |
cache = Memory(location=".cache", verbose=0).cache
|
| 39 |
bleu = evaluate.load("sacrebleu")
|
| 40 |
+
rate_limit = AsyncLimiter(max_rate=15, time_period=1)
|
| 41 |
|
| 42 |
|
| 43 |
def check_rate_limit():
|
|
|
|
| 47 |
headers={"Authorization": f"Bearer {getenv('OPENROUTER_API_KEY')}"},
|
| 48 |
).json()
|
| 49 |
)
|
| 50 |
+
models = requests.get(
|
| 51 |
+
"https://openrouter.ai/api/v1/models",
|
| 52 |
+
headers={"Authorization": f"Bearer {getenv('OPENROUTER_API_KEY')}"},
|
| 53 |
+
).json()["data"]
|
| 54 |
+
model = next((m for m in models if m["id"] == "google/gemini-flash-1.5"), None)
|
| 55 |
+
print(model)
|
| 56 |
|
| 57 |
|
| 58 |
@cache
|
| 59 |
async def complete(**kwargs):
|
| 60 |
async with rate_limit:
|
| 61 |
response = await client.chat.completions.create(**kwargs)
|
| 62 |
+
if not response.choices:
|
| 63 |
+
raise Exception(response)
|
| 64 |
return response
|
| 65 |
|
| 66 |
|
|
|
|
| 86 |
"content": f"Translate the following text to the {target_language} language; use the {target_script} script; reply only with the translation:\n\n{sentence}",
|
| 87 |
}
|
| 88 |
],
|
| 89 |
+
temperature=0,
|
| 90 |
max_tokens=1024,
|
| 91 |
)
|
| 92 |
return reply.choices[0].message.content
|
| 93 |
|
| 94 |
|
| 95 |
def get_language_stats(language_code):
|
| 96 |
+
lang, script = language_code.split("_", 1)
|
| 97 |
+
script = script.split("_", 1)[0]
|
| 98 |
stats = language_stats[language_stats["iso639_3"] == lang]
|
| 99 |
if not stats.empty:
|
| 100 |
stats = stats.iloc[0].to_dict()
|
|
|
|
| 103 |
stats["script"] = script_names[script_names["Code"] == script]["English Name"].iloc[
|
| 104 |
0
|
| 105 |
]
|
| 106 |
+
name_series = language_names[language_names["LangID"] == lang]["Name"]
|
| 107 |
+
stats["name"] = (
|
| 108 |
+
name_series.iloc[0]
|
| 109 |
+
if not name_series.empty
|
| 110 |
+
else stats.get("itemLabel_en") or stats.get("itemLabel", lang)
|
| 111 |
+
)
|
| 112 |
return stats
|
| 113 |
|
| 114 |
|
|
|
|
| 121 |
continue
|
| 122 |
target_sentences = open(f"{dataset}/dev.{target_language}").readlines()
|
| 123 |
for model in models:
|
| 124 |
+
if model != fast_model and target_language not in detailed_target_languages:
|
| 125 |
+
continue
|
| 126 |
stats = get_language_stats(target_language)
|
| 127 |
print(f"{model} -> {stats['name']}")
|
| 128 |
predictions = [
|
results.json
CHANGED
|
@@ -1,51 +1,43 @@
|
|
| 1 |
[
|
| 2 |
-
{
|
| 3 |
-
"model": "openai/gpt-4o-mini",
|
| 4 |
-
"original_language": "eng_Latn",
|
| 5 |
-
"target_language": "isl_Latn",
|
| 6 |
-
"target_language_name": "Icelandic",
|
| 7 |
-
"speakers": 358000,
|
| 8 |
-
"bleu": 61.11721529849627
|
| 9 |
-
},
|
| 10 |
{
|
| 11 |
"model": "anthropic/claude-3.5-sonnet",
|
| 12 |
"original_language": "eng_Latn",
|
| 13 |
-
"target_language": "
|
| 14 |
-
"target_language_name": "
|
| 15 |
-
"speakers":
|
| 16 |
-
"bleu":
|
| 17 |
},
|
| 18 |
{
|
| 19 |
-
"model": "
|
| 20 |
"original_language": "eng_Latn",
|
| 21 |
-
"target_language": "
|
| 22 |
-
"target_language_name": "
|
| 23 |
-
"speakers":
|
| 24 |
-
"bleu":
|
| 25 |
},
|
| 26 |
{
|
| 27 |
-
"model": "
|
| 28 |
"original_language": "eng_Latn",
|
| 29 |
-
"target_language": "
|
| 30 |
-
"target_language_name": "
|
| 31 |
-
"speakers":
|
| 32 |
-
"bleu":
|
| 33 |
},
|
| 34 |
{
|
| 35 |
-
"model": "
|
| 36 |
"original_language": "eng_Latn",
|
| 37 |
-
"target_language": "
|
| 38 |
-
"target_language_name": "
|
| 39 |
-
"speakers":
|
| 40 |
-
"bleu":
|
| 41 |
},
|
| 42 |
{
|
| 43 |
-
"model": "
|
| 44 |
"original_language": "eng_Latn",
|
| 45 |
-
"target_language": "
|
| 46 |
-
"target_language_name": "
|
| 47 |
-
"speakers":
|
| 48 |
-
"bleu":
|
| 49 |
},
|
| 50 |
{
|
| 51 |
"model": "openai/gpt-4o-mini",
|
|
@@ -53,7 +45,7 @@
|
|
| 53 |
"target_language": "ind_Latn",
|
| 54 |
"target_language_name": "Indonesian",
|
| 55 |
"speakers": 198996550,
|
| 56 |
-
"bleu": 76.
|
| 57 |
},
|
| 58 |
{
|
| 59 |
"model": "anthropic/claude-3.5-sonnet",
|
|
@@ -61,7 +53,7 @@
|
|
| 61 |
"target_language": "ind_Latn",
|
| 62 |
"target_language_name": "Indonesian",
|
| 63 |
"speakers": 198996550,
|
| 64 |
-
"bleu": 75.
|
| 65 |
},
|
| 66 |
{
|
| 67 |
"model": "meta-llama/llama-3.1-70b-instruct",
|
|
@@ -69,7 +61,7 @@
|
|
| 69 |
"target_language": "ind_Latn",
|
| 70 |
"target_language_name": "Indonesian",
|
| 71 |
"speakers": 198996550,
|
| 72 |
-
"bleu": 74.
|
| 73 |
},
|
| 74 |
{
|
| 75 |
"model": "mistralai/mistral-nemo",
|
|
@@ -77,694 +69,1782 @@
|
|
| 77 |
"target_language": "ind_Latn",
|
| 78 |
"target_language_name": "Indonesian",
|
| 79 |
"speakers": 198996550,
|
| 80 |
-
"bleu":
|
| 81 |
},
|
| 82 |
{
|
| 83 |
-
"model": "
|
| 84 |
"original_language": "eng_Latn",
|
| 85 |
"target_language": "ind_Latn",
|
| 86 |
"target_language_name": "Indonesian",
|
| 87 |
"speakers": 198996550,
|
| 88 |
-
"bleu":
|
| 89 |
},
|
| 90 |
{
|
| 91 |
-
"model": "
|
| 92 |
"original_language": "eng_Latn",
|
| 93 |
-
"target_language": "
|
| 94 |
-
"target_language_name": "
|
| 95 |
-
"speakers":
|
| 96 |
-
"bleu":
|
| 97 |
},
|
| 98 |
{
|
| 99 |
-
"model": "
|
| 100 |
"original_language": "eng_Latn",
|
| 101 |
-
"target_language": "
|
| 102 |
-
"target_language_name": "
|
| 103 |
-
"speakers":
|
| 104 |
-
"bleu":
|
| 105 |
},
|
| 106 |
{
|
| 107 |
"model": "anthropic/claude-3.5-sonnet",
|
| 108 |
"original_language": "eng_Latn",
|
| 109 |
-
"target_language": "
|
| 110 |
-
"target_language_name": "
|
| 111 |
-
"speakers":
|
| 112 |
-
"bleu":
|
| 113 |
},
|
| 114 |
{
|
| 115 |
-
"model": "
|
| 116 |
"original_language": "eng_Latn",
|
| 117 |
-
"target_language": "
|
| 118 |
-
"target_language_name": "
|
| 119 |
-
"speakers":
|
| 120 |
-
"bleu":
|
| 121 |
},
|
| 122 |
{
|
| 123 |
-
"model": "
|
| 124 |
"original_language": "eng_Latn",
|
| 125 |
-
"target_language": "
|
| 126 |
-
"target_language_name": "
|
| 127 |
-
"speakers":
|
| 128 |
-
"bleu":
|
| 129 |
},
|
| 130 |
{
|
| 131 |
-
"model": "
|
| 132 |
"original_language": "eng_Latn",
|
| 133 |
-
"target_language": "
|
| 134 |
-
"target_language_name": "
|
| 135 |
-
"speakers":
|
| 136 |
-
"bleu":
|
| 137 |
},
|
| 138 |
{
|
| 139 |
-
"model": "
|
| 140 |
"original_language": "eng_Latn",
|
| 141 |
-
"target_language": "
|
| 142 |
-
"target_language_name": "
|
| 143 |
-
"speakers":
|
| 144 |
-
"bleu":
|
| 145 |
},
|
| 146 |
{
|
| 147 |
-
"model": "
|
| 148 |
"original_language": "eng_Latn",
|
| 149 |
-
"target_language": "
|
| 150 |
-
"target_language_name": "
|
| 151 |
-
"speakers":
|
| 152 |
-
"bleu":
|
| 153 |
},
|
| 154 |
{
|
| 155 |
"model": "anthropic/claude-3.5-sonnet",
|
| 156 |
"original_language": "eng_Latn",
|
| 157 |
-
"target_language": "
|
| 158 |
-
"target_language_name": "
|
| 159 |
-
"speakers":
|
| 160 |
-
"bleu":
|
| 161 |
},
|
| 162 |
{
|
| 163 |
-
"model": "
|
| 164 |
"original_language": "eng_Latn",
|
| 165 |
-
"target_language": "
|
| 166 |
-
"target_language_name": "
|
| 167 |
-
"speakers":
|
| 168 |
-
"bleu":
|
| 169 |
},
|
| 170 |
{
|
| 171 |
-
"model": "
|
| 172 |
"original_language": "eng_Latn",
|
| 173 |
-
"target_language": "
|
| 174 |
-
"target_language_name": "
|
| 175 |
-
"speakers":
|
| 176 |
-
"bleu":
|
| 177 |
},
|
| 178 |
{
|
| 179 |
-
"model": "
|
| 180 |
"original_language": "eng_Latn",
|
| 181 |
-
"target_language": "
|
| 182 |
-
"target_language_name": "
|
| 183 |
-
"speakers":
|
| 184 |
-
"bleu":
|
| 185 |
},
|
| 186 |
{
|
| 187 |
-
"model": "
|
| 188 |
"original_language": "eng_Latn",
|
| 189 |
-
"target_language": "
|
| 190 |
-
"target_language_name": "
|
| 191 |
-
"speakers":
|
| 192 |
-
"bleu":
|
| 193 |
},
|
| 194 |
{
|
| 195 |
-
"model": "
|
| 196 |
"original_language": "eng_Latn",
|
| 197 |
-
"target_language": "
|
| 198 |
-
"target_language_name": "
|
| 199 |
-
"speakers":
|
| 200 |
-
"bleu":
|
| 201 |
},
|
| 202 |
{
|
| 203 |
"model": "anthropic/claude-3.5-sonnet",
|
| 204 |
"original_language": "eng_Latn",
|
| 205 |
-
"target_language": "
|
| 206 |
-
"target_language_name": "
|
| 207 |
-
"speakers":
|
| 208 |
-
"bleu":
|
| 209 |
},
|
| 210 |
{
|
| 211 |
-
"model": "
|
| 212 |
"original_language": "eng_Latn",
|
| 213 |
-
"target_language": "
|
| 214 |
-
"target_language_name": "
|
| 215 |
-
"speakers":
|
| 216 |
-
"bleu":
|
| 217 |
},
|
| 218 |
{
|
| 219 |
-
"model": "
|
| 220 |
"original_language": "eng_Latn",
|
| 221 |
-
"target_language": "
|
| 222 |
-
"target_language_name": "
|
| 223 |
-
"speakers":
|
| 224 |
-
"bleu":
|
| 225 |
},
|
| 226 |
{
|
| 227 |
-
"model": "
|
| 228 |
"original_language": "eng_Latn",
|
| 229 |
-
"target_language": "
|
| 230 |
-
"target_language_name": "
|
| 231 |
-
"speakers":
|
| 232 |
-
"bleu":
|
| 233 |
},
|
| 234 |
{
|
| 235 |
-
"model": "
|
| 236 |
"original_language": "eng_Latn",
|
| 237 |
-
"target_language": "
|
| 238 |
-
"target_language_name": "
|
| 239 |
-
"speakers":
|
| 240 |
-
"bleu":
|
| 241 |
},
|
| 242 |
{
|
| 243 |
-
"model": "
|
| 244 |
"original_language": "eng_Latn",
|
| 245 |
-
"target_language": "
|
| 246 |
-
"target_language_name": "
|
| 247 |
-
"speakers":
|
| 248 |
-
"bleu":
|
| 249 |
},
|
| 250 |
{
|
| 251 |
"model": "anthropic/claude-3.5-sonnet",
|
| 252 |
"original_language": "eng_Latn",
|
| 253 |
-
"target_language": "
|
| 254 |
-
"target_language_name": "
|
| 255 |
-
"speakers":
|
| 256 |
-
"bleu":
|
| 257 |
},
|
| 258 |
{
|
| 259 |
-
"model": "
|
| 260 |
"original_language": "eng_Latn",
|
| 261 |
-
"target_language": "
|
| 262 |
-
"target_language_name": "
|
| 263 |
-
"speakers":
|
| 264 |
-
"bleu":
|
| 265 |
},
|
| 266 |
{
|
| 267 |
-
"model": "
|
| 268 |
"original_language": "eng_Latn",
|
| 269 |
-
"target_language": "
|
| 270 |
-
"target_language_name": "
|
| 271 |
-
"speakers":
|
| 272 |
-
"bleu":
|
| 273 |
},
|
| 274 |
{
|
| 275 |
-
"model": "
|
| 276 |
"original_language": "eng_Latn",
|
| 277 |
-
"target_language": "
|
| 278 |
-
"target_language_name": "
|
| 279 |
-
"speakers":
|
| 280 |
-
"bleu":
|
| 281 |
},
|
| 282 |
{
|
| 283 |
-
"model": "
|
| 284 |
"original_language": "eng_Latn",
|
| 285 |
-
"target_language": "
|
| 286 |
"target_language_name": "Banjar",
|
| 287 |
"speakers": 3500000,
|
| 288 |
-
"bleu":
|
| 289 |
-
},
|
| 290 |
-
{
|
| 291 |
-
"model": "openai/gpt-4o-mini",
|
| 292 |
-
"original_language": "eng_Latn",
|
| 293 |
-
"target_language": "bho_Deva",
|
| 294 |
-
"target_language_name": "Bhojpuri",
|
| 295 |
-
"speakers": 52200000,
|
| 296 |
-
"bleu": 43.19693805178097
|
| 297 |
},
|
| 298 |
{
|
| 299 |
"model": "anthropic/claude-3.5-sonnet",
|
| 300 |
"original_language": "eng_Latn",
|
| 301 |
-
"target_language": "
|
| 302 |
-
"target_language_name": "
|
| 303 |
-
"speakers":
|
| 304 |
-
"bleu":
|
| 305 |
-
},
|
| 306 |
-
{
|
| 307 |
-
"model": "meta-llama/llama-3.1-70b-instruct",
|
| 308 |
-
"original_language": "eng_Latn",
|
| 309 |
-
"target_language": "bho_Deva",
|
| 310 |
-
"target_language_name": "Bhojpuri",
|
| 311 |
-
"speakers": 52200000,
|
| 312 |
-
"bleu": 43.97962317460702
|
| 313 |
},
|
| 314 |
{
|
| 315 |
-
"model": "
|
| 316 |
"original_language": "eng_Latn",
|
| 317 |
-
"target_language": "
|
| 318 |
-
"target_language_name": "
|
| 319 |
-
"speakers":
|
| 320 |
-
"bleu":
|
| 321 |
},
|
| 322 |
{
|
| 323 |
-
"model": "
|
| 324 |
"original_language": "eng_Latn",
|
| 325 |
-
"target_language": "
|
| 326 |
-
"target_language_name": "
|
| 327 |
-
"speakers":
|
| 328 |
-
"bleu":
|
| 329 |
},
|
| 330 |
{
|
| 331 |
-
"model": "
|
| 332 |
"original_language": "eng_Latn",
|
| 333 |
-
"target_language": "
|
| 334 |
-
"target_language_name": "
|
| 335 |
-
"speakers":
|
| 336 |
-
"bleu":
|
| 337 |
},
|
| 338 |
{
|
| 339 |
-
"model": "
|
| 340 |
"original_language": "eng_Latn",
|
| 341 |
-
"target_language": "
|
| 342 |
-
"target_language_name": "
|
| 343 |
-
"speakers":
|
| 344 |
-
"bleu":
|
| 345 |
},
|
| 346 |
{
|
| 347 |
"model": "anthropic/claude-3.5-sonnet",
|
| 348 |
"original_language": "eng_Latn",
|
| 349 |
-
"target_language": "
|
| 350 |
-
"target_language_name": "
|
| 351 |
-
"speakers":
|
| 352 |
-
"bleu":
|
| 353 |
},
|
| 354 |
{
|
| 355 |
-
"model": "
|
| 356 |
"original_language": "eng_Latn",
|
| 357 |
-
"target_language": "
|
| 358 |
-
"target_language_name": "
|
| 359 |
-
"speakers":
|
| 360 |
-
"bleu":
|
| 361 |
},
|
| 362 |
{
|
| 363 |
-
"model": "
|
| 364 |
"original_language": "eng_Latn",
|
| 365 |
-
"target_language": "
|
| 366 |
-
"target_language_name": "
|
| 367 |
-
"speakers":
|
| 368 |
-
"bleu":
|
| 369 |
},
|
| 370 |
{
|
| 371 |
-
"model": "
|
| 372 |
"original_language": "eng_Latn",
|
| 373 |
-
"target_language": "
|
| 374 |
-
"target_language_name": "
|
| 375 |
-
"speakers":
|
| 376 |
-
"bleu":
|
| 377 |
},
|
| 378 |
{
|
| 379 |
-
"model": "
|
| 380 |
"original_language": "eng_Latn",
|
| 381 |
-
"target_language": "
|
| 382 |
-
"target_language_name": "
|
| 383 |
-
"speakers":
|
| 384 |
-
"bleu":
|
| 385 |
},
|
| 386 |
{
|
| 387 |
-
"model": "
|
| 388 |
"original_language": "eng_Latn",
|
| 389 |
-
"target_language": "
|
| 390 |
-
"target_language_name": "
|
| 391 |
-
"speakers":
|
| 392 |
-
"bleu":
|
| 393 |
},
|
| 394 |
{
|
| 395 |
"model": "anthropic/claude-3.5-sonnet",
|
| 396 |
"original_language": "eng_Latn",
|
| 397 |
-
"target_language": "
|
| 398 |
-
"target_language_name": "
|
| 399 |
-
"speakers":
|
| 400 |
-
"bleu":
|
| 401 |
},
|
| 402 |
{
|
| 403 |
-
"model": "
|
| 404 |
"original_language": "eng_Latn",
|
| 405 |
-
"target_language": "
|
| 406 |
-
"target_language_name": "
|
| 407 |
-
"speakers":
|
| 408 |
-
"bleu":
|
| 409 |
},
|
| 410 |
{
|
| 411 |
-
"model": "
|
| 412 |
"original_language": "eng_Latn",
|
| 413 |
-
"target_language": "
|
| 414 |
-
"target_language_name": "
|
| 415 |
-
"speakers":
|
| 416 |
-
"bleu":
|
| 417 |
},
|
| 418 |
{
|
| 419 |
-
"model": "
|
| 420 |
"original_language": "eng_Latn",
|
| 421 |
-
"target_language": "
|
| 422 |
-
"target_language_name": "
|
| 423 |
-
"speakers":
|
| 424 |
-
"bleu":
|
| 425 |
},
|
| 426 |
{
|
| 427 |
-
"model": "
|
| 428 |
"original_language": "eng_Latn",
|
| 429 |
-
"target_language": "
|
| 430 |
-
"target_language_name": "
|
| 431 |
-
"speakers":
|
| 432 |
-
"bleu":
|
| 433 |
},
|
| 434 |
{
|
| 435 |
"model": "openai/gpt-4o-mini",
|
| 436 |
"original_language": "eng_Latn",
|
| 437 |
-
"target_language": "
|
| 438 |
-
"target_language_name": "
|
| 439 |
-
"speakers":
|
| 440 |
-
"bleu":
|
| 441 |
},
|
| 442 |
{
|
| 443 |
"model": "anthropic/claude-3.5-sonnet",
|
| 444 |
"original_language": "eng_Latn",
|
| 445 |
-
"target_language": "
|
| 446 |
-
"target_language_name": "
|
| 447 |
-
"speakers":
|
| 448 |
-
"bleu":
|
| 449 |
},
|
| 450 |
{
|
| 451 |
"model": "meta-llama/llama-3.1-70b-instruct",
|
| 452 |
"original_language": "eng_Latn",
|
| 453 |
-
"target_language": "
|
| 454 |
-
"target_language_name": "
|
| 455 |
-
"speakers":
|
| 456 |
-
"bleu":
|
| 457 |
},
|
| 458 |
{
|
| 459 |
"model": "mistralai/mistral-nemo",
|
| 460 |
"original_language": "eng_Latn",
|
| 461 |
-
"target_language": "
|
| 462 |
-
"target_language_name": "
|
| 463 |
-
"speakers":
|
| 464 |
-
"bleu":
|
| 465 |
},
|
| 466 |
{
|
| 467 |
-
"model": "
|
| 468 |
"original_language": "eng_Latn",
|
| 469 |
-
"target_language": "
|
| 470 |
-
"target_language_name": "
|
| 471 |
-
"speakers":
|
| 472 |
-
"bleu":
|
| 473 |
},
|
| 474 |
{
|
| 475 |
-
"model": "
|
| 476 |
"original_language": "eng_Latn",
|
| 477 |
-
"target_language": "
|
| 478 |
-
"target_language_name": "
|
| 479 |
-
"speakers":
|
| 480 |
-
"bleu":
|
| 481 |
},
|
| 482 |
{
|
| 483 |
-
"model": "
|
| 484 |
"original_language": "eng_Latn",
|
| 485 |
-
"target_language": "
|
| 486 |
-
"target_language_name": "
|
| 487 |
-
"speakers":
|
| 488 |
-
"bleu":
|
| 489 |
},
|
| 490 |
{
|
| 491 |
"model": "anthropic/claude-3.5-sonnet",
|
| 492 |
"original_language": "eng_Latn",
|
| 493 |
-
"target_language": "
|
| 494 |
-
"target_language_name": "
|
| 495 |
-
"speakers":
|
| 496 |
-
"bleu":
|
| 497 |
},
|
| 498 |
{
|
| 499 |
-
"model": "
|
| 500 |
"original_language": "eng_Latn",
|
| 501 |
-
"target_language": "
|
| 502 |
-
"target_language_name": "
|
| 503 |
-
"speakers":
|
| 504 |
-
"bleu":
|
| 505 |
},
|
| 506 |
{
|
| 507 |
-
"model": "
|
| 508 |
"original_language": "eng_Latn",
|
| 509 |
-
"target_language": "
|
| 510 |
-
"target_language_name": "
|
| 511 |
-
"speakers":
|
| 512 |
-
"bleu":
|
| 513 |
},
|
| 514 |
{
|
| 515 |
-
"model": "
|
| 516 |
"original_language": "eng_Latn",
|
| 517 |
-
"target_language": "
|
| 518 |
-
"target_language_name": "
|
| 519 |
-
"speakers":
|
| 520 |
-
"bleu":
|
| 521 |
},
|
| 522 |
{
|
| 523 |
-
"model": "
|
| 524 |
"original_language": "eng_Latn",
|
| 525 |
-
"target_language": "
|
| 526 |
-
"target_language_name": "
|
| 527 |
-
"speakers":
|
| 528 |
-
"bleu":
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 529 |
},
|
| 530 |
{
|
| 531 |
"model": "openai/gpt-4o-mini",
|
| 532 |
"original_language": "eng_Latn",
|
| 533 |
-
"target_language": "
|
| 534 |
-
"target_language_name": "
|
| 535 |
-
"speakers":
|
| 536 |
-
"bleu":
|
| 537 |
},
|
| 538 |
{
|
| 539 |
"model": "anthropic/claude-3.5-sonnet",
|
| 540 |
"original_language": "eng_Latn",
|
| 541 |
-
"target_language": "
|
| 542 |
-
"target_language_name": "
|
| 543 |
-
"speakers":
|
| 544 |
-
"bleu":
|
| 545 |
},
|
| 546 |
{
|
| 547 |
"model": "meta-llama/llama-3.1-70b-instruct",
|
| 548 |
"original_language": "eng_Latn",
|
| 549 |
-
"target_language": "
|
| 550 |
-
"target_language_name": "
|
| 551 |
-
"speakers":
|
| 552 |
-
"bleu":
|
| 553 |
},
|
| 554 |
{
|
| 555 |
"model": "mistralai/mistral-nemo",
|
| 556 |
"original_language": "eng_Latn",
|
| 557 |
-
"target_language": "
|
| 558 |
-
"target_language_name": "
|
| 559 |
-
"speakers":
|
| 560 |
-
"bleu":
|
| 561 |
},
|
| 562 |
{
|
| 563 |
-
"model": "
|
| 564 |
"original_language": "eng_Latn",
|
| 565 |
-
"target_language": "
|
| 566 |
-
"target_language_name": "
|
| 567 |
-
"speakers":
|
| 568 |
-
"bleu":
|
| 569 |
},
|
| 570 |
{
|
| 571 |
-
"model": "
|
| 572 |
"original_language": "eng_Latn",
|
| 573 |
-
"target_language": "
|
| 574 |
-
"target_language_name": "
|
| 575 |
-
"speakers":
|
| 576 |
-
"bleu":
|
| 577 |
},
|
| 578 |
{
|
| 579 |
-
"model": "
|
| 580 |
"original_language": "eng_Latn",
|
| 581 |
-
"target_language": "
|
| 582 |
-
"target_language_name": "
|
| 583 |
-
"speakers":
|
| 584 |
-
"bleu":
|
| 585 |
},
|
| 586 |
{
|
| 587 |
"model": "anthropic/claude-3.5-sonnet",
|
| 588 |
"original_language": "eng_Latn",
|
| 589 |
-
"target_language": "
|
| 590 |
-
"target_language_name": "
|
| 591 |
-
"speakers":
|
| 592 |
-
"bleu":
|
| 593 |
},
|
| 594 |
{
|
| 595 |
-
"model": "
|
| 596 |
"original_language": "eng_Latn",
|
| 597 |
-
"target_language": "
|
| 598 |
-
"target_language_name": "
|
| 599 |
-
"speakers":
|
| 600 |
-
"bleu":
|
| 601 |
},
|
| 602 |
{
|
| 603 |
-
"model": "
|
| 604 |
"original_language": "eng_Latn",
|
| 605 |
-
"target_language": "
|
| 606 |
-
"target_language_name": "
|
| 607 |
-
"speakers":
|
| 608 |
-
"bleu": 66.
|
| 609 |
},
|
| 610 |
{
|
| 611 |
-
"model": "
|
| 612 |
"original_language": "eng_Latn",
|
| 613 |
-
"target_language": "
|
| 614 |
-
"target_language_name": "
|
| 615 |
-
"speakers":
|
| 616 |
-
"bleu":
|
| 617 |
},
|
| 618 |
{
|
| 619 |
-
"model": "
|
| 620 |
"original_language": "eng_Latn",
|
| 621 |
-
"target_language": "
|
| 622 |
-
"target_language_name": "
|
| 623 |
-
"speakers":
|
| 624 |
-
"bleu":
|
| 625 |
},
|
| 626 |
{
|
| 627 |
-
"model": "
|
| 628 |
"original_language": "eng_Latn",
|
| 629 |
-
"target_language": "
|
| 630 |
-
"target_language_name": "
|
| 631 |
-
"speakers":
|
| 632 |
-
"bleu":
|
| 633 |
},
|
| 634 |
{
|
| 635 |
"model": "anthropic/claude-3.5-sonnet",
|
| 636 |
"original_language": "eng_Latn",
|
| 637 |
-
"target_language": "
|
| 638 |
-
"target_language_name": "
|
| 639 |
-
"speakers":
|
| 640 |
-
"bleu":
|
| 641 |
},
|
| 642 |
{
|
| 643 |
-
"model": "
|
| 644 |
"original_language": "eng_Latn",
|
| 645 |
-
"target_language": "
|
| 646 |
-
"target_language_name": "
|
| 647 |
-
"speakers":
|
| 648 |
-
"bleu":
|
| 649 |
},
|
| 650 |
{
|
| 651 |
-
"model": "
|
| 652 |
"original_language": "eng_Latn",
|
| 653 |
-
"target_language": "
|
| 654 |
-
"target_language_name": "
|
| 655 |
-
"speakers":
|
| 656 |
-
"bleu":
|
| 657 |
},
|
| 658 |
{
|
| 659 |
-
"model": "
|
| 660 |
"original_language": "eng_Latn",
|
| 661 |
-
"target_language": "
|
| 662 |
-
"target_language_name": "
|
| 663 |
-
"speakers":
|
| 664 |
-
"bleu":
|
| 665 |
},
|
| 666 |
{
|
| 667 |
-
"model": "
|
| 668 |
"original_language": "eng_Latn",
|
| 669 |
-
"target_language": "
|
| 670 |
-
"target_language_name": "
|
| 671 |
-
"speakers":
|
| 672 |
-
"bleu":
|
| 673 |
},
|
| 674 |
{
|
| 675 |
-
"model": "
|
| 676 |
"original_language": "eng_Latn",
|
| 677 |
-
"target_language": "
|
| 678 |
-
"target_language_name": "
|
| 679 |
-
"speakers":
|
| 680 |
-
"bleu":
|
| 681 |
},
|
| 682 |
{
|
| 683 |
"model": "anthropic/claude-3.5-sonnet",
|
| 684 |
"original_language": "eng_Latn",
|
| 685 |
-
"target_language": "
|
| 686 |
-
"target_language_name": "
|
| 687 |
-
"speakers":
|
| 688 |
-
"bleu":
|
| 689 |
},
|
| 690 |
{
|
| 691 |
-
"model": "
|
| 692 |
"original_language": "eng_Latn",
|
| 693 |
-
"target_language": "
|
| 694 |
-
"target_language_name": "
|
| 695 |
-
"speakers":
|
| 696 |
-
"bleu":
|
| 697 |
},
|
| 698 |
{
|
| 699 |
-
"model": "
|
| 700 |
"original_language": "eng_Latn",
|
| 701 |
-
"target_language": "
|
| 702 |
-
"target_language_name": "
|
| 703 |
-
"speakers":
|
| 704 |
-
"bleu":
|
| 705 |
},
|
| 706 |
{
|
| 707 |
-
"model": "
|
| 708 |
"original_language": "eng_Latn",
|
| 709 |
-
"target_language": "
|
| 710 |
-
"target_language_name": "
|
| 711 |
-
"speakers":
|
| 712 |
-
"bleu":
|
| 713 |
},
|
| 714 |
{
|
| 715 |
-
"model": "
|
| 716 |
"original_language": "eng_Latn",
|
| 717 |
-
"target_language": "
|
| 718 |
-
"target_language_name": "
|
| 719 |
-
"speakers":
|
| 720 |
-
"bleu":
|
| 721 |
},
|
| 722 |
{
|
| 723 |
-
"model": "
|
| 724 |
"original_language": "eng_Latn",
|
| 725 |
-
"target_language": "
|
| 726 |
-
"target_language_name": "
|
| 727 |
-
"speakers":
|
| 728 |
-
"bleu":
|
| 729 |
},
|
| 730 |
{
|
| 731 |
"model": "anthropic/claude-3.5-sonnet",
|
| 732 |
"original_language": "eng_Latn",
|
| 733 |
-
"target_language": "
|
| 734 |
-
"target_language_name": "
|
| 735 |
-
"speakers":
|
| 736 |
-
"bleu":
|
| 737 |
},
|
| 738 |
{
|
| 739 |
-
"model": "
|
| 740 |
"original_language": "eng_Latn",
|
| 741 |
-
"target_language": "
|
| 742 |
-
"target_language_name": "
|
| 743 |
-
"speakers":
|
| 744 |
-
"bleu":
|
| 745 |
},
|
| 746 |
{
|
| 747 |
-
"model": "
|
| 748 |
"original_language": "eng_Latn",
|
| 749 |
-
"target_language": "
|
| 750 |
-
"target_language_name": "
|
| 751 |
-
"speakers":
|
| 752 |
-
"bleu":
|
| 753 |
},
|
| 754 |
{
|
| 755 |
-
"model": "
|
| 756 |
"original_language": "eng_Latn",
|
| 757 |
-
"target_language": "
|
| 758 |
-
"target_language_name": "
|
| 759 |
-
"speakers":
|
| 760 |
-
"bleu":
|
| 761 |
},
|
| 762 |
{
|
| 763 |
-
"model": "
|
| 764 |
"original_language": "eng_Latn",
|
| 765 |
-
"target_language": "
|
| 766 |
-
"target_language_name": "
|
| 767 |
-
"speakers":
|
| 768 |
-
"bleu":
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 769 |
}
|
| 770 |
]
|
|
|
|
| 1 |
[
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 2 |
{
|
| 3 |
"model": "anthropic/claude-3.5-sonnet",
|
| 4 |
"original_language": "eng_Latn",
|
| 5 |
+
"target_language": "tur_Latn",
|
| 6 |
+
"target_language_name": "Turkish",
|
| 7 |
+
"speakers": 82231620,
|
| 8 |
+
"bleu": 67.16006256755001
|
| 9 |
},
|
| 10 |
{
|
| 11 |
+
"model": "anthropic/claude-3.5-sonnet",
|
| 12 |
"original_language": "eng_Latn",
|
| 13 |
+
"target_language": "ary_Arab",
|
| 14 |
+
"target_language_name": " Moroccan Arabic",
|
| 15 |
+
"speakers": 27500000,
|
| 16 |
+
"bleu": 48.56078739780091
|
| 17 |
},
|
| 18 |
{
|
| 19 |
+
"model": "anthropic/claude-3.5-sonnet",
|
| 20 |
"original_language": "eng_Latn",
|
| 21 |
+
"target_language": "fij_Latn",
|
| 22 |
+
"target_language_name": "Fijian",
|
| 23 |
+
"speakers": 341270,
|
| 24 |
+
"bleu": 58.28926672457303
|
| 25 |
},
|
| 26 |
{
|
| 27 |
+
"model": "anthropic/claude-3.5-sonnet",
|
| 28 |
"original_language": "eng_Latn",
|
| 29 |
+
"target_language": "lug_Latn",
|
| 30 |
+
"target_language_name": "Ganda",
|
| 31 |
+
"speakers": 4100000,
|
| 32 |
+
"bleu": 45.86933229358203
|
| 33 |
},
|
| 34 |
{
|
| 35 |
+
"model": "anthropic/claude-3.5-sonnet",
|
| 36 |
"original_language": "eng_Latn",
|
| 37 |
+
"target_language": "kin_Latn",
|
| 38 |
+
"target_language_name": "Kinyarwanda",
|
| 39 |
+
"speakers": 12100000,
|
| 40 |
+
"bleu": 57.241062675597036
|
| 41 |
},
|
| 42 |
{
|
| 43 |
"model": "openai/gpt-4o-mini",
|
|
|
|
| 45 |
"target_language": "ind_Latn",
|
| 46 |
"target_language_name": "Indonesian",
|
| 47 |
"speakers": 198996550,
|
| 48 |
+
"bleu": 76.69607051201163
|
| 49 |
},
|
| 50 |
{
|
| 51 |
"model": "anthropic/claude-3.5-sonnet",
|
|
|
|
| 53 |
"target_language": "ind_Latn",
|
| 54 |
"target_language_name": "Indonesian",
|
| 55 |
"speakers": 198996550,
|
| 56 |
+
"bleu": 75.20007995551391
|
| 57 |
},
|
| 58 |
{
|
| 59 |
"model": "meta-llama/llama-3.1-70b-instruct",
|
|
|
|
| 61 |
"target_language": "ind_Latn",
|
| 62 |
"target_language_name": "Indonesian",
|
| 63 |
"speakers": 198996550,
|
| 64 |
+
"bleu": 74.1959714053824
|
| 65 |
},
|
| 66 |
{
|
| 67 |
"model": "mistralai/mistral-nemo",
|
|
|
|
| 69 |
"target_language": "ind_Latn",
|
| 70 |
"target_language_name": "Indonesian",
|
| 71 |
"speakers": 198996550,
|
| 72 |
+
"bleu": 65.59558256613556
|
| 73 |
},
|
| 74 |
{
|
| 75 |
+
"model": "qwen/qwen-2.5-72b-instruct",
|
| 76 |
"original_language": "eng_Latn",
|
| 77 |
"target_language": "ind_Latn",
|
| 78 |
"target_language_name": "Indonesian",
|
| 79 |
"speakers": 198996550,
|
| 80 |
+
"bleu": 72.85582869172275
|
| 81 |
},
|
| 82 |
{
|
| 83 |
+
"model": "anthropic/claude-3.5-sonnet",
|
| 84 |
"original_language": "eng_Latn",
|
| 85 |
+
"target_language": "nus_Latn",
|
| 86 |
+
"target_language_name": "Nuer",
|
| 87 |
+
"speakers": 900000,
|
| 88 |
+
"bleu": 16.57969879511241
|
| 89 |
},
|
| 90 |
{
|
| 91 |
+
"model": "anthropic/claude-3.5-sonnet",
|
| 92 |
"original_language": "eng_Latn",
|
| 93 |
+
"target_language": "szl_Latn",
|
| 94 |
+
"target_language_name": "Silesian",
|
| 95 |
+
"speakers": 522000,
|
| 96 |
+
"bleu": 56.78363920686616
|
| 97 |
},
|
| 98 |
{
|
| 99 |
"model": "anthropic/claude-3.5-sonnet",
|
| 100 |
"original_language": "eng_Latn",
|
| 101 |
+
"target_language": "azj_Latn",
|
| 102 |
+
"target_language_name": " North Azerbaijani",
|
| 103 |
+
"speakers": 9220610,
|
| 104 |
+
"bleu": 55.00459613512087
|
| 105 |
},
|
| 106 |
{
|
| 107 |
+
"model": "anthropic/claude-3.5-sonnet",
|
| 108 |
"original_language": "eng_Latn",
|
| 109 |
+
"target_language": "dik_Latn",
|
| 110 |
+
"target_language_name": " Southwestern Dinka",
|
| 111 |
+
"speakers": 0,
|
| 112 |
+
"bleu": 12.497832051373198
|
| 113 |
},
|
| 114 |
{
|
| 115 |
+
"model": "anthropic/claude-3.5-sonnet",
|
| 116 |
"original_language": "eng_Latn",
|
| 117 |
+
"target_language": "smo_Latn",
|
| 118 |
+
"target_language_name": "Samoan",
|
| 119 |
+
"speakers": 415720,
|
| 120 |
+
"bleu": 56.71388314225869
|
| 121 |
},
|
| 122 |
{
|
| 123 |
+
"model": "anthropic/claude-3.5-sonnet",
|
| 124 |
"original_language": "eng_Latn",
|
| 125 |
+
"target_language": "heb_Hebr",
|
| 126 |
+
"target_language_name": "Hebrew",
|
| 127 |
+
"speakers": 9303950,
|
| 128 |
+
"bleu": 72.0702990513479
|
| 129 |
},
|
| 130 |
{
|
| 131 |
+
"model": "anthropic/claude-3.5-sonnet",
|
| 132 |
"original_language": "eng_Latn",
|
| 133 |
+
"target_language": "lao_Laoo",
|
| 134 |
+
"target_language_name": "Lao",
|
| 135 |
+
"speakers": 5225552,
|
| 136 |
+
"bleu": 60.02109096770294
|
| 137 |
},
|
| 138 |
{
|
| 139 |
+
"model": "anthropic/claude-3.5-sonnet",
|
| 140 |
"original_language": "eng_Latn",
|
| 141 |
+
"target_language": "bul_Cyrl",
|
| 142 |
+
"target_language_name": "Bulgarian",
|
| 143 |
+
"speakers": 9000000,
|
| 144 |
+
"bleu": 72.9695925130979
|
| 145 |
},
|
| 146 |
{
|
| 147 |
"model": "anthropic/claude-3.5-sonnet",
|
| 148 |
"original_language": "eng_Latn",
|
| 149 |
+
"target_language": "dgo_Deva",
|
| 150 |
+
"target_language_name": "Dogri",
|
| 151 |
+
"speakers": 2000000,
|
| 152 |
+
"bleu": 44.91535352779186
|
| 153 |
},
|
| 154 |
{
|
| 155 |
+
"model": "anthropic/claude-3.5-sonnet",
|
| 156 |
"original_language": "eng_Latn",
|
| 157 |
+
"target_language": "epo_Latn",
|
| 158 |
+
"target_language_name": "Esperanto",
|
| 159 |
+
"speakers": 2000000,
|
| 160 |
+
"bleu": 69.60565775541012
|
| 161 |
},
|
| 162 |
{
|
| 163 |
+
"model": "anthropic/claude-3.5-sonnet",
|
| 164 |
"original_language": "eng_Latn",
|
| 165 |
+
"target_language": "azb_Arab",
|
| 166 |
+
"target_language_name": " South Azerbaijani",
|
| 167 |
+
"speakers": 15000000,
|
| 168 |
+
"bleu": 43.53622667084785
|
| 169 |
},
|
| 170 |
{
|
| 171 |
+
"model": "anthropic/claude-3.5-sonnet",
|
| 172 |
"original_language": "eng_Latn",
|
| 173 |
+
"target_language": "pap_Latn",
|
| 174 |
+
"target_language_name": "Papiamentu",
|
| 175 |
+
"speakers": 321300,
|
| 176 |
+
"bleu": 69.79553281331113
|
| 177 |
},
|
| 178 |
{
|
| 179 |
+
"model": "anthropic/claude-3.5-sonnet",
|
| 180 |
"original_language": "eng_Latn",
|
| 181 |
+
"target_language": "ces_Latn",
|
| 182 |
+
"target_language_name": "Czech",
|
| 183 |
+
"speakers": 10700000,
|
| 184 |
+
"bleu": 69.71122905993063
|
| 185 |
},
|
| 186 |
{
|
| 187 |
+
"model": "anthropic/claude-3.5-sonnet",
|
| 188 |
"original_language": "eng_Latn",
|
| 189 |
+
"target_language": "gle_Latn",
|
| 190 |
+
"target_language_name": "Irish",
|
| 191 |
+
"speakers": 1030000,
|
| 192 |
+
"bleu": 69.97251945242859
|
| 193 |
},
|
| 194 |
{
|
| 195 |
"model": "anthropic/claude-3.5-sonnet",
|
| 196 |
"original_language": "eng_Latn",
|
| 197 |
+
"target_language": "cym_Latn",
|
| 198 |
+
"target_language_name": "Welsh",
|
| 199 |
+
"speakers": 977366,
|
| 200 |
+
"bleu": 83.34377244735965
|
| 201 |
},
|
| 202 |
{
|
| 203 |
+
"model": "anthropic/claude-3.5-sonnet",
|
| 204 |
"original_language": "eng_Latn",
|
| 205 |
+
"target_language": "war_Latn",
|
| 206 |
+
"target_language_name": "Waray-Waray",
|
| 207 |
+
"speakers": 3100000,
|
| 208 |
+
"bleu": 66.38502312428538
|
| 209 |
},
|
| 210 |
{
|
| 211 |
+
"model": "anthropic/claude-3.5-sonnet",
|
| 212 |
"original_language": "eng_Latn",
|
| 213 |
+
"target_language": "tuk_Latn",
|
| 214 |
+
"target_language_name": "Turkmen",
|
| 215 |
+
"speakers": 16000000,
|
| 216 |
+
"bleu": 60.559370593640274
|
| 217 |
},
|
| 218 |
{
|
| 219 |
+
"model": "anthropic/claude-3.5-sonnet",
|
| 220 |
"original_language": "eng_Latn",
|
| 221 |
+
"target_language": "kea_Latn",
|
| 222 |
+
"target_language_name": "Kabuverdianu",
|
| 223 |
+
"speakers": 871000,
|
| 224 |
+
"bleu": 65.11060103907447
|
| 225 |
},
|
| 226 |
{
|
| 227 |
+
"model": "anthropic/claude-3.5-sonnet",
|
| 228 |
"original_language": "eng_Latn",
|
| 229 |
+
"target_language": "swe_Latn",
|
| 230 |
+
"target_language_name": "Swedish",
|
| 231 |
+
"speakers": 9244250,
|
| 232 |
+
"bleu": 77.42161024703672
|
| 233 |
},
|
| 234 |
{
|
| 235 |
+
"model": "anthropic/claude-3.5-sonnet",
|
| 236 |
"original_language": "eng_Latn",
|
| 237 |
+
"target_language": "mni_Mtei",
|
| 238 |
+
"target_language_name": "Meitei",
|
| 239 |
+
"speakers": 1470000,
|
| 240 |
+
"bleu": 41.90750872077243
|
| 241 |
},
|
| 242 |
{
|
| 243 |
"model": "anthropic/claude-3.5-sonnet",
|
| 244 |
"original_language": "eng_Latn",
|
| 245 |
+
"target_language": "kan_Knda",
|
| 246 |
+
"target_language_name": "Kannada",
|
| 247 |
+
"speakers": 43600000,
|
| 248 |
+
"bleu": 60.01420283321725
|
| 249 |
},
|
| 250 |
{
|
| 251 |
+
"model": "anthropic/claude-3.5-sonnet",
|
| 252 |
"original_language": "eng_Latn",
|
| 253 |
+
"target_language": "plt_Latn",
|
| 254 |
+
"target_language_name": " Merina Malagasy",
|
| 255 |
+
"speakers": 0,
|
| 256 |
+
"bleu": 60.430438804745
|
| 257 |
},
|
| 258 |
{
|
| 259 |
+
"model": "anthropic/claude-3.5-sonnet",
|
| 260 |
"original_language": "eng_Latn",
|
| 261 |
+
"target_language": "ewe_Latn",
|
| 262 |
+
"target_language_name": "Éwé",
|
| 263 |
+
"speakers": 3000000,
|
| 264 |
+
"bleu": 41.6614038790914
|
| 265 |
},
|
| 266 |
{
|
| 267 |
+
"model": "anthropic/claude-3.5-sonnet",
|
| 268 |
"original_language": "eng_Latn",
|
| 269 |
+
"target_language": "rus_Cyrl",
|
| 270 |
+
"target_language_name": "Russian",
|
| 271 |
+
"speakers": 171428900,
|
| 272 |
+
"bleu": 71.14894410390329
|
| 273 |
},
|
| 274 |
{
|
| 275 |
+
"model": "anthropic/claude-3.5-sonnet",
|
| 276 |
"original_language": "eng_Latn",
|
| 277 |
+
"target_language": "bjn_Arab",
|
| 278 |
"target_language_name": "Banjar",
|
| 279 |
"speakers": 3500000,
|
| 280 |
+
"bleu": 36.7812759423696
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 281 |
},
|
| 282 |
{
|
| 283 |
"model": "anthropic/claude-3.5-sonnet",
|
| 284 |
"original_language": "eng_Latn",
|
| 285 |
+
"target_language": "kmb_Latn",
|
| 286 |
+
"target_language_name": "Kimbundu",
|
| 287 |
+
"speakers": 0,
|
| 288 |
+
"bleu": 5.85234572235619
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 289 |
},
|
| 290 |
{
|
| 291 |
+
"model": "anthropic/claude-3.5-sonnet",
|
| 292 |
"original_language": "eng_Latn",
|
| 293 |
+
"target_language": "vec_Latn",
|
| 294 |
+
"target_language_name": "Venetian",
|
| 295 |
+
"speakers": 2000000,
|
| 296 |
+
"bleu": 60.61408762705794
|
| 297 |
},
|
| 298 |
{
|
| 299 |
+
"model": "anthropic/claude-3.5-sonnet",
|
| 300 |
"original_language": "eng_Latn",
|
| 301 |
+
"target_language": "aeb_Arab",
|
| 302 |
+
"target_language_name": " Tunisian Arabic",
|
| 303 |
+
"speakers": 11600000,
|
| 304 |
+
"bleu": 49.87359800112665
|
| 305 |
},
|
| 306 |
{
|
| 307 |
+
"model": "anthropic/claude-3.5-sonnet",
|
| 308 |
"original_language": "eng_Latn",
|
| 309 |
+
"target_language": "lit_Latn",
|
| 310 |
+
"target_language_name": "Lithuanian",
|
| 311 |
+
"speakers": 4000000,
|
| 312 |
+
"bleu": 67.16256955707802
|
| 313 |
},
|
| 314 |
{
|
| 315 |
+
"model": "anthropic/claude-3.5-sonnet",
|
| 316 |
"original_language": "eng_Latn",
|
| 317 |
+
"target_language": "swh_Latn",
|
| 318 |
+
"target_language_name": "Swahili",
|
| 319 |
+
"speakers": 82300000,
|
| 320 |
+
"bleu": 73.51990421418041
|
| 321 |
},
|
| 322 |
{
|
| 323 |
"model": "anthropic/claude-3.5-sonnet",
|
| 324 |
"original_language": "eng_Latn",
|
| 325 |
+
"target_language": "bug_Latn",
|
| 326 |
+
"target_language_name": "Bugis",
|
| 327 |
+
"speakers": 5017800,
|
| 328 |
+
"bleu": 44.838817003109384
|
| 329 |
},
|
| 330 |
{
|
| 331 |
+
"model": "anthropic/claude-3.5-sonnet",
|
| 332 |
"original_language": "eng_Latn",
|
| 333 |
+
"target_language": "apc_Arab_nort3139",
|
| 334 |
+
"target_language_name": " Levantine Arabic",
|
| 335 |
+
"speakers": 44000000,
|
| 336 |
+
"bleu": 56.66525774941823
|
| 337 |
},
|
| 338 |
{
|
| 339 |
+
"model": "anthropic/claude-3.5-sonnet",
|
| 340 |
"original_language": "eng_Latn",
|
| 341 |
+
"target_language": "lus_Latn",
|
| 342 |
+
"target_language_name": "Mizo",
|
| 343 |
+
"speakers": 500000,
|
| 344 |
+
"bleu": 51.65580174875804
|
| 345 |
},
|
| 346 |
{
|
| 347 |
+
"model": "anthropic/claude-3.5-sonnet",
|
| 348 |
"original_language": "eng_Latn",
|
| 349 |
+
"target_language": "lim_Latn",
|
| 350 |
+
"target_language_name": "Limburgish",
|
| 351 |
+
"speakers": 1600000,
|
| 352 |
+
"bleu": 59.44855049817084
|
| 353 |
},
|
| 354 |
{
|
| 355 |
+
"model": "anthropic/claude-3.5-sonnet",
|
| 356 |
"original_language": "eng_Latn",
|
| 357 |
+
"target_language": "mri_Latn",
|
| 358 |
+
"target_language_name": "Maori",
|
| 359 |
+
"speakers": 160000,
|
| 360 |
+
"bleu": 54.831993564329125
|
| 361 |
},
|
| 362 |
{
|
| 363 |
+
"model": "anthropic/claude-3.5-sonnet",
|
| 364 |
"original_language": "eng_Latn",
|
| 365 |
+
"target_language": "kam_Latn",
|
| 366 |
+
"target_language_name": "Kamba",
|
| 367 |
+
"speakers": 3893000,
|
| 368 |
+
"bleu": 41.73348967095708
|
| 369 |
},
|
| 370 |
{
|
| 371 |
"model": "anthropic/claude-3.5-sonnet",
|
| 372 |
"original_language": "eng_Latn",
|
| 373 |
+
"target_language": "ban_Latn",
|
| 374 |
+
"target_language_name": "Bali (Indonesia)",
|
| 375 |
+
"speakers": 4000000,
|
| 376 |
+
"bleu": 52.87524191594727
|
| 377 |
},
|
| 378 |
{
|
| 379 |
+
"model": "anthropic/claude-3.5-sonnet",
|
| 380 |
"original_language": "eng_Latn",
|
| 381 |
+
"target_language": "pan_Guru",
|
| 382 |
+
"target_language_name": " Eastern Punjabi",
|
| 383 |
+
"speakers": 125000000,
|
| 384 |
+
"bleu": 60.833539867728966
|
| 385 |
},
|
| 386 |
{
|
| 387 |
+
"model": "anthropic/claude-3.5-sonnet",
|
| 388 |
"original_language": "eng_Latn",
|
| 389 |
+
"target_language": "por_Latn",
|
| 390 |
+
"target_language_name": "Portuguese",
|
| 391 |
+
"speakers": 254300000,
|
| 392 |
+
"bleu": 77.49780742224304
|
| 393 |
},
|
| 394 |
{
|
| 395 |
+
"model": "anthropic/claude-3.5-sonnet",
|
| 396 |
"original_language": "eng_Latn",
|
| 397 |
+
"target_language": "crh_Latn",
|
| 398 |
+
"target_language_name": "Crimean Tatar",
|
| 399 |
+
"speakers": 552740,
|
| 400 |
+
"bleu": 52.705024944759934
|
| 401 |
},
|
| 402 |
{
|
| 403 |
+
"model": "anthropic/claude-3.5-sonnet",
|
| 404 |
"original_language": "eng_Latn",
|
| 405 |
+
"target_language": "srp_Cyrl",
|
| 406 |
+
"target_language_name": "Serbian",
|
| 407 |
+
"speakers": 9000000,
|
| 408 |
+
"bleu": 69.96913961762156
|
| 409 |
},
|
| 410 |
{
|
| 411 |
"model": "openai/gpt-4o-mini",
|
| 412 |
"original_language": "eng_Latn",
|
| 413 |
+
"target_language": "kas_Deva",
|
| 414 |
+
"target_language_name": "Kashmiri",
|
| 415 |
+
"speakers": 6900000,
|
| 416 |
+
"bleu": 22.94872648513265
|
| 417 |
},
|
| 418 |
{
|
| 419 |
"model": "anthropic/claude-3.5-sonnet",
|
| 420 |
"original_language": "eng_Latn",
|
| 421 |
+
"target_language": "kas_Deva",
|
| 422 |
+
"target_language_name": "Kashmiri",
|
| 423 |
+
"speakers": 6900000,
|
| 424 |
+
"bleu": 27.525562771983658
|
| 425 |
},
|
| 426 |
{
|
| 427 |
"model": "meta-llama/llama-3.1-70b-instruct",
|
| 428 |
"original_language": "eng_Latn",
|
| 429 |
+
"target_language": "kas_Deva",
|
| 430 |
+
"target_language_name": "Kashmiri",
|
| 431 |
+
"speakers": 6900000,
|
| 432 |
+
"bleu": 7.999053096113321
|
| 433 |
},
|
| 434 |
{
|
| 435 |
"model": "mistralai/mistral-nemo",
|
| 436 |
"original_language": "eng_Latn",
|
| 437 |
+
"target_language": "kas_Deva",
|
| 438 |
+
"target_language_name": "Kashmiri",
|
| 439 |
+
"speakers": 6900000,
|
| 440 |
+
"bleu": 15.126083511737422
|
| 441 |
},
|
| 442 |
{
|
| 443 |
+
"model": "qwen/qwen-2.5-72b-instruct",
|
| 444 |
"original_language": "eng_Latn",
|
| 445 |
+
"target_language": "kas_Deva",
|
| 446 |
+
"target_language_name": "Kashmiri",
|
| 447 |
+
"speakers": 6900000,
|
| 448 |
+
"bleu": 21.928943407791756
|
| 449 |
},
|
| 450 |
{
|
| 451 |
+
"model": "anthropic/claude-3.5-sonnet",
|
| 452 |
"original_language": "eng_Latn",
|
| 453 |
+
"target_language": "bod_Tibt",
|
| 454 |
+
"target_language_name": " Central Tibetan",
|
| 455 |
+
"speakers": 1200000,
|
| 456 |
+
"bleu": 51.76205985600136
|
| 457 |
},
|
| 458 |
{
|
| 459 |
+
"model": "anthropic/claude-3.5-sonnet",
|
| 460 |
"original_language": "eng_Latn",
|
| 461 |
+
"target_language": "slv_Latn",
|
| 462 |
+
"target_language_name": "Slovene",
|
| 463 |
+
"speakers": 2400000,
|
| 464 |
+
"bleu": 72.56912707571306
|
| 465 |
},
|
| 466 |
{
|
| 467 |
"model": "anthropic/claude-3.5-sonnet",
|
| 468 |
"original_language": "eng_Latn",
|
| 469 |
+
"target_language": "ars_Arab",
|
| 470 |
+
"target_language_name": " Najdi Arabic",
|
| 471 |
+
"speakers": 0,
|
| 472 |
+
"bleu": 47.7692581451387
|
| 473 |
},
|
| 474 |
{
|
| 475 |
+
"model": "anthropic/claude-3.5-sonnet",
|
| 476 |
"original_language": "eng_Latn",
|
| 477 |
+
"target_language": "cat_Latn",
|
| 478 |
+
"target_language_name": "Catalan",
|
| 479 |
+
"speakers": 5100000,
|
| 480 |
+
"bleu": 74.45950079317922
|
| 481 |
},
|
| 482 |
{
|
| 483 |
+
"model": "anthropic/claude-3.5-sonnet",
|
| 484 |
"original_language": "eng_Latn",
|
| 485 |
+
"target_language": "zul_Latn",
|
| 486 |
+
"target_language_name": "Zulu",
|
| 487 |
+
"speakers": 15700000,
|
| 488 |
+
"bleu": 59.176207838896076
|
| 489 |
},
|
| 490 |
{
|
| 491 |
+
"model": "anthropic/claude-3.5-sonnet",
|
| 492 |
"original_language": "eng_Latn",
|
| 493 |
+
"target_language": "pes_Arab",
|
| 494 |
+
"target_language_name": " Iranian Persian",
|
| 495 |
+
"speakers": 52800000,
|
| 496 |
+
"bleu": 57.466690672020064
|
| 497 |
},
|
| 498 |
{
|
| 499 |
+
"model": "anthropic/claude-3.5-sonnet",
|
| 500 |
"original_language": "eng_Latn",
|
| 501 |
+
"target_language": "taq_Latn",
|
| 502 |
+
"target_language_name": "Tamasheq",
|
| 503 |
+
"speakers": 500000,
|
| 504 |
+
"bleu": 25.866944911127725
|
| 505 |
+
},
|
| 506 |
+
{
|
| 507 |
+
"model": "anthropic/claude-3.5-sonnet",
|
| 508 |
+
"original_language": "eng_Latn",
|
| 509 |
+
"target_language": "snd_Deva",
|
| 510 |
+
"target_language_name": "Sindhi",
|
| 511 |
+
"speakers": 25000000,
|
| 512 |
+
"bleu": 40.04493401977834
|
| 513 |
+
},
|
| 514 |
+
{
|
| 515 |
+
"model": "anthropic/claude-3.5-sonnet",
|
| 516 |
+
"original_language": "eng_Latn",
|
| 517 |
+
"target_language": "ssw_Latn",
|
| 518 |
+
"target_language_name": "Swati",
|
| 519 |
+
"speakers": 2034200,
|
| 520 |
+
"bleu": 52.77460964391619
|
| 521 |
+
},
|
| 522 |
+
{
|
| 523 |
+
"model": "anthropic/claude-3.5-sonnet",
|
| 524 |
+
"original_language": "eng_Latn",
|
| 525 |
+
"target_language": "mkd_Cyrl",
|
| 526 |
+
"target_language_name": "Macedonian",
|
| 527 |
+
"speakers": 2000000,
|
| 528 |
+
"bleu": 72.27334714365769
|
| 529 |
},
|
| 530 |
{
|
| 531 |
"model": "openai/gpt-4o-mini",
|
| 532 |
"original_language": "eng_Latn",
|
| 533 |
+
"target_language": "pol_Latn",
|
| 534 |
+
"target_language_name": "Polish",
|
| 535 |
+
"speakers": 40200000,
|
| 536 |
+
"bleu": 63.79524354957938
|
| 537 |
},
|
| 538 |
{
|
| 539 |
"model": "anthropic/claude-3.5-sonnet",
|
| 540 |
"original_language": "eng_Latn",
|
| 541 |
+
"target_language": "pol_Latn",
|
| 542 |
+
"target_language_name": "Polish",
|
| 543 |
+
"speakers": 40200000,
|
| 544 |
+
"bleu": 65.97562270518736
|
| 545 |
},
|
| 546 |
{
|
| 547 |
"model": "meta-llama/llama-3.1-70b-instruct",
|
| 548 |
"original_language": "eng_Latn",
|
| 549 |
+
"target_language": "pol_Latn",
|
| 550 |
+
"target_language_name": "Polish",
|
| 551 |
+
"speakers": 40200000,
|
| 552 |
+
"bleu": 62.09512880944625
|
| 553 |
},
|
| 554 |
{
|
| 555 |
"model": "mistralai/mistral-nemo",
|
| 556 |
"original_language": "eng_Latn",
|
| 557 |
+
"target_language": "pol_Latn",
|
| 558 |
+
"target_language_name": "Polish",
|
| 559 |
+
"speakers": 40200000,
|
| 560 |
+
"bleu": 56.42877796144466
|
| 561 |
},
|
| 562 |
{
|
| 563 |
+
"model": "qwen/qwen-2.5-72b-instruct",
|
| 564 |
"original_language": "eng_Latn",
|
| 565 |
+
"target_language": "pol_Latn",
|
| 566 |
+
"target_language_name": "Polish",
|
| 567 |
+
"speakers": 40200000,
|
| 568 |
+
"bleu": 61.08942681151859
|
| 569 |
},
|
| 570 |
{
|
| 571 |
+
"model": "anthropic/claude-3.5-sonnet",
|
| 572 |
"original_language": "eng_Latn",
|
| 573 |
+
"target_language": "srd_Latn",
|
| 574 |
+
"target_language_name": "Sardinian",
|
| 575 |
+
"speakers": 1300000,
|
| 576 |
+
"bleu": 62.69039147714039
|
| 577 |
},
|
| 578 |
{
|
| 579 |
+
"model": "anthropic/claude-3.5-sonnet",
|
| 580 |
"original_language": "eng_Latn",
|
| 581 |
+
"target_language": "arb_Latn",
|
| 582 |
+
"target_language_name": " Standard Arabic",
|
| 583 |
+
"speakers": 0,
|
| 584 |
+
"bleu": 47.790331753697075
|
| 585 |
},
|
| 586 |
{
|
| 587 |
"model": "anthropic/claude-3.5-sonnet",
|
| 588 |
"original_language": "eng_Latn",
|
| 589 |
+
"target_language": "twi_Latn_asan1239",
|
| 590 |
+
"target_language_name": "Twi",
|
| 591 |
+
"speakers": 3000000,
|
| 592 |
+
"bleu": 44.44337481309101
|
| 593 |
},
|
| 594 |
{
|
| 595 |
+
"model": "anthropic/claude-3.5-sonnet",
|
| 596 |
"original_language": "eng_Latn",
|
| 597 |
+
"target_language": "tum_Latn",
|
| 598 |
+
"target_language_name": "Tumbuka",
|
| 599 |
+
"speakers": 2680000,
|
| 600 |
+
"bleu": 44.0490017392109
|
| 601 |
},
|
| 602 |
{
|
| 603 |
+
"model": "anthropic/claude-3.5-sonnet",
|
| 604 |
"original_language": "eng_Latn",
|
| 605 |
+
"target_language": "fur_Latn",
|
| 606 |
+
"target_language_name": "Friulian",
|
| 607 |
+
"speakers": 300000,
|
| 608 |
+
"bleu": 66.54880923723718
|
| 609 |
},
|
| 610 |
{
|
| 611 |
+
"model": "anthropic/claude-3.5-sonnet",
|
| 612 |
"original_language": "eng_Latn",
|
| 613 |
+
"target_language": "lua_Latn",
|
| 614 |
+
"target_language_name": "Luba-Kasai",
|
| 615 |
+
"speakers": 6300000,
|
| 616 |
+
"bleu": 45.065529165477344
|
| 617 |
},
|
| 618 |
{
|
| 619 |
+
"model": "anthropic/claude-3.5-sonnet",
|
| 620 |
"original_language": "eng_Latn",
|
| 621 |
+
"target_language": "fil_Latn",
|
| 622 |
+
"target_language_name": "Filipino",
|
| 623 |
+
"speakers": 90000000,
|
| 624 |
+
"bleu": 70.19284983784472
|
| 625 |
},
|
| 626 |
{
|
| 627 |
+
"model": "anthropic/claude-3.5-sonnet",
|
| 628 |
"original_language": "eng_Latn",
|
| 629 |
+
"target_language": "afr_Latn",
|
| 630 |
+
"target_language_name": "Afrikaans",
|
| 631 |
+
"speakers": 10300000,
|
| 632 |
+
"bleu": 76.89005407773752
|
| 633 |
},
|
| 634 |
{
|
| 635 |
"model": "anthropic/claude-3.5-sonnet",
|
| 636 |
"original_language": "eng_Latn",
|
| 637 |
+
"target_language": "bos_Latn",
|
| 638 |
+
"target_language_name": "Bosnian",
|
| 639 |
+
"speakers": 3500000,
|
| 640 |
+
"bleu": 72.54880271311463
|
| 641 |
},
|
| 642 |
{
|
| 643 |
+
"model": "anthropic/claude-3.5-sonnet",
|
| 644 |
"original_language": "eng_Latn",
|
| 645 |
+
"target_language": "ltg_Latn",
|
| 646 |
+
"target_language_name": "Latgalian",
|
| 647 |
+
"speakers": 200000,
|
| 648 |
+
"bleu": 56.484355652391756
|
| 649 |
},
|
| 650 |
{
|
| 651 |
+
"model": "anthropic/claude-3.5-sonnet",
|
| 652 |
"original_language": "eng_Latn",
|
| 653 |
+
"target_language": "acq_Arab",
|
| 654 |
+
"target_language_name": " Ta’izzi-Adeni Arabic",
|
| 655 |
+
"speakers": 10500000,
|
| 656 |
+
"bleu": 48.67285742584471
|
| 657 |
},
|
| 658 |
{
|
| 659 |
+
"model": "anthropic/claude-3.5-sonnet",
|
| 660 |
"original_language": "eng_Latn",
|
| 661 |
+
"target_language": "mag_Deva",
|
| 662 |
+
"target_language_name": "Magahi",
|
| 663 |
+
"speakers": 20700000,
|
| 664 |
+
"bleu": 58.54742215461198
|
| 665 |
},
|
| 666 |
{
|
| 667 |
+
"model": "anthropic/claude-3.5-sonnet",
|
| 668 |
"original_language": "eng_Latn",
|
| 669 |
+
"target_language": "min_Latn",
|
| 670 |
+
"target_language_name": "Minangkabau",
|
| 671 |
+
"speakers": 5530000,
|
| 672 |
+
"bleu": 64.0323403919738
|
| 673 |
},
|
| 674 |
{
|
| 675 |
+
"model": "anthropic/claude-3.5-sonnet",
|
| 676 |
"original_language": "eng_Latn",
|
| 677 |
+
"target_language": "kor_Hang",
|
| 678 |
+
"target_language_name": "Korean",
|
| 679 |
+
"speakers": 77300000,
|
| 680 |
+
"bleu": 43.68722859743311
|
| 681 |
},
|
| 682 |
{
|
| 683 |
"model": "anthropic/claude-3.5-sonnet",
|
| 684 |
"original_language": "eng_Latn",
|
| 685 |
+
"target_language": "zsm_Latn",
|
| 686 |
+
"target_language_name": " Standard Malay",
|
| 687 |
+
"speakers": 0,
|
| 688 |
+
"bleu": 75.58682556964494
|
| 689 |
},
|
| 690 |
{
|
| 691 |
+
"model": "anthropic/claude-3.5-sonnet",
|
| 692 |
"original_language": "eng_Latn",
|
| 693 |
+
"target_language": "mar_Deva",
|
| 694 |
+
"target_language_name": "Marathi",
|
| 695 |
+
"speakers": 83100000,
|
| 696 |
+
"bleu": 57.44340907113495
|
| 697 |
},
|
| 698 |
{
|
| 699 |
+
"model": "anthropic/claude-3.5-sonnet",
|
| 700 |
"original_language": "eng_Latn",
|
| 701 |
+
"target_language": "pbt_Arab",
|
| 702 |
+
"target_language_name": " Southern Pashto",
|
| 703 |
+
"speakers": 10900000,
|
| 704 |
+
"bleu": 38.548696222210154
|
| 705 |
},
|
| 706 |
{
|
| 707 |
+
"model": "anthropic/claude-3.5-sonnet",
|
| 708 |
"original_language": "eng_Latn",
|
| 709 |
+
"target_language": "lij_Latn",
|
| 710 |
+
"target_language_name": "Ligurian",
|
| 711 |
+
"speakers": 500000,
|
| 712 |
+
"bleu": 55.85306363017816
|
| 713 |
},
|
| 714 |
{
|
| 715 |
+
"model": "anthropic/claude-3.5-sonnet",
|
| 716 |
"original_language": "eng_Latn",
|
| 717 |
+
"target_language": "knc_Latn",
|
| 718 |
+
"target_language_name": " Yerwa Kanuri",
|
| 719 |
+
"speakers": 0,
|
| 720 |
+
"bleu": 22.241385961047616
|
| 721 |
},
|
| 722 |
{
|
| 723 |
+
"model": "anthropic/claude-3.5-sonnet",
|
| 724 |
"original_language": "eng_Latn",
|
| 725 |
+
"target_language": "chv_Cyrl",
|
| 726 |
+
"target_language_name": "Chuvash",
|
| 727 |
+
"speakers": 1279650,
|
| 728 |
+
"bleu": 45.05466587233098
|
| 729 |
},
|
| 730 |
{
|
| 731 |
"model": "anthropic/claude-3.5-sonnet",
|
| 732 |
"original_language": "eng_Latn",
|
| 733 |
+
"target_language": "asm_Beng",
|
| 734 |
+
"target_language_name": "Assamese",
|
| 735 |
+
"speakers": 15300000,
|
| 736 |
+
"bleu": 47.03513316051628
|
| 737 |
},
|
| 738 |
{
|
| 739 |
+
"model": "anthropic/claude-3.5-sonnet",
|
| 740 |
"original_language": "eng_Latn",
|
| 741 |
+
"target_language": "ace_Arab",
|
| 742 |
+
"target_language_name": "Aceh",
|
| 743 |
+
"speakers": 3500032,
|
| 744 |
+
"bleu": 23.349267705271775
|
| 745 |
},
|
| 746 |
{
|
| 747 |
+
"model": "anthropic/claude-3.5-sonnet",
|
| 748 |
"original_language": "eng_Latn",
|
| 749 |
+
"target_language": "tha_Thai",
|
| 750 |
+
"target_language_name": "Thai",
|
| 751 |
+
"speakers": 40000000,
|
| 752 |
+
"bleu": 62.81253609435389
|
| 753 |
},
|
| 754 |
{
|
| 755 |
+
"model": "anthropic/claude-3.5-sonnet",
|
| 756 |
"original_language": "eng_Latn",
|
| 757 |
+
"target_language": "fao_Latn",
|
| 758 |
+
"target_language_name": "Faroese",
|
| 759 |
+
"speakers": 69150,
|
| 760 |
+
"bleu": 65.91479024829229
|
| 761 |
},
|
| 762 |
{
|
| 763 |
+
"model": "anthropic/claude-3.5-sonnet",
|
| 764 |
"original_language": "eng_Latn",
|
| 765 |
+
"target_language": "nqo_Nkoo",
|
| 766 |
+
"target_language_name": "N’Ko",
|
| 767 |
+
"speakers": 0,
|
| 768 |
+
"bleu": 32.48349079900792
|
| 769 |
+
},
|
| 770 |
+
{
|
| 771 |
+
"model": "anthropic/claude-3.5-sonnet",
|
| 772 |
+
"original_language": "eng_Latn",
|
| 773 |
+
"target_language": "ilo_Latn",
|
| 774 |
+
"target_language_name": "Ilocano",
|
| 775 |
+
"speakers": 9100000,
|
| 776 |
+
"bleu": 62.605886459379576
|
| 777 |
+
},
|
| 778 |
+
{
|
| 779 |
+
"model": "anthropic/claude-3.5-sonnet",
|
| 780 |
+
"original_language": "eng_Latn",
|
| 781 |
+
"target_language": "kat_Geor",
|
| 782 |
+
"target_language_name": "Georgian",
|
| 783 |
+
"speakers": 3700000,
|
| 784 |
+
"bleu": 61.016636144241765
|
| 785 |
+
},
|
| 786 |
+
{
|
| 787 |
+
"model": "anthropic/claude-3.5-sonnet",
|
| 788 |
+
"original_language": "eng_Latn",
|
| 789 |
+
"target_language": "ayr_Latn",
|
| 790 |
+
"target_language_name": " Central Aymara",
|
| 791 |
+
"speakers": 0,
|
| 792 |
+
"bleu": 40.77379070593447
|
| 793 |
+
},
|
| 794 |
+
{
|
| 795 |
+
"model": "anthropic/claude-3.5-sonnet",
|
| 796 |
+
"original_language": "eng_Latn",
|
| 797 |
+
"target_language": "dan_Latn",
|
| 798 |
+
"target_language_name": "Danish",
|
| 799 |
+
"speakers": 6000000,
|
| 800 |
+
"bleu": 78.0935433283814
|
| 801 |
+
},
|
| 802 |
+
{
|
| 803 |
+
"model": "anthropic/claude-3.5-sonnet",
|
| 804 |
+
"original_language": "eng_Latn",
|
| 805 |
+
"target_language": "brx_Deva",
|
| 806 |
+
"target_language_name": "Boro (India)",
|
| 807 |
+
"speakers": 1482929,
|
| 808 |
+
"bleu": 36.11004749691388
|
| 809 |
+
},
|
| 810 |
+
{
|
| 811 |
+
"model": "anthropic/claude-3.5-sonnet",
|
| 812 |
+
"original_language": "eng_Latn",
|
| 813 |
+
"target_language": "sag_Latn",
|
| 814 |
+
"target_language_name": "Sango",
|
| 815 |
+
"speakers": 4600000,
|
| 816 |
+
"bleu": 34.875422265717596
|
| 817 |
+
},
|
| 818 |
+
{
|
| 819 |
+
"model": "anthropic/claude-3.5-sonnet",
|
| 820 |
+
"original_language": "eng_Latn",
|
| 821 |
+
"target_language": "lvs_Latn",
|
| 822 |
+
"target_language_name": " Standard Latvian",
|
| 823 |
+
"speakers": 0,
|
| 824 |
+
"bleu": 64.89951881611144
|
| 825 |
+
},
|
| 826 |
+
{
|
| 827 |
+
"model": "anthropic/claude-3.5-sonnet",
|
| 828 |
+
"original_language": "eng_Latn",
|
| 829 |
+
"target_language": "jpn_Jpan",
|
| 830 |
+
"target_language_name": "Japanese",
|
| 831 |
+
"speakers": 128000000,
|
| 832 |
+
"bleu": 49.91661356931259
|
| 833 |
+
},
|
| 834 |
+
{
|
| 835 |
+
"model": "anthropic/claude-3.5-sonnet",
|
| 836 |
+
"original_language": "eng_Latn",
|
| 837 |
+
"target_language": "uig_Arab",
|
| 838 |
+
"target_language_name": "Uyghur",
|
| 839 |
+
"speakers": 10400000,
|
| 840 |
+
"bleu": 53.53468771030665
|
| 841 |
+
},
|
| 842 |
+
{
|
| 843 |
+
"model": "anthropic/claude-3.5-sonnet",
|
| 844 |
+
"original_language": "eng_Latn",
|
| 845 |
+
"target_language": "fra_Latn",
|
| 846 |
+
"target_language_name": "French",
|
| 847 |
+
"speakers": 208157220,
|
| 848 |
+
"bleu": 79.3023871219446
|
| 849 |
+
},
|
| 850 |
+
{
|
| 851 |
+
"model": "anthropic/claude-3.5-sonnet",
|
| 852 |
+
"original_language": "eng_Latn",
|
| 853 |
+
"target_language": "jav_Latn",
|
| 854 |
+
"target_language_name": "Javanese",
|
| 855 |
+
"speakers": 84308740,
|
| 856 |
+
"bleu": 60.44033529900538
|
| 857 |
+
},
|
| 858 |
+
{
|
| 859 |
+
"model": "anthropic/claude-3.5-sonnet",
|
| 860 |
+
"original_language": "eng_Latn",
|
| 861 |
+
"target_language": "sun_Latn",
|
| 862 |
+
"target_language_name": "Sunda",
|
| 863 |
+
"speakers": 32400000,
|
| 864 |
+
"bleu": 56.40659991041485
|
| 865 |
+
},
|
| 866 |
+
{
|
| 867 |
+
"model": "anthropic/claude-3.5-sonnet",
|
| 868 |
+
"original_language": "eng_Latn",
|
| 869 |
+
"target_language": "umb_Latn",
|
| 870 |
+
"target_language_name": "Umbundu",
|
| 871 |
+
"speakers": 6000000,
|
| 872 |
+
"bleu": 21.080277559665817
|
| 873 |
+
},
|
| 874 |
+
{
|
| 875 |
+
"model": "anthropic/claude-3.5-sonnet",
|
| 876 |
+
"original_language": "eng_Latn",
|
| 877 |
+
"target_language": "bel_Cyrl",
|
| 878 |
+
"target_language_name": "Belarusian",
|
| 879 |
+
"speakers": 7900000,
|
| 880 |
+
"bleu": 54.51951664423131
|
| 881 |
+
},
|
| 882 |
+
{
|
| 883 |
+
"model": "anthropic/claude-3.5-sonnet",
|
| 884 |
+
"original_language": "eng_Latn",
|
| 885 |
+
"target_language": "cjk_Latn",
|
| 886 |
+
"target_language_name": "Chokwe",
|
| 887 |
+
"speakers": 0,
|
| 888 |
+
"bleu": 10.186407416077753
|
| 889 |
+
},
|
| 890 |
+
{
|
| 891 |
+
"model": "anthropic/claude-3.5-sonnet",
|
| 892 |
+
"original_language": "eng_Latn",
|
| 893 |
+
"target_language": "yue_Hant",
|
| 894 |
+
"target_language_name": " Yue Chinese",
|
| 895 |
+
"speakers": 73100000,
|
| 896 |
+
"bleu": 34.25609770821219
|
| 897 |
+
},
|
| 898 |
+
{
|
| 899 |
+
"model": "anthropic/claude-3.5-sonnet",
|
| 900 |
+
"original_language": "eng_Latn",
|
| 901 |
+
"target_language": "hat_Latn",
|
| 902 |
+
"target_language_name": "Haitian Creole",
|
| 903 |
+
"speakers": 9600000,
|
| 904 |
+
"bleu": 63.85321875910916
|
| 905 |
+
},
|
| 906 |
+
{
|
| 907 |
+
"model": "anthropic/claude-3.5-sonnet",
|
| 908 |
+
"original_language": "eng_Latn",
|
| 909 |
+
"target_language": "kmr_Latn",
|
| 910 |
+
"target_language_name": " Northern Kurdish",
|
| 911 |
+
"speakers": 14600000,
|
| 912 |
+
"bleu": 55.00856002671919
|
| 913 |
+
},
|
| 914 |
+
{
|
| 915 |
+
"model": "anthropic/claude-3.5-sonnet",
|
| 916 |
+
"original_language": "eng_Latn",
|
| 917 |
+
"target_language": "ceb_Latn",
|
| 918 |
+
"target_language_name": "Cebuano",
|
| 919 |
+
"speakers": 15900000,
|
| 920 |
+
"bleu": 69.455795865483
|
| 921 |
+
},
|
| 922 |
+
{
|
| 923 |
+
"model": "anthropic/claude-3.5-sonnet",
|
| 924 |
+
"original_language": "eng_Latn",
|
| 925 |
+
"target_language": "dzo_Tibt",
|
| 926 |
+
"target_language_name": "Dzongkha",
|
| 927 |
+
"speakers": 237080,
|
| 928 |
+
"bleu": 44.35738140173861
|
| 929 |
+
},
|
| 930 |
+
{
|
| 931 |
+
"model": "anthropic/claude-3.5-sonnet",
|
| 932 |
+
"original_language": "eng_Latn",
|
| 933 |
+
"target_language": "deu_Latn",
|
| 934 |
+
"target_language_name": " Standard German",
|
| 935 |
+
"speakers": 105000000,
|
| 936 |
+
"bleu": 77.22130383692244
|
| 937 |
+
},
|
| 938 |
+
{
|
| 939 |
+
"model": "anthropic/claude-3.5-sonnet",
|
| 940 |
+
"original_language": "eng_Latn",
|
| 941 |
+
"target_language": "ibo_Latn",
|
| 942 |
+
"target_language_name": "Igbo",
|
| 943 |
+
"speakers": 27000000,
|
| 944 |
+
"bleu": 46.40173449341075
|
| 945 |
+
},
|
| 946 |
+
{
|
| 947 |
+
"model": "anthropic/claude-3.5-sonnet",
|
| 948 |
+
"original_language": "eng_Latn",
|
| 949 |
+
"target_language": "vie_Latn",
|
| 950 |
+
"target_language_name": "Vietnamese",
|
| 951 |
+
"speakers": 76000000,
|
| 952 |
+
"bleu": 70.35607494641172
|
| 953 |
+
},
|
| 954 |
+
{
|
| 955 |
+
"model": "anthropic/claude-3.5-sonnet",
|
| 956 |
+
"original_language": "eng_Latn",
|
| 957 |
+
"target_language": "quy_Latn",
|
| 958 |
+
"target_language_name": " Ayacucho Quechua",
|
| 959 |
+
"speakers": 918200,
|
| 960 |
+
"bleu": 46.24441292595311
|
| 961 |
+
},
|
| 962 |
+
{
|
| 963 |
+
"model": "anthropic/claude-3.5-sonnet",
|
| 964 |
+
"original_language": "eng_Latn",
|
| 965 |
+
"target_language": "cmn_Hant",
|
| 966 |
+
"target_language_name": " Mandarin Chinese",
|
| 967 |
+
"speakers": 1074000000,
|
| 968 |
+
"bleu": 41.46450104859355
|
| 969 |
+
},
|
| 970 |
+
{
|
| 971 |
+
"model": "anthropic/claude-3.5-sonnet",
|
| 972 |
+
"original_language": "eng_Latn",
|
| 973 |
+
"target_language": "mai_Deva",
|
| 974 |
+
"target_language_name": "Maithili",
|
| 975 |
+
"speakers": 33900000,
|
| 976 |
+
"bleu": 54.65300713908629
|
| 977 |
+
},
|
| 978 |
+
{
|
| 979 |
+
"model": "anthropic/claude-3.5-sonnet",
|
| 980 |
+
"original_language": "eng_Latn",
|
| 981 |
+
"target_language": "gla_Latn",
|
| 982 |
+
"target_language_name": "Scottish Gaelic",
|
| 983 |
+
"speakers": 60130,
|
| 984 |
+
"bleu": 62.604437133773324
|
| 985 |
+
},
|
| 986 |
+
{
|
| 987 |
+
"model": "anthropic/claude-3.5-sonnet",
|
| 988 |
+
"original_language": "eng_Latn",
|
| 989 |
+
"target_language": "urd_Arab",
|
| 990 |
+
"target_language_name": "Urdu",
|
| 991 |
+
"speakers": 94022900,
|
| 992 |
+
"bleu": 61.12554572717868
|
| 993 |
+
},
|
| 994 |
+
{
|
| 995 |
+
"model": "anthropic/claude-3.5-sonnet",
|
| 996 |
+
"original_language": "eng_Latn",
|
| 997 |
+
"target_language": "shn_Mymr",
|
| 998 |
+
"target_language_name": "Shan",
|
| 999 |
+
"speakers": 3000000,
|
| 1000 |
+
"bleu": 29.21299485766884
|
| 1001 |
+
},
|
| 1002 |
+
{
|
| 1003 |
+
"model": "anthropic/claude-3.5-sonnet",
|
| 1004 |
+
"original_language": "eng_Latn",
|
| 1005 |
+
"target_language": "wol_Latn",
|
| 1006 |
+
"target_language_name": "Wolof",
|
| 1007 |
+
"speakers": 3700000,
|
| 1008 |
+
"bleu": 42.64301275691043
|
| 1009 |
+
},
|
| 1010 |
+
{
|
| 1011 |
+
"model": "anthropic/claude-3.5-sonnet",
|
| 1012 |
+
"original_language": "eng_Latn",
|
| 1013 |
+
"target_language": "cmn_Hans",
|
| 1014 |
+
"target_language_name": " Mandarin Chinese",
|
| 1015 |
+
"speakers": 1074000000,
|
| 1016 |
+
"bleu": 43.72017219180501
|
| 1017 |
+
},
|
| 1018 |
+
{
|
| 1019 |
+
"model": "anthropic/claude-3.5-sonnet",
|
| 1020 |
+
"original_language": "eng_Latn",
|
| 1021 |
+
"target_language": "guj_Gujr",
|
| 1022 |
+
"target_language_name": "Gujarati",
|
| 1023 |
+
"speakers": 56400000,
|
| 1024 |
+
"bleu": 55.588451345198735
|
| 1025 |
+
},
|
| 1026 |
+
{
|
| 1027 |
+
"model": "anthropic/claude-3.5-sonnet",
|
| 1028 |
+
"original_language": "eng_Latn",
|
| 1029 |
+
"target_language": "ekk_Latn",
|
| 1030 |
+
"target_language_name": " Standard Estonian",
|
| 1031 |
+
"speakers": 1164770,
|
| 1032 |
+
"bleu": 68.06935269432235
|
| 1033 |
+
},
|
| 1034 |
+
{
|
| 1035 |
+
"model": "anthropic/claude-3.5-sonnet",
|
| 1036 |
+
"original_language": "eng_Latn",
|
| 1037 |
+
"target_language": "luo_Latn",
|
| 1038 |
+
"target_language_name": "Dholuo",
|
| 1039 |
+
"speakers": 3000000,
|
| 1040 |
+
"bleu": 46.41194790710186
|
| 1041 |
+
},
|
| 1042 |
+
{
|
| 1043 |
+
"model": "anthropic/claude-3.5-sonnet",
|
| 1044 |
+
"original_language": "eng_Latn",
|
| 1045 |
+
"target_language": "hrv_Latn",
|
| 1046 |
+
"target_language_name": "Croatian",
|
| 1047 |
+
"speakers": 7000000,
|
| 1048 |
+
"bleu": 69.54569836615161
|
| 1049 |
+
},
|
| 1050 |
+
{
|
| 1051 |
+
"model": "anthropic/claude-3.5-sonnet",
|
| 1052 |
+
"original_language": "eng_Latn",
|
| 1053 |
+
"target_language": "uzn_Latn",
|
| 1054 |
+
"target_language_name": " Northern Uzbek",
|
| 1055 |
+
"speakers": 26912410,
|
| 1056 |
+
"bleu": 64.07804482004295
|
| 1057 |
+
},
|
| 1058 |
+
{
|
| 1059 |
+
"model": "anthropic/claude-3.5-sonnet",
|
| 1060 |
+
"original_language": "eng_Latn",
|
| 1061 |
+
"target_language": "ben_Beng",
|
| 1062 |
+
"target_language_name": "Bengali",
|
| 1063 |
+
"speakers": 300000000,
|
| 1064 |
+
"bleu": 57.14175888160181
|
| 1065 |
+
},
|
| 1066 |
+
{
|
| 1067 |
+
"model": "anthropic/claude-3.5-sonnet",
|
| 1068 |
+
"original_language": "eng_Latn",
|
| 1069 |
+
"target_language": "nya_Latn",
|
| 1070 |
+
"target_language_name": "Chichewa",
|
| 1071 |
+
"speakers": 12000000,
|
| 1072 |
+
"bleu": 59.76016801606614
|
| 1073 |
+
},
|
| 1074 |
+
{
|
| 1075 |
+
"model": "anthropic/claude-3.5-sonnet",
|
| 1076 |
+
"original_language": "eng_Latn",
|
| 1077 |
+
"target_language": "tsn_Latn",
|
| 1078 |
+
"target_language_name": "Setswana",
|
| 1079 |
+
"speakers": 4500000,
|
| 1080 |
+
"bleu": 55.22888902281337
|
| 1081 |
+
},
|
| 1082 |
+
{
|
| 1083 |
+
"model": "anthropic/claude-3.5-sonnet",
|
| 1084 |
+
"original_language": "eng_Latn",
|
| 1085 |
+
"target_language": "fin_Latn",
|
| 1086 |
+
"target_language_name": "Finnish",
|
| 1087 |
+
"speakers": 5413380,
|
| 1088 |
+
"bleu": 70.94250295175219
|
| 1089 |
+
},
|
| 1090 |
+
{
|
| 1091 |
+
"model": "anthropic/claude-3.5-sonnet",
|
| 1092 |
+
"original_language": "eng_Latn",
|
| 1093 |
+
"target_language": "nso_Latn",
|
| 1094 |
+
"target_language_name": " Northern Sotho",
|
| 1095 |
+
"speakers": 4100000,
|
| 1096 |
+
"bleu": 63.048250806570664
|
| 1097 |
+
},
|
| 1098 |
+
{
|
| 1099 |
+
"model": "anthropic/claude-3.5-sonnet",
|
| 1100 |
+
"original_language": "eng_Latn",
|
| 1101 |
+
"target_language": "sna_Latn",
|
| 1102 |
+
"target_language_name": "Shona",
|
| 1103 |
+
"speakers": 9023000,
|
| 1104 |
+
"bleu": 51.55921914049446
|
| 1105 |
+
},
|
| 1106 |
+
{
|
| 1107 |
+
"model": "anthropic/claude-3.5-sonnet",
|
| 1108 |
+
"original_language": "eng_Latn",
|
| 1109 |
+
"target_language": "snd_Arab",
|
| 1110 |
+
"target_language_name": "Sindhi",
|
| 1111 |
+
"speakers": 25000000,
|
| 1112 |
+
"bleu": 56.33027730975489
|
| 1113 |
+
},
|
| 1114 |
+
{
|
| 1115 |
+
"model": "anthropic/claude-3.5-sonnet",
|
| 1116 |
+
"original_language": "eng_Latn",
|
| 1117 |
+
"target_language": "xho_Latn",
|
| 1118 |
+
"target_language_name": "Xhosa",
|
| 1119 |
+
"speakers": 11000000,
|
| 1120 |
+
"bleu": 55.46880910094653
|
| 1121 |
+
},
|
| 1122 |
+
{
|
| 1123 |
+
"model": "anthropic/claude-3.5-sonnet",
|
| 1124 |
+
"original_language": "eng_Latn",
|
| 1125 |
+
"target_language": "kik_Latn",
|
| 1126 |
+
"target_language_name": "Gikuyu",
|
| 1127 |
+
"speakers": 6623000,
|
| 1128 |
+
"bleu": 40.92882752909001
|
| 1129 |
+
},
|
| 1130 |
+
{
|
| 1131 |
+
"model": "anthropic/claude-3.5-sonnet",
|
| 1132 |
+
"original_language": "eng_Latn",
|
| 1133 |
+
"target_language": "tso_Latn",
|
| 1134 |
+
"target_language_name": "Tsonga",
|
| 1135 |
+
"speakers": 13000000,
|
| 1136 |
+
"bleu": 58.35165735971044
|
| 1137 |
+
},
|
| 1138 |
+
{
|
| 1139 |
+
"model": "anthropic/claude-3.5-sonnet",
|
| 1140 |
+
"original_language": "eng_Latn",
|
| 1141 |
+
"target_language": "tat_Cyrl",
|
| 1142 |
+
"target_language_name": "Tatar",
|
| 1143 |
+
"speakers": 5427318,
|
| 1144 |
+
"bleu": 60.3447467212788
|
| 1145 |
+
},
|
| 1146 |
+
{
|
| 1147 |
+
"model": "anthropic/claude-3.5-sonnet",
|
| 1148 |
+
"original_language": "eng_Latn",
|
| 1149 |
+
"target_language": "awa_Deva",
|
| 1150 |
+
"target_language_name": "Awadhi",
|
| 1151 |
+
"speakers": 22000000,
|
| 1152 |
+
"bleu": 46.0797144146192
|
| 1153 |
+
},
|
| 1154 |
+
{
|
| 1155 |
+
"model": "anthropic/claude-3.5-sonnet",
|
| 1156 |
+
"original_language": "eng_Latn",
|
| 1157 |
+
"target_language": "gom_Deva",
|
| 1158 |
+
"target_language_name": " Goan Konkani",
|
| 1159 |
+
"speakers": 3633900,
|
| 1160 |
+
"bleu": 46.88835079678478
|
| 1161 |
+
},
|
| 1162 |
+
{
|
| 1163 |
+
"model": "anthropic/claude-3.5-sonnet",
|
| 1164 |
+
"original_language": "eng_Latn",
|
| 1165 |
+
"target_language": "amh_Ethi",
|
| 1166 |
+
"target_language_name": "Amharic",
|
| 1167 |
+
"speakers": 25000000,
|
| 1168 |
+
"bleu": 43.15445686971015
|
| 1169 |
+
},
|
| 1170 |
+
{
|
| 1171 |
+
"model": "anthropic/claude-3.5-sonnet",
|
| 1172 |
+
"original_language": "eng_Latn",
|
| 1173 |
+
"target_language": "tam_Taml",
|
| 1174 |
+
"target_language_name": "Tamil",
|
| 1175 |
+
"speakers": 75000000,
|
| 1176 |
+
"bleu": 65.78632210538115
|
| 1177 |
+
},
|
| 1178 |
+
{
|
| 1179 |
+
"model": "openai/gpt-4o-mini",
|
| 1180 |
+
"original_language": "eng_Latn",
|
| 1181 |
+
"target_language": "isl_Latn",
|
| 1182 |
+
"target_language_name": "Icelandic",
|
| 1183 |
+
"speakers": 358000,
|
| 1184 |
+
"bleu": 61.13552606922321
|
| 1185 |
+
},
|
| 1186 |
+
{
|
| 1187 |
+
"model": "anthropic/claude-3.5-sonnet",
|
| 1188 |
+
"original_language": "eng_Latn",
|
| 1189 |
+
"target_language": "isl_Latn",
|
| 1190 |
+
"target_language_name": "Icelandic",
|
| 1191 |
+
"speakers": 358000,
|
| 1192 |
+
"bleu": 66.67473000551618
|
| 1193 |
+
},
|
| 1194 |
+
{
|
| 1195 |
+
"model": "meta-llama/llama-3.1-70b-instruct",
|
| 1196 |
+
"original_language": "eng_Latn",
|
| 1197 |
+
"target_language": "isl_Latn",
|
| 1198 |
+
"target_language_name": "Icelandic",
|
| 1199 |
+
"speakers": 358000,
|
| 1200 |
+
"bleu": 58.60923195347865
|
| 1201 |
+
},
|
| 1202 |
+
{
|
| 1203 |
+
"model": "mistralai/mistral-nemo",
|
| 1204 |
+
"original_language": "eng_Latn",
|
| 1205 |
+
"target_language": "isl_Latn",
|
| 1206 |
+
"target_language_name": "Icelandic",
|
| 1207 |
+
"speakers": 358000,
|
| 1208 |
+
"bleu": 45.58482442810681
|
| 1209 |
+
},
|
| 1210 |
+
{
|
| 1211 |
+
"model": "qwen/qwen-2.5-72b-instruct",
|
| 1212 |
+
"original_language": "eng_Latn",
|
| 1213 |
+
"target_language": "isl_Latn",
|
| 1214 |
+
"target_language_name": "Icelandic",
|
| 1215 |
+
"speakers": 358000,
|
| 1216 |
+
"bleu": 40.16071522003955
|
| 1217 |
+
},
|
| 1218 |
+
{
|
| 1219 |
+
"model": "anthropic/claude-3.5-sonnet",
|
| 1220 |
+
"original_language": "eng_Latn",
|
| 1221 |
+
"target_language": "san_Deva",
|
| 1222 |
+
"target_language_name": "Sanskrit",
|
| 1223 |
+
"speakers": 49736,
|
| 1224 |
+
"bleu": 32.78132499113236
|
| 1225 |
+
},
|
| 1226 |
+
{
|
| 1227 |
+
"model": "anthropic/claude-3.5-sonnet",
|
| 1228 |
+
"original_language": "eng_Latn",
|
| 1229 |
+
"target_language": "als_Latn",
|
| 1230 |
+
"target_language_name": " Tosk Albanian",
|
| 1231 |
+
"speakers": 3000000,
|
| 1232 |
+
"bleu": 69.24285560147364
|
| 1233 |
+
},
|
| 1234 |
+
{
|
| 1235 |
+
"model": "anthropic/claude-3.5-sonnet",
|
| 1236 |
+
"original_language": "eng_Latn",
|
| 1237 |
+
"target_language": "ron_Latn",
|
| 1238 |
+
"target_language_name": "Romanian",
|
| 1239 |
+
"speakers": 24300000,
|
| 1240 |
+
"bleu": 76.4907159034647
|
| 1241 |
+
},
|
| 1242 |
+
{
|
| 1243 |
+
"model": "anthropic/claude-3.5-sonnet",
|
| 1244 |
+
"original_language": "eng_Latn",
|
| 1245 |
+
"target_language": "kaz_Cyrl",
|
| 1246 |
+
"target_language_name": "Kazakh",
|
| 1247 |
+
"speakers": 13161980,
|
| 1248 |
+
"bleu": 61.12516213751114
|
| 1249 |
+
},
|
| 1250 |
+
{
|
| 1251 |
+
"model": "anthropic/claude-3.5-sonnet",
|
| 1252 |
+
"original_language": "eng_Latn",
|
| 1253 |
+
"target_language": "sat_Olck",
|
| 1254 |
+
"target_language_name": "Santhali",
|
| 1255 |
+
"speakers": 7200000,
|
| 1256 |
+
"bleu": 31.51192472690372
|
| 1257 |
+
},
|
| 1258 |
+
{
|
| 1259 |
+
"model": "anthropic/claude-3.5-sonnet",
|
| 1260 |
+
"original_language": "eng_Latn",
|
| 1261 |
+
"target_language": "ukr_Cyrl",
|
| 1262 |
+
"target_language_name": "Ukrainian",
|
| 1263 |
+
"speakers": 34710100,
|
| 1264 |
+
"bleu": 68.09762325436868
|
| 1265 |
+
},
|
| 1266 |
+
{
|
| 1267 |
+
"model": "anthropic/claude-3.5-sonnet",
|
| 1268 |
+
"original_language": "eng_Latn",
|
| 1269 |
+
"target_language": "khk_Cyrl",
|
| 1270 |
+
"target_language_name": " Halh Mongolian",
|
| 1271 |
+
"speakers": 2704030,
|
| 1272 |
+
"bleu": 59.14263972986465
|
| 1273 |
+
},
|
| 1274 |
+
{
|
| 1275 |
+
"model": "anthropic/claude-3.5-sonnet",
|
| 1276 |
+
"original_language": "eng_Latn",
|
| 1277 |
+
"target_language": "bjn_Latn",
|
| 1278 |
+
"target_language_name": "Banjar",
|
| 1279 |
+
"speakers": 3500000,
|
| 1280 |
+
"bleu": 56.309519555010915
|
| 1281 |
+
},
|
| 1282 |
+
{
|
| 1283 |
+
"model": "anthropic/claude-3.5-sonnet",
|
| 1284 |
+
"original_language": "eng_Latn",
|
| 1285 |
+
"target_language": "fon_Latn",
|
| 1286 |
+
"target_language_name": "Fon",
|
| 1287 |
+
"speakers": 1935500,
|
| 1288 |
+
"bleu": 25.279777366609945
|
| 1289 |
+
},
|
| 1290 |
+
{
|
| 1291 |
+
"model": "anthropic/claude-3.5-sonnet",
|
| 1292 |
+
"original_language": "eng_Latn",
|
| 1293 |
+
"target_language": "sin_Sinh",
|
| 1294 |
+
"target_language_name": "Sinhala",
|
| 1295 |
+
"speakers": 15300000,
|
| 1296 |
+
"bleu": 56.75673117959971
|
| 1297 |
+
},
|
| 1298 |
+
{
|
| 1299 |
+
"model": "anthropic/claude-3.5-sonnet",
|
| 1300 |
+
"original_language": "eng_Latn",
|
| 1301 |
+
"target_language": "nno_Latn",
|
| 1302 |
+
"target_language_name": "nno",
|
| 1303 |
+
"speakers": 0,
|
| 1304 |
+
"bleu": 71.86156462958435
|
| 1305 |
+
},
|
| 1306 |
+
{
|
| 1307 |
+
"model": "anthropic/claude-3.5-sonnet",
|
| 1308 |
+
"original_language": "eng_Latn",
|
| 1309 |
+
"target_language": "hau_Latn",
|
| 1310 |
+
"target_language_name": "Hausa",
|
| 1311 |
+
"speakers": 43900000,
|
| 1312 |
+
"bleu": 56.34319579006431
|
| 1313 |
+
},
|
| 1314 |
+
{
|
| 1315 |
+
"model": "anthropic/claude-3.5-sonnet",
|
| 1316 |
+
"original_language": "eng_Latn",
|
| 1317 |
+
"target_language": "prs_Arab",
|
| 1318 |
+
"target_language_name": "Dari",
|
| 1319 |
+
"speakers": 9600000,
|
| 1320 |
+
"bleu": 52.55397957953147
|
| 1321 |
+
},
|
| 1322 |
+
{
|
| 1323 |
+
"model": "anthropic/claude-3.5-sonnet",
|
| 1324 |
+
"original_language": "eng_Latn",
|
| 1325 |
+
"target_language": "ell_Grek",
|
| 1326 |
+
"target_language_name": "Greek",
|
| 1327 |
+
"speakers": 15000000,
|
| 1328 |
+
"bleu": 66.23477821529342
|
| 1329 |
+
},
|
| 1330 |
+
{
|
| 1331 |
+
"model": "anthropic/claude-3.5-sonnet",
|
| 1332 |
+
"original_language": "eng_Latn",
|
| 1333 |
+
"target_language": "tpi_Latn",
|
| 1334 |
+
"target_language_name": "Tok Pisin",
|
| 1335 |
+
"speakers": 4000000,
|
| 1336 |
+
"bleu": 56.54077603673191
|
| 1337 |
+
},
|
| 1338 |
+
{
|
| 1339 |
+
"model": "anthropic/claude-3.5-sonnet",
|
| 1340 |
+
"original_language": "eng_Latn",
|
| 1341 |
+
"target_language": "hye_Armn",
|
| 1342 |
+
"target_language_name": "Armenian",
|
| 1343 |
+
"speakers": 6700000,
|
| 1344 |
+
"bleu": 64.68044008058686
|
| 1345 |
+
},
|
| 1346 |
+
{
|
| 1347 |
+
"model": "anthropic/claude-3.5-sonnet",
|
| 1348 |
+
"original_language": "eng_Latn",
|
| 1349 |
+
"target_language": "eus_Latn",
|
| 1350 |
+
"target_language_name": "Basque",
|
| 1351 |
+
"speakers": 750000,
|
| 1352 |
+
"bleu": 65.89687213771296
|
| 1353 |
+
},
|
| 1354 |
+
{
|
| 1355 |
+
"model": "anthropic/claude-3.5-sonnet",
|
| 1356 |
+
"original_language": "eng_Latn",
|
| 1357 |
+
"target_language": "nob_Latn",
|
| 1358 |
+
"target_language_name": "Bokmål",
|
| 1359 |
+
"speakers": 4000000,
|
| 1360 |
+
"bleu": 77.49395130155645
|
| 1361 |
+
},
|
| 1362 |
+
{
|
| 1363 |
+
"model": "anthropic/claude-3.5-sonnet",
|
| 1364 |
+
"original_language": "eng_Latn",
|
| 1365 |
+
"target_language": "slk_Latn",
|
| 1366 |
+
"target_language_name": "Slovak",
|
| 1367 |
+
"speakers": 6000000,
|
| 1368 |
+
"bleu": 67.92848040860814
|
| 1369 |
+
},
|
| 1370 |
+
{
|
| 1371 |
+
"model": "anthropic/claude-3.5-sonnet",
|
| 1372 |
+
"original_language": "eng_Latn",
|
| 1373 |
+
"target_language": "knc_Arab",
|
| 1374 |
+
"target_language_name": " Yerwa Kanuri",
|
| 1375 |
+
"speakers": 0,
|
| 1376 |
+
"bleu": 14.714612284264362
|
| 1377 |
+
},
|
| 1378 |
+
{
|
| 1379 |
+
"model": "openai/gpt-4o-mini",
|
| 1380 |
+
"original_language": "eng_Latn",
|
| 1381 |
+
"target_language": "lin_Latn",
|
| 1382 |
+
"target_language_name": "Lingala",
|
| 1383 |
+
"speakers": 20000000,
|
| 1384 |
+
"bleu": 50.384710146677506
|
| 1385 |
+
},
|
| 1386 |
+
{
|
| 1387 |
+
"model": "anthropic/claude-3.5-sonnet",
|
| 1388 |
+
"original_language": "eng_Latn",
|
| 1389 |
+
"target_language": "lin_Latn",
|
| 1390 |
+
"target_language_name": "Lingala",
|
| 1391 |
+
"speakers": 20000000,
|
| 1392 |
+
"bleu": 56.735518064625495
|
| 1393 |
+
},
|
| 1394 |
+
{
|
| 1395 |
+
"model": "meta-llama/llama-3.1-70b-instruct",
|
| 1396 |
+
"original_language": "eng_Latn",
|
| 1397 |
+
"target_language": "lin_Latn",
|
| 1398 |
+
"target_language_name": "Lingala",
|
| 1399 |
+
"speakers": 20000000,
|
| 1400 |
+
"bleu": 19.732953348932526
|
| 1401 |
+
},
|
| 1402 |
+
{
|
| 1403 |
+
"model": "mistralai/mistral-nemo",
|
| 1404 |
+
"original_language": "eng_Latn",
|
| 1405 |
+
"target_language": "lin_Latn",
|
| 1406 |
+
"target_language_name": "Lingala",
|
| 1407 |
+
"speakers": 20000000,
|
| 1408 |
+
"bleu": 8.64985622273109
|
| 1409 |
+
},
|
| 1410 |
+
{
|
| 1411 |
+
"model": "qwen/qwen-2.5-72b-instruct",
|
| 1412 |
+
"original_language": "eng_Latn",
|
| 1413 |
+
"target_language": "lin_Latn",
|
| 1414 |
+
"target_language_name": "Lingala",
|
| 1415 |
+
"speakers": 20000000,
|
| 1416 |
+
"bleu": 16.658410482633357
|
| 1417 |
+
},
|
| 1418 |
+
{
|
| 1419 |
+
"model": "anthropic/claude-3.5-sonnet",
|
| 1420 |
+
"original_language": "eng_Latn",
|
| 1421 |
+
"target_language": "bam_Latn",
|
| 1422 |
+
"target_language_name": "Bamanankan",
|
| 1423 |
+
"speakers": 2700000,
|
| 1424 |
+
"bleu": 38.693909140769804
|
| 1425 |
+
},
|
| 1426 |
+
{
|
| 1427 |
+
"model": "anthropic/claude-3.5-sonnet",
|
| 1428 |
+
"original_language": "eng_Latn",
|
| 1429 |
+
"target_language": "sot_Latn",
|
| 1430 |
+
"target_language_name": " Southern Sotho",
|
| 1431 |
+
"speakers": 6000000,
|
| 1432 |
+
"bleu": 57.153751026567605
|
| 1433 |
+
},
|
| 1434 |
+
{
|
| 1435 |
+
"model": "anthropic/claude-3.5-sonnet",
|
| 1436 |
+
"original_language": "eng_Latn",
|
| 1437 |
+
"target_language": "min_Arab",
|
| 1438 |
+
"target_language_name": "Minangkabau",
|
| 1439 |
+
"speakers": 5530000,
|
| 1440 |
+
"bleu": 37.44925084737469
|
| 1441 |
+
},
|
| 1442 |
+
{
|
| 1443 |
+
"model": "anthropic/claude-3.5-sonnet",
|
| 1444 |
+
"original_language": "eng_Latn",
|
| 1445 |
+
"target_language": "zgh_Tfng",
|
| 1446 |
+
"target_language_name": " Standard Moroccan Tamazight",
|
| 1447 |
+
"speakers": 0,
|
| 1448 |
+
"bleu": 36.02110203894128
|
| 1449 |
+
},
|
| 1450 |
+
{
|
| 1451 |
+
"model": "anthropic/claude-3.5-sonnet",
|
| 1452 |
+
"original_language": "eng_Latn",
|
| 1453 |
+
"target_language": "gug_Latn",
|
| 1454 |
+
"target_language_name": " Paraguayan Guaraní",
|
| 1455 |
+
"speakers": 0,
|
| 1456 |
+
"bleu": 42.90235038974312
|
| 1457 |
+
},
|
| 1458 |
+
{
|
| 1459 |
+
"model": "anthropic/claude-3.5-sonnet",
|
| 1460 |
+
"original_language": "eng_Latn",
|
| 1461 |
+
"target_language": "lmo_Latn",
|
| 1462 |
+
"target_language_name": "Lombard",
|
| 1463 |
+
"speakers": 3900000,
|
| 1464 |
+
"bleu": 46.38844026736926
|
| 1465 |
+
},
|
| 1466 |
+
{
|
| 1467 |
+
"model": "anthropic/claude-3.5-sonnet",
|
| 1468 |
+
"original_language": "eng_Latn",
|
| 1469 |
+
"target_language": "yor_Latn",
|
| 1470 |
+
"target_language_name": "Yoruba",
|
| 1471 |
+
"speakers": 40000000,
|
| 1472 |
+
"bleu": 34.264254226792296
|
| 1473 |
+
},
|
| 1474 |
+
{
|
| 1475 |
+
"model": "anthropic/claude-3.5-sonnet",
|
| 1476 |
+
"original_language": "eng_Latn",
|
| 1477 |
+
"target_language": "taq_Tfng",
|
| 1478 |
+
"target_language_name": "Tamasheq",
|
| 1479 |
+
"speakers": 500000,
|
| 1480 |
+
"bleu": 10.997033033155907
|
| 1481 |
+
},
|
| 1482 |
+
{
|
| 1483 |
+
"model": "anthropic/claude-3.5-sonnet",
|
| 1484 |
+
"original_language": "eng_Latn",
|
| 1485 |
+
"target_language": "tgk_Cyrl",
|
| 1486 |
+
"target_language_name": "Tajik",
|
| 1487 |
+
"speakers": 14000000,
|
| 1488 |
+
"bleu": 60.97836841576954
|
| 1489 |
+
},
|
| 1490 |
+
{
|
| 1491 |
+
"model": "anthropic/claude-3.5-sonnet",
|
| 1492 |
+
"original_language": "eng_Latn",
|
| 1493 |
+
"target_language": "fuv_Latn",
|
| 1494 |
+
"target_language_name": " Nigerian Fulfulde",
|
| 1495 |
+
"speakers": 14500000,
|
| 1496 |
+
"bleu": 28.24585718309509
|
| 1497 |
+
},
|
| 1498 |
+
{
|
| 1499 |
+
"model": "anthropic/claude-3.5-sonnet",
|
| 1500 |
+
"original_language": "eng_Latn",
|
| 1501 |
+
"target_language": "mal_Mlym",
|
| 1502 |
+
"target_language_name": "Malayalam",
|
| 1503 |
+
"speakers": 37100000,
|
| 1504 |
+
"bleu": 64.06558940908465
|
| 1505 |
+
},
|
| 1506 |
+
{
|
| 1507 |
+
"model": "anthropic/claude-3.5-sonnet",
|
| 1508 |
+
"original_language": "eng_Latn",
|
| 1509 |
+
"target_language": "tel_Telu",
|
| 1510 |
+
"target_language_name": "Telugu",
|
| 1511 |
+
"speakers": 82000000,
|
| 1512 |
+
"bleu": 61.635245762892694
|
| 1513 |
+
},
|
| 1514 |
+
{
|
| 1515 |
+
"model": "anthropic/claude-3.5-sonnet",
|
| 1516 |
+
"original_language": "eng_Latn",
|
| 1517 |
+
"target_language": "arb_Arab",
|
| 1518 |
+
"target_language_name": " Standard Arabic",
|
| 1519 |
+
"speakers": 0,
|
| 1520 |
+
"bleu": 65.45362559909618
|
| 1521 |
+
},
|
| 1522 |
+
{
|
| 1523 |
+
"model": "anthropic/claude-3.5-sonnet",
|
| 1524 |
+
"original_language": "eng_Latn",
|
| 1525 |
+
"target_language": "khm_Khmr",
|
| 1526 |
+
"target_language_name": "Khmer",
|
| 1527 |
+
"speakers": 16600000,
|
| 1528 |
+
"bleu": 49.209825704340375
|
| 1529 |
+
},
|
| 1530 |
+
{
|
| 1531 |
+
"model": "anthropic/claude-3.5-sonnet",
|
| 1532 |
+
"original_language": "eng_Latn",
|
| 1533 |
+
"target_language": "scn_Latn",
|
| 1534 |
+
"target_language_name": "Sicilian",
|
| 1535 |
+
"speakers": 4700000,
|
| 1536 |
+
"bleu": 58.589535944250635
|
| 1537 |
+
},
|
| 1538 |
+
{
|
| 1539 |
+
"model": "anthropic/claude-3.5-sonnet",
|
| 1540 |
+
"original_language": "eng_Latn",
|
| 1541 |
+
"target_language": "ltz_Latn",
|
| 1542 |
+
"target_language_name": "Luxembourgish",
|
| 1543 |
+
"speakers": 391200,
|
| 1544 |
+
"bleu": 70.8338190437548
|
| 1545 |
+
},
|
| 1546 |
+
{
|
| 1547 |
+
"model": "anthropic/claude-3.5-sonnet",
|
| 1548 |
+
"original_language": "eng_Latn",
|
| 1549 |
+
"target_language": "pag_Latn",
|
| 1550 |
+
"target_language_name": "Pangasinan",
|
| 1551 |
+
"speakers": 1100000,
|
| 1552 |
+
"bleu": 56.00481838266269
|
| 1553 |
+
},
|
| 1554 |
+
{
|
| 1555 |
+
"model": "anthropic/claude-3.5-sonnet",
|
| 1556 |
+
"original_language": "eng_Latn",
|
| 1557 |
+
"target_language": "kab_Latn",
|
| 1558 |
+
"target_language_name": "Kabyle",
|
| 1559 |
+
"speakers": 5586000,
|
| 1560 |
+
"bleu": 41.14429925869902
|
| 1561 |
+
},
|
| 1562 |
+
{
|
| 1563 |
+
"model": "anthropic/claude-3.5-sonnet",
|
| 1564 |
+
"original_language": "eng_Latn",
|
| 1565 |
+
"target_language": "bak_Cyrl",
|
| 1566 |
+
"target_language_name": "Bashkort",
|
| 1567 |
+
"speakers": 1200000,
|
| 1568 |
+
"bleu": 57.54538429274717
|
| 1569 |
+
},
|
| 1570 |
+
{
|
| 1571 |
+
"model": "anthropic/claude-3.5-sonnet",
|
| 1572 |
+
"original_language": "eng_Latn",
|
| 1573 |
+
"target_language": "twi_Latn_akua1239",
|
| 1574 |
+
"target_language_name": "Twi",
|
| 1575 |
+
"speakers": 3000000,
|
| 1576 |
+
"bleu": 45.1519376004116
|
| 1577 |
+
},
|
| 1578 |
+
{
|
| 1579 |
+
"model": "anthropic/claude-3.5-sonnet",
|
| 1580 |
+
"original_language": "eng_Latn",
|
| 1581 |
+
"target_language": "hin_Deva",
|
| 1582 |
+
"target_language_name": "Hindi",
|
| 1583 |
+
"speakers": 341000000,
|
| 1584 |
+
"bleu": 64.936216689785
|
| 1585 |
+
},
|
| 1586 |
+
{
|
| 1587 |
+
"model": "anthropic/claude-3.5-sonnet",
|
| 1588 |
+
"original_language": "eng_Latn",
|
| 1589 |
+
"target_language": "kas_Arab",
|
| 1590 |
+
"target_language_name": "Kashmiri",
|
| 1591 |
+
"speakers": 6900000,
|
| 1592 |
+
"bleu": 38.28328065553461
|
| 1593 |
+
},
|
| 1594 |
+
{
|
| 1595 |
+
"model": "anthropic/claude-3.5-sonnet",
|
| 1596 |
+
"original_language": "eng_Latn",
|
| 1597 |
+
"target_language": "mlt_Latn",
|
| 1598 |
+
"target_language_name": "Maltese",
|
| 1599 |
+
"speakers": 570000,
|
| 1600 |
+
"bleu": 80.08667772627608
|
| 1601 |
+
},
|
| 1602 |
+
{
|
| 1603 |
+
"model": "anthropic/claude-3.5-sonnet",
|
| 1604 |
+
"original_language": "eng_Latn",
|
| 1605 |
+
"target_language": "som_Latn",
|
| 1606 |
+
"target_language_name": "Somali",
|
| 1607 |
+
"speakers": 16200000,
|
| 1608 |
+
"bleu": 55.370649647294535
|
| 1609 |
+
},
|
| 1610 |
+
{
|
| 1611 |
+
"model": "anthropic/claude-3.5-sonnet",
|
| 1612 |
+
"original_language": "eng_Latn",
|
| 1613 |
+
"target_language": "hne_Deva",
|
| 1614 |
+
"target_language_name": "Chhattisgarhi",
|
| 1615 |
+
"speakers": 16300000,
|
| 1616 |
+
"bleu": 47.979750130407254
|
| 1617 |
+
},
|
| 1618 |
+
{
|
| 1619 |
+
"model": "anthropic/claude-3.5-sonnet",
|
| 1620 |
+
"original_language": "eng_Latn",
|
| 1621 |
+
"target_language": "glg_Latn",
|
| 1622 |
+
"target_language_name": "Galician",
|
| 1623 |
+
"speakers": 2500000,
|
| 1624 |
+
"bleu": 68.70247869041181
|
| 1625 |
+
},
|
| 1626 |
+
{
|
| 1627 |
+
"model": "anthropic/claude-3.5-sonnet",
|
| 1628 |
+
"original_language": "eng_Latn",
|
| 1629 |
+
"target_language": "ory_Orya",
|
| 1630 |
+
"target_language_name": "Odia",
|
| 1631 |
+
"speakers": 34500000,
|
| 1632 |
+
"bleu": 57.362809651798656
|
| 1633 |
+
},
|
| 1634 |
+
{
|
| 1635 |
+
"model": "anthropic/claude-3.5-sonnet",
|
| 1636 |
+
"original_language": "eng_Latn",
|
| 1637 |
+
"target_language": "nld_Latn",
|
| 1638 |
+
"target_language_name": "Dutch",
|
| 1639 |
+
"speakers": 23100000,
|
| 1640 |
+
"bleu": 71.18493263152928
|
| 1641 |
+
},
|
| 1642 |
+
{
|
| 1643 |
+
"model": "anthropic/claude-3.5-sonnet",
|
| 1644 |
+
"original_language": "eng_Latn",
|
| 1645 |
+
"target_language": "apc_Arab_sout3123",
|
| 1646 |
+
"target_language_name": " Levantine Arabic",
|
| 1647 |
+
"speakers": 44000000,
|
| 1648 |
+
"bleu": 55.666484540051364
|
| 1649 |
+
},
|
| 1650 |
+
{
|
| 1651 |
+
"model": "anthropic/claude-3.5-sonnet",
|
| 1652 |
+
"original_language": "eng_Latn",
|
| 1653 |
+
"target_language": "oci_Latn",
|
| 1654 |
+
"target_language_name": "Occitan",
|
| 1655 |
+
"speakers": 542000,
|
| 1656 |
+
"bleu": 71.53274018395614
|
| 1657 |
+
},
|
| 1658 |
+
{
|
| 1659 |
+
"model": "anthropic/claude-3.5-sonnet",
|
| 1660 |
+
"original_language": "eng_Latn",
|
| 1661 |
+
"target_language": "mni_Beng",
|
| 1662 |
+
"target_language_name": "Meitei",
|
| 1663 |
+
"speakers": 1470000,
|
| 1664 |
+
"bleu": 40.61648039338993
|
| 1665 |
+
},
|
| 1666 |
+
{
|
| 1667 |
+
"model": "anthropic/claude-3.5-sonnet",
|
| 1668 |
+
"original_language": "eng_Latn",
|
| 1669 |
+
"target_language": "hun_Latn",
|
| 1670 |
+
"target_language_name": "Hungarian",
|
| 1671 |
+
"speakers": 12600000,
|
| 1672 |
+
"bleu": 66.13011194084116
|
| 1673 |
+
},
|
| 1674 |
+
{
|
| 1675 |
+
"model": "anthropic/claude-3.5-sonnet",
|
| 1676 |
+
"original_language": "eng_Latn",
|
| 1677 |
+
"target_language": "bho_Deva",
|
| 1678 |
+
"target_language_name": "Bhojpuri",
|
| 1679 |
+
"speakers": 52200000,
|
| 1680 |
+
"bleu": 44.54123379070156
|
| 1681 |
+
},
|
| 1682 |
+
{
|
| 1683 |
+
"model": "anthropic/claude-3.5-sonnet",
|
| 1684 |
+
"original_language": "eng_Latn",
|
| 1685 |
+
"target_language": "mya_Mymr",
|
| 1686 |
+
"target_language_name": "Burmese",
|
| 1687 |
+
"speakers": 32900000,
|
| 1688 |
+
"bleu": 55.723591167735165
|
| 1689 |
+
},
|
| 1690 |
+
{
|
| 1691 |
+
"model": "anthropic/claude-3.5-sonnet",
|
| 1692 |
+
"original_language": "eng_Latn",
|
| 1693 |
+
"target_language": "run_Latn",
|
| 1694 |
+
"target_language_name": "Rundi",
|
| 1695 |
+
"speakers": 10800000,
|
| 1696 |
+
"bleu": 48.94351362900039
|
| 1697 |
+
},
|
| 1698 |
+
{
|
| 1699 |
+
"model": "anthropic/claude-3.5-sonnet",
|
| 1700 |
+
"original_language": "eng_Latn",
|
| 1701 |
+
"target_language": "ast_Latn",
|
| 1702 |
+
"target_language_name": "Asturian",
|
| 1703 |
+
"speakers": 450000,
|
| 1704 |
+
"bleu": 71.34456234933488
|
| 1705 |
+
},
|
| 1706 |
+
{
|
| 1707 |
+
"model": "anthropic/claude-3.5-sonnet",
|
| 1708 |
+
"original_language": "eng_Latn",
|
| 1709 |
+
"target_language": "tir_Ethi",
|
| 1710 |
+
"target_language_name": "Tigrigna",
|
| 1711 |
+
"speakers": 7507780,
|
| 1712 |
+
"bleu": 32.87119617033141
|
| 1713 |
+
},
|
| 1714 |
+
{
|
| 1715 |
+
"model": "anthropic/claude-3.5-sonnet",
|
| 1716 |
+
"original_language": "eng_Latn",
|
| 1717 |
+
"target_language": "kac_Latn",
|
| 1718 |
+
"target_language_name": "Jingpho",
|
| 1719 |
+
"speakers": 940000,
|
| 1720 |
+
"bleu": 43.550058140290794
|
| 1721 |
+
},
|
| 1722 |
+
{
|
| 1723 |
+
"model": "anthropic/claude-3.5-sonnet",
|
| 1724 |
+
"original_language": "eng_Latn",
|
| 1725 |
+
"target_language": "acm_Arab",
|
| 1726 |
+
"target_language_name": " Mesopotamian Arabic",
|
| 1727 |
+
"speakers": 15700000,
|
| 1728 |
+
"bleu": 50.086563426937225
|
| 1729 |
+
},
|
| 1730 |
+
{
|
| 1731 |
+
"model": "anthropic/claude-3.5-sonnet",
|
| 1732 |
+
"original_language": "eng_Latn",
|
| 1733 |
+
"target_language": "arz_Arab",
|
| 1734 |
+
"target_language_name": " Egyptian Arabic",
|
| 1735 |
+
"speakers": 100542400,
|
| 1736 |
+
"bleu": 54.06827805197923
|
| 1737 |
+
},
|
| 1738 |
+
{
|
| 1739 |
+
"model": "anthropic/claude-3.5-sonnet",
|
| 1740 |
+
"original_language": "eng_Latn",
|
| 1741 |
+
"target_language": "mhr_Cyrl",
|
| 1742 |
+
"target_language_name": " Meadow Mari",
|
| 1743 |
+
"speakers": 482000,
|
| 1744 |
+
"bleu": 49.560611727256386
|
| 1745 |
+
},
|
| 1746 |
+
{
|
| 1747 |
+
"model": "anthropic/claude-3.5-sonnet",
|
| 1748 |
+
"original_language": "eng_Latn",
|
| 1749 |
+
"target_language": "ita_Latn",
|
| 1750 |
+
"target_language_name": "Italian",
|
| 1751 |
+
"speakers": 64819790,
|
| 1752 |
+
"bleu": 69.15883435724486
|
| 1753 |
+
},
|
| 1754 |
+
{
|
| 1755 |
+
"model": "anthropic/claude-3.5-sonnet",
|
| 1756 |
+
"original_language": "eng_Latn",
|
| 1757 |
+
"target_language": "spa_Latn",
|
| 1758 |
+
"target_language_name": "Spanish",
|
| 1759 |
+
"speakers": 485000000,
|
| 1760 |
+
"bleu": 63.84670733785411
|
| 1761 |
+
},
|
| 1762 |
+
{
|
| 1763 |
+
"model": "anthropic/claude-3.5-sonnet",
|
| 1764 |
+
"original_language": "eng_Latn",
|
| 1765 |
+
"target_language": "ydd_Hebr",
|
| 1766 |
+
"target_language_name": " Eastern Yiddish",
|
| 1767 |
+
"speakers": 0,
|
| 1768 |
+
"bleu": 49.97450075850061
|
| 1769 |
+
},
|
| 1770 |
+
{
|
| 1771 |
+
"model": "anthropic/claude-3.5-sonnet",
|
| 1772 |
+
"original_language": "eng_Latn",
|
| 1773 |
+
"target_language": "gaz_Latn",
|
| 1774 |
+
"target_language_name": " West Central Oromo",
|
| 1775 |
+
"speakers": 0,
|
| 1776 |
+
"bleu": 47.19114355070805
|
| 1777 |
+
},
|
| 1778 |
+
{
|
| 1779 |
+
"model": "anthropic/claude-3.5-sonnet",
|
| 1780 |
+
"original_language": "eng_Latn",
|
| 1781 |
+
"target_language": "ktu_Latn",
|
| 1782 |
+
"target_language_name": "Kituba (Democratic Republic of the Congo)",
|
| 1783 |
+
"speakers": 0,
|
| 1784 |
+
"bleu": 52.848460160201476
|
| 1785 |
+
},
|
| 1786 |
+
{
|
| 1787 |
+
"model": "anthropic/claude-3.5-sonnet",
|
| 1788 |
+
"original_language": "eng_Latn",
|
| 1789 |
+
"target_language": "dyu_Latn",
|
| 1790 |
+
"target_language_name": "Jula",
|
| 1791 |
+
"speakers": 2700000,
|
| 1792 |
+
"bleu": 29.541518029704612
|
| 1793 |
+
},
|
| 1794 |
+
{
|
| 1795 |
+
"model": "anthropic/claude-3.5-sonnet",
|
| 1796 |
+
"original_language": "eng_Latn",
|
| 1797 |
+
"target_language": "ace_Latn",
|
| 1798 |
+
"target_language_name": "Aceh",
|
| 1799 |
+
"speakers": 3500032,
|
| 1800 |
+
"bleu": 54.98266447488466
|
| 1801 |
+
},
|
| 1802 |
+
{
|
| 1803 |
+
"model": "anthropic/claude-3.5-sonnet",
|
| 1804 |
+
"original_language": "eng_Latn",
|
| 1805 |
+
"target_language": "ckb_Arab",
|
| 1806 |
+
"target_language_name": " Central Kurdish",
|
| 1807 |
+
"speakers": 7250000,
|
| 1808 |
+
"bleu": 58.304911173323845
|
| 1809 |
+
},
|
| 1810 |
+
{
|
| 1811 |
+
"model": "anthropic/claude-3.5-sonnet",
|
| 1812 |
+
"original_language": "eng_Latn",
|
| 1813 |
+
"target_language": "mos_Latn",
|
| 1814 |
+
"target_language_name": "Moore",
|
| 1815 |
+
"speakers": 7600000,
|
| 1816 |
+
"bleu": 32.845809798291015
|
| 1817 |
+
},
|
| 1818 |
+
{
|
| 1819 |
+
"model": "anthropic/claude-3.5-sonnet",
|
| 1820 |
+
"original_language": "eng_Latn",
|
| 1821 |
+
"target_language": "kir_Cyrl",
|
| 1822 |
+
"target_language_name": "Kyrgyz",
|
| 1823 |
+
"speakers": 4568480,
|
| 1824 |
+
"bleu": 57.082442245268965
|
| 1825 |
+
},
|
| 1826 |
+
{
|
| 1827 |
+
"model": "anthropic/claude-3.5-sonnet",
|
| 1828 |
+
"original_language": "eng_Latn",
|
| 1829 |
+
"target_language": "npi_Deva",
|
| 1830 |
+
"target_language_name": "Nepali",
|
| 1831 |
+
"speakers": 0,
|
| 1832 |
+
"bleu": 55.29193473519464
|
| 1833 |
+
},
|
| 1834 |
+
{
|
| 1835 |
+
"model": "anthropic/claude-3.5-sonnet",
|
| 1836 |
+
"original_language": "eng_Latn",
|
| 1837 |
+
"target_language": "kbp_Latn",
|
| 1838 |
+
"target_language_name": "Kabiyè",
|
| 1839 |
+
"speakers": 1000000,
|
| 1840 |
+
"bleu": 22.549850465519835
|
| 1841 |
+
},
|
| 1842 |
+
{
|
| 1843 |
+
"model": "anthropic/claude-3.5-sonnet",
|
| 1844 |
+
"original_language": "eng_Latn",
|
| 1845 |
+
"target_language": "bem_Latn",
|
| 1846 |
+
"target_language_name": "Bemba",
|
| 1847 |
+
"speakers": 3600000,
|
| 1848 |
+
"bleu": 47.80685489558032
|
| 1849 |
}
|
| 1850 |
]
|
results_summary.json
CHANGED
|
@@ -1,77 +1,997 @@
|
|
| 1 |
[
|
| 2 |
{
|
| 3 |
"target_language_name":" Ayacucho Quechua",
|
| 4 |
-
"bleu":
|
| 5 |
"speakers":918200.0
|
| 6 |
},
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 7 |
{
|
| 8 |
"target_language_name":" Standard German",
|
| 9 |
-
"bleu":
|
| 10 |
"speakers":105000000.0
|
| 11 |
},
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 12 |
{
|
| 13 |
"target_language_name":" Tosk Albanian",
|
| 14 |
-
"bleu":
|
| 15 |
"speakers":3000000.0
|
| 16 |
},
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 17 |
{
|
| 18 |
"target_language_name":"Bali (Indonesia)",
|
| 19 |
-
"bleu":
|
| 20 |
"speakers":4000000.0
|
| 21 |
},
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 22 |
{
|
| 23 |
"target_language_name":"Banjar",
|
| 24 |
-
"bleu":
|
| 25 |
"speakers":3500000.0
|
| 26 |
},
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 27 |
{
|
| 28 |
"target_language_name":"Bhojpuri",
|
| 29 |
-
"bleu":
|
| 30 |
"speakers":52200000.0
|
| 31 |
},
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 32 |
{
|
| 33 |
"target_language_name":"Czech",
|
| 34 |
-
"bleu":
|
| 35 |
"speakers":10700000.0
|
| 36 |
},
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 37 |
{
|
| 38 |
"target_language_name":"Icelandic",
|
| 39 |
-
"bleu":
|
| 40 |
"speakers":358000.0
|
| 41 |
},
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 42 |
{
|
| 43 |
"target_language_name":"Indonesian",
|
| 44 |
-
"bleu":
|
| 45 |
"speakers":198996550.0
|
| 46 |
},
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 47 |
{
|
| 48 |
"target_language_name":"Kashmiri",
|
| 49 |
-
"bleu":
|
| 50 |
"speakers":6900000.0
|
| 51 |
},
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 52 |
{
|
| 53 |
"target_language_name":"Lingala",
|
| 54 |
-
"bleu":
|
| 55 |
"speakers":20000000.0
|
| 56 |
},
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 57 |
{
|
| 58 |
"target_language_name":"Nuer",
|
| 59 |
-
"bleu":
|
| 60 |
"speakers":900000.0
|
| 61 |
},
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 62 |
{
|
| 63 |
"target_language_name":"Polish",
|
| 64 |
-
"bleu":
|
| 65 |
"speakers":40200000.0
|
| 66 |
},
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 67 |
{
|
| 68 |
"target_language_name":"Sango",
|
| 69 |
-
"bleu":
|
| 70 |
"speakers":4600000.0
|
| 71 |
},
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 72 |
{
|
| 73 |
"target_language_name":"Serbian",
|
| 74 |
-
"bleu":
|
| 75 |
"speakers":9000000.0
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 76 |
}
|
| 77 |
]
|
|
|
|
| 1 |
[
|
| 2 |
{
|
| 3 |
"target_language_name":" Ayacucho Quechua",
|
| 4 |
+
"bleu":46.244412926,
|
| 5 |
"speakers":918200.0
|
| 6 |
},
|
| 7 |
+
{
|
| 8 |
+
"target_language_name":" Central Aymara",
|
| 9 |
+
"bleu":40.7737907059,
|
| 10 |
+
"speakers":0.0
|
| 11 |
+
},
|
| 12 |
+
{
|
| 13 |
+
"target_language_name":" Central Kurdish",
|
| 14 |
+
"bleu":58.3049111733,
|
| 15 |
+
"speakers":7250000.0
|
| 16 |
+
},
|
| 17 |
+
{
|
| 18 |
+
"target_language_name":" Central Tibetan",
|
| 19 |
+
"bleu":51.762059856,
|
| 20 |
+
"speakers":1200000.0
|
| 21 |
+
},
|
| 22 |
+
{
|
| 23 |
+
"target_language_name":" Eastern Punjabi",
|
| 24 |
+
"bleu":60.8335398677,
|
| 25 |
+
"speakers":125000000.0
|
| 26 |
+
},
|
| 27 |
+
{
|
| 28 |
+
"target_language_name":" Eastern Yiddish",
|
| 29 |
+
"bleu":49.9745007585,
|
| 30 |
+
"speakers":0.0
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"target_language_name":" Egyptian Arabic",
|
| 34 |
+
"bleu":54.068278052,
|
| 35 |
+
"speakers":100542400.0
|
| 36 |
+
},
|
| 37 |
+
{
|
| 38 |
+
"target_language_name":" Goan Konkani",
|
| 39 |
+
"bleu":46.8883507968,
|
| 40 |
+
"speakers":3633900.0
|
| 41 |
+
},
|
| 42 |
+
{
|
| 43 |
+
"target_language_name":" Halh Mongolian",
|
| 44 |
+
"bleu":59.1426397299,
|
| 45 |
+
"speakers":2704030.0
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"target_language_name":" Iranian Persian",
|
| 49 |
+
"bleu":57.466690672,
|
| 50 |
+
"speakers":52800000.0
|
| 51 |
+
},
|
| 52 |
+
{
|
| 53 |
+
"target_language_name":" Levantine Arabic",
|
| 54 |
+
"bleu":56.1658711447,
|
| 55 |
+
"speakers":44000000.0
|
| 56 |
+
},
|
| 57 |
+
{
|
| 58 |
+
"target_language_name":" Mandarin Chinese",
|
| 59 |
+
"bleu":42.5923366202,
|
| 60 |
+
"speakers":1074000000.0
|
| 61 |
+
},
|
| 62 |
+
{
|
| 63 |
+
"target_language_name":" Meadow Mari",
|
| 64 |
+
"bleu":49.5606117273,
|
| 65 |
+
"speakers":482000.0
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"target_language_name":" Merina Malagasy",
|
| 69 |
+
"bleu":60.4304388047,
|
| 70 |
+
"speakers":0.0
|
| 71 |
+
},
|
| 72 |
+
{
|
| 73 |
+
"target_language_name":" Mesopotamian Arabic",
|
| 74 |
+
"bleu":50.0865634269,
|
| 75 |
+
"speakers":15700000.0
|
| 76 |
+
},
|
| 77 |
+
{
|
| 78 |
+
"target_language_name":" Moroccan Arabic",
|
| 79 |
+
"bleu":48.5607873978,
|
| 80 |
+
"speakers":27500000.0
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"target_language_name":" Najdi Arabic",
|
| 84 |
+
"bleu":47.7692581451,
|
| 85 |
+
"speakers":0.0
|
| 86 |
+
},
|
| 87 |
+
{
|
| 88 |
+
"target_language_name":" Nigerian Fulfulde",
|
| 89 |
+
"bleu":28.2458571831,
|
| 90 |
+
"speakers":14500000.0
|
| 91 |
+
},
|
| 92 |
+
{
|
| 93 |
+
"target_language_name":" North Azerbaijani",
|
| 94 |
+
"bleu":55.0045961351,
|
| 95 |
+
"speakers":9220610.0
|
| 96 |
+
},
|
| 97 |
+
{
|
| 98 |
+
"target_language_name":" Northern Kurdish",
|
| 99 |
+
"bleu":55.0085600267,
|
| 100 |
+
"speakers":14600000.0
|
| 101 |
+
},
|
| 102 |
+
{
|
| 103 |
+
"target_language_name":" Northern Sotho",
|
| 104 |
+
"bleu":63.0482508066,
|
| 105 |
+
"speakers":4100000.0
|
| 106 |
+
},
|
| 107 |
+
{
|
| 108 |
+
"target_language_name":" Northern Uzbek",
|
| 109 |
+
"bleu":64.07804482,
|
| 110 |
+
"speakers":26912410.0
|
| 111 |
+
},
|
| 112 |
+
{
|
| 113 |
+
"target_language_name":" Paraguayan Guaran\u00ed",
|
| 114 |
+
"bleu":42.9023503897,
|
| 115 |
+
"speakers":0.0
|
| 116 |
+
},
|
| 117 |
+
{
|
| 118 |
+
"target_language_name":" South Azerbaijani",
|
| 119 |
+
"bleu":43.5362266708,
|
| 120 |
+
"speakers":15000000.0
|
| 121 |
+
},
|
| 122 |
+
{
|
| 123 |
+
"target_language_name":" Southern Pashto",
|
| 124 |
+
"bleu":38.5486962222,
|
| 125 |
+
"speakers":10900000.0
|
| 126 |
+
},
|
| 127 |
+
{
|
| 128 |
+
"target_language_name":" Southern Sotho",
|
| 129 |
+
"bleu":57.1537510266,
|
| 130 |
+
"speakers":6000000.0
|
| 131 |
+
},
|
| 132 |
+
{
|
| 133 |
+
"target_language_name":" Southwestern Dinka",
|
| 134 |
+
"bleu":12.4978320514,
|
| 135 |
+
"speakers":0.0
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"target_language_name":" Standard Arabic",
|
| 139 |
+
"bleu":56.6219786764,
|
| 140 |
+
"speakers":0.0
|
| 141 |
+
},
|
| 142 |
+
{
|
| 143 |
+
"target_language_name":" Standard Estonian",
|
| 144 |
+
"bleu":68.0693526943,
|
| 145 |
+
"speakers":1164770.0
|
| 146 |
+
},
|
| 147 |
{
|
| 148 |
"target_language_name":" Standard German",
|
| 149 |
+
"bleu":77.2213038369,
|
| 150 |
"speakers":105000000.0
|
| 151 |
},
|
| 152 |
+
{
|
| 153 |
+
"target_language_name":" Standard Latvian",
|
| 154 |
+
"bleu":64.8995188161,
|
| 155 |
+
"speakers":0.0
|
| 156 |
+
},
|
| 157 |
+
{
|
| 158 |
+
"target_language_name":" Standard Malay",
|
| 159 |
+
"bleu":75.5868255696,
|
| 160 |
+
"speakers":0.0
|
| 161 |
+
},
|
| 162 |
+
{
|
| 163 |
+
"target_language_name":" Standard Moroccan Tamazight",
|
| 164 |
+
"bleu":36.0211020389,
|
| 165 |
+
"speakers":0.0
|
| 166 |
+
},
|
| 167 |
+
{
|
| 168 |
+
"target_language_name":" Ta\u2019izzi-Adeni Arabic",
|
| 169 |
+
"bleu":48.6728574258,
|
| 170 |
+
"speakers":10500000.0
|
| 171 |
+
},
|
| 172 |
{
|
| 173 |
"target_language_name":" Tosk Albanian",
|
| 174 |
+
"bleu":69.2428556015,
|
| 175 |
"speakers":3000000.0
|
| 176 |
},
|
| 177 |
+
{
|
| 178 |
+
"target_language_name":" Tunisian Arabic",
|
| 179 |
+
"bleu":49.8735980011,
|
| 180 |
+
"speakers":11600000.0
|
| 181 |
+
},
|
| 182 |
+
{
|
| 183 |
+
"target_language_name":" West Central Oromo",
|
| 184 |
+
"bleu":47.1911435507,
|
| 185 |
+
"speakers":0.0
|
| 186 |
+
},
|
| 187 |
+
{
|
| 188 |
+
"target_language_name":" Yerwa Kanuri",
|
| 189 |
+
"bleu":18.4779991227,
|
| 190 |
+
"speakers":0.0
|
| 191 |
+
},
|
| 192 |
+
{
|
| 193 |
+
"target_language_name":" Yue Chinese",
|
| 194 |
+
"bleu":34.2560977082,
|
| 195 |
+
"speakers":73100000.0
|
| 196 |
+
},
|
| 197 |
+
{
|
| 198 |
+
"target_language_name":"Aceh",
|
| 199 |
+
"bleu":39.1659660901,
|
| 200 |
+
"speakers":3500032.0
|
| 201 |
+
},
|
| 202 |
+
{
|
| 203 |
+
"target_language_name":"Afrikaans",
|
| 204 |
+
"bleu":76.8900540777,
|
| 205 |
+
"speakers":10300000.0
|
| 206 |
+
},
|
| 207 |
+
{
|
| 208 |
+
"target_language_name":"Amharic",
|
| 209 |
+
"bleu":43.1544568697,
|
| 210 |
+
"speakers":25000000.0
|
| 211 |
+
},
|
| 212 |
+
{
|
| 213 |
+
"target_language_name":"Armenian",
|
| 214 |
+
"bleu":64.6804400806,
|
| 215 |
+
"speakers":6700000.0
|
| 216 |
+
},
|
| 217 |
+
{
|
| 218 |
+
"target_language_name":"Assamese",
|
| 219 |
+
"bleu":47.0351331605,
|
| 220 |
+
"speakers":15300000.0
|
| 221 |
+
},
|
| 222 |
+
{
|
| 223 |
+
"target_language_name":"Asturian",
|
| 224 |
+
"bleu":71.3445623493,
|
| 225 |
+
"speakers":450000.0
|
| 226 |
+
},
|
| 227 |
+
{
|
| 228 |
+
"target_language_name":"Awadhi",
|
| 229 |
+
"bleu":46.0797144146,
|
| 230 |
+
"speakers":22000000.0
|
| 231 |
+
},
|
| 232 |
{
|
| 233 |
"target_language_name":"Bali (Indonesia)",
|
| 234 |
+
"bleu":52.8752419159,
|
| 235 |
"speakers":4000000.0
|
| 236 |
},
|
| 237 |
+
{
|
| 238 |
+
"target_language_name":"Bamanankan",
|
| 239 |
+
"bleu":38.6939091408,
|
| 240 |
+
"speakers":2700000.0
|
| 241 |
+
},
|
| 242 |
{
|
| 243 |
"target_language_name":"Banjar",
|
| 244 |
+
"bleu":46.5453977487,
|
| 245 |
"speakers":3500000.0
|
| 246 |
},
|
| 247 |
+
{
|
| 248 |
+
"target_language_name":"Bashkort",
|
| 249 |
+
"bleu":57.5453842927,
|
| 250 |
+
"speakers":1200000.0
|
| 251 |
+
},
|
| 252 |
+
{
|
| 253 |
+
"target_language_name":"Basque",
|
| 254 |
+
"bleu":65.8968721377,
|
| 255 |
+
"speakers":750000.0
|
| 256 |
+
},
|
| 257 |
+
{
|
| 258 |
+
"target_language_name":"Belarusian",
|
| 259 |
+
"bleu":54.5195166442,
|
| 260 |
+
"speakers":7900000.0
|
| 261 |
+
},
|
| 262 |
+
{
|
| 263 |
+
"target_language_name":"Bemba",
|
| 264 |
+
"bleu":47.8068548956,
|
| 265 |
+
"speakers":3600000.0
|
| 266 |
+
},
|
| 267 |
+
{
|
| 268 |
+
"target_language_name":"Bengali",
|
| 269 |
+
"bleu":57.1417588816,
|
| 270 |
+
"speakers":300000000.0
|
| 271 |
+
},
|
| 272 |
{
|
| 273 |
"target_language_name":"Bhojpuri",
|
| 274 |
+
"bleu":44.5412337907,
|
| 275 |
"speakers":52200000.0
|
| 276 |
},
|
| 277 |
+
{
|
| 278 |
+
"target_language_name":"Bokm\u00e5l",
|
| 279 |
+
"bleu":77.4939513016,
|
| 280 |
+
"speakers":4000000.0
|
| 281 |
+
},
|
| 282 |
+
{
|
| 283 |
+
"target_language_name":"Boro (India)",
|
| 284 |
+
"bleu":36.1100474969,
|
| 285 |
+
"speakers":1482929.0
|
| 286 |
+
},
|
| 287 |
+
{
|
| 288 |
+
"target_language_name":"Bosnian",
|
| 289 |
+
"bleu":72.5488027131,
|
| 290 |
+
"speakers":3500000.0
|
| 291 |
+
},
|
| 292 |
+
{
|
| 293 |
+
"target_language_name":"Bugis",
|
| 294 |
+
"bleu":44.8388170031,
|
| 295 |
+
"speakers":5017800.0
|
| 296 |
+
},
|
| 297 |
+
{
|
| 298 |
+
"target_language_name":"Bulgarian",
|
| 299 |
+
"bleu":72.9695925131,
|
| 300 |
+
"speakers":9000000.0
|
| 301 |
+
},
|
| 302 |
+
{
|
| 303 |
+
"target_language_name":"Burmese",
|
| 304 |
+
"bleu":55.7235911677,
|
| 305 |
+
"speakers":32900000.0
|
| 306 |
+
},
|
| 307 |
+
{
|
| 308 |
+
"target_language_name":"Catalan",
|
| 309 |
+
"bleu":74.4595007932,
|
| 310 |
+
"speakers":5100000.0
|
| 311 |
+
},
|
| 312 |
+
{
|
| 313 |
+
"target_language_name":"Cebuano",
|
| 314 |
+
"bleu":69.4557958655,
|
| 315 |
+
"speakers":15900000.0
|
| 316 |
+
},
|
| 317 |
+
{
|
| 318 |
+
"target_language_name":"Chhattisgarhi",
|
| 319 |
+
"bleu":47.9797501304,
|
| 320 |
+
"speakers":16300000.0
|
| 321 |
+
},
|
| 322 |
+
{
|
| 323 |
+
"target_language_name":"Chichewa",
|
| 324 |
+
"bleu":59.7601680161,
|
| 325 |
+
"speakers":12000000.0
|
| 326 |
+
},
|
| 327 |
+
{
|
| 328 |
+
"target_language_name":"Chokwe",
|
| 329 |
+
"bleu":10.1864074161,
|
| 330 |
+
"speakers":0.0
|
| 331 |
+
},
|
| 332 |
+
{
|
| 333 |
+
"target_language_name":"Chuvash",
|
| 334 |
+
"bleu":45.0546658723,
|
| 335 |
+
"speakers":1279650.0
|
| 336 |
+
},
|
| 337 |
+
{
|
| 338 |
+
"target_language_name":"Crimean Tatar",
|
| 339 |
+
"bleu":52.7050249448,
|
| 340 |
+
"speakers":552740.0
|
| 341 |
+
},
|
| 342 |
+
{
|
| 343 |
+
"target_language_name":"Croatian",
|
| 344 |
+
"bleu":69.5456983662,
|
| 345 |
+
"speakers":7000000.0
|
| 346 |
+
},
|
| 347 |
{
|
| 348 |
"target_language_name":"Czech",
|
| 349 |
+
"bleu":69.7112290599,
|
| 350 |
"speakers":10700000.0
|
| 351 |
},
|
| 352 |
+
{
|
| 353 |
+
"target_language_name":"Danish",
|
| 354 |
+
"bleu":78.0935433284,
|
| 355 |
+
"speakers":6000000.0
|
| 356 |
+
},
|
| 357 |
+
{
|
| 358 |
+
"target_language_name":"Dari",
|
| 359 |
+
"bleu":52.5539795795,
|
| 360 |
+
"speakers":9600000.0
|
| 361 |
+
},
|
| 362 |
+
{
|
| 363 |
+
"target_language_name":"Dholuo",
|
| 364 |
+
"bleu":46.4119479071,
|
| 365 |
+
"speakers":3000000.0
|
| 366 |
+
},
|
| 367 |
+
{
|
| 368 |
+
"target_language_name":"Dogri",
|
| 369 |
+
"bleu":44.9153535278,
|
| 370 |
+
"speakers":2000000.0
|
| 371 |
+
},
|
| 372 |
+
{
|
| 373 |
+
"target_language_name":"Dutch",
|
| 374 |
+
"bleu":71.1849326315,
|
| 375 |
+
"speakers":23100000.0
|
| 376 |
+
},
|
| 377 |
+
{
|
| 378 |
+
"target_language_name":"Dzongkha",
|
| 379 |
+
"bleu":44.3573814017,
|
| 380 |
+
"speakers":237080.0
|
| 381 |
+
},
|
| 382 |
+
{
|
| 383 |
+
"target_language_name":"Esperanto",
|
| 384 |
+
"bleu":69.6056577554,
|
| 385 |
+
"speakers":2000000.0
|
| 386 |
+
},
|
| 387 |
+
{
|
| 388 |
+
"target_language_name":"Faroese",
|
| 389 |
+
"bleu":65.9147902483,
|
| 390 |
+
"speakers":69150.0
|
| 391 |
+
},
|
| 392 |
+
{
|
| 393 |
+
"target_language_name":"Fijian",
|
| 394 |
+
"bleu":58.2892667246,
|
| 395 |
+
"speakers":341270.0
|
| 396 |
+
},
|
| 397 |
+
{
|
| 398 |
+
"target_language_name":"Filipino",
|
| 399 |
+
"bleu":70.1928498378,
|
| 400 |
+
"speakers":90000000.0
|
| 401 |
+
},
|
| 402 |
+
{
|
| 403 |
+
"target_language_name":"Finnish",
|
| 404 |
+
"bleu":70.9425029518,
|
| 405 |
+
"speakers":5413380.0
|
| 406 |
+
},
|
| 407 |
+
{
|
| 408 |
+
"target_language_name":"Fon",
|
| 409 |
+
"bleu":25.2797773666,
|
| 410 |
+
"speakers":1935500.0
|
| 411 |
+
},
|
| 412 |
+
{
|
| 413 |
+
"target_language_name":"French",
|
| 414 |
+
"bleu":79.3023871219,
|
| 415 |
+
"speakers":208157220.0
|
| 416 |
+
},
|
| 417 |
+
{
|
| 418 |
+
"target_language_name":"Friulian",
|
| 419 |
+
"bleu":66.5488092372,
|
| 420 |
+
"speakers":300000.0
|
| 421 |
+
},
|
| 422 |
+
{
|
| 423 |
+
"target_language_name":"Galician",
|
| 424 |
+
"bleu":68.7024786904,
|
| 425 |
+
"speakers":2500000.0
|
| 426 |
+
},
|
| 427 |
+
{
|
| 428 |
+
"target_language_name":"Ganda",
|
| 429 |
+
"bleu":45.8693322936,
|
| 430 |
+
"speakers":4100000.0
|
| 431 |
+
},
|
| 432 |
+
{
|
| 433 |
+
"target_language_name":"Georgian",
|
| 434 |
+
"bleu":61.0166361442,
|
| 435 |
+
"speakers":3700000.0
|
| 436 |
+
},
|
| 437 |
+
{
|
| 438 |
+
"target_language_name":"Gikuyu",
|
| 439 |
+
"bleu":40.9288275291,
|
| 440 |
+
"speakers":6623000.0
|
| 441 |
+
},
|
| 442 |
+
{
|
| 443 |
+
"target_language_name":"Greek",
|
| 444 |
+
"bleu":66.2347782153,
|
| 445 |
+
"speakers":15000000.0
|
| 446 |
+
},
|
| 447 |
+
{
|
| 448 |
+
"target_language_name":"Gujarati",
|
| 449 |
+
"bleu":55.5884513452,
|
| 450 |
+
"speakers":56400000.0
|
| 451 |
+
},
|
| 452 |
+
{
|
| 453 |
+
"target_language_name":"Haitian Creole",
|
| 454 |
+
"bleu":63.8532187591,
|
| 455 |
+
"speakers":9600000.0
|
| 456 |
+
},
|
| 457 |
+
{
|
| 458 |
+
"target_language_name":"Hausa",
|
| 459 |
+
"bleu":56.3431957901,
|
| 460 |
+
"speakers":43900000.0
|
| 461 |
+
},
|
| 462 |
+
{
|
| 463 |
+
"target_language_name":"Hebrew",
|
| 464 |
+
"bleu":72.0702990513,
|
| 465 |
+
"speakers":9303950.0
|
| 466 |
+
},
|
| 467 |
+
{
|
| 468 |
+
"target_language_name":"Hindi",
|
| 469 |
+
"bleu":64.9362166898,
|
| 470 |
+
"speakers":341000000.0
|
| 471 |
+
},
|
| 472 |
+
{
|
| 473 |
+
"target_language_name":"Hungarian",
|
| 474 |
+
"bleu":66.1301119408,
|
| 475 |
+
"speakers":12600000.0
|
| 476 |
+
},
|
| 477 |
{
|
| 478 |
"target_language_name":"Icelandic",
|
| 479 |
+
"bleu":54.4330055353,
|
| 480 |
"speakers":358000.0
|
| 481 |
},
|
| 482 |
+
{
|
| 483 |
+
"target_language_name":"Igbo",
|
| 484 |
+
"bleu":46.4017344934,
|
| 485 |
+
"speakers":27000000.0
|
| 486 |
+
},
|
| 487 |
+
{
|
| 488 |
+
"target_language_name":"Ilocano",
|
| 489 |
+
"bleu":62.6058864594,
|
| 490 |
+
"speakers":9100000.0
|
| 491 |
+
},
|
| 492 |
{
|
| 493 |
"target_language_name":"Indonesian",
|
| 494 |
+
"bleu":72.9087066262,
|
| 495 |
"speakers":198996550.0
|
| 496 |
},
|
| 497 |
+
{
|
| 498 |
+
"target_language_name":"Irish",
|
| 499 |
+
"bleu":69.9725194524,
|
| 500 |
+
"speakers":1030000.0
|
| 501 |
+
},
|
| 502 |
+
{
|
| 503 |
+
"target_language_name":"Italian",
|
| 504 |
+
"bleu":69.1588343572,
|
| 505 |
+
"speakers":64819790.0
|
| 506 |
+
},
|
| 507 |
+
{
|
| 508 |
+
"target_language_name":"Japanese",
|
| 509 |
+
"bleu":49.9166135693,
|
| 510 |
+
"speakers":128000000.0
|
| 511 |
+
},
|
| 512 |
+
{
|
| 513 |
+
"target_language_name":"Javanese",
|
| 514 |
+
"bleu":60.440335299,
|
| 515 |
+
"speakers":84308740.0
|
| 516 |
+
},
|
| 517 |
+
{
|
| 518 |
+
"target_language_name":"Jingpho",
|
| 519 |
+
"bleu":43.5500581403,
|
| 520 |
+
"speakers":940000.0
|
| 521 |
+
},
|
| 522 |
+
{
|
| 523 |
+
"target_language_name":"Jula",
|
| 524 |
+
"bleu":29.5415180297,
|
| 525 |
+
"speakers":2700000.0
|
| 526 |
+
},
|
| 527 |
+
{
|
| 528 |
+
"target_language_name":"Kabiy\u00e8",
|
| 529 |
+
"bleu":22.5498504655,
|
| 530 |
+
"speakers":1000000.0
|
| 531 |
+
},
|
| 532 |
+
{
|
| 533 |
+
"target_language_name":"Kabuverdianu",
|
| 534 |
+
"bleu":65.1106010391,
|
| 535 |
+
"speakers":871000.0
|
| 536 |
+
},
|
| 537 |
+
{
|
| 538 |
+
"target_language_name":"Kabyle",
|
| 539 |
+
"bleu":41.1442992587,
|
| 540 |
+
"speakers":5586000.0
|
| 541 |
+
},
|
| 542 |
+
{
|
| 543 |
+
"target_language_name":"Kamba",
|
| 544 |
+
"bleu":41.733489671,
|
| 545 |
+
"speakers":3893000.0
|
| 546 |
+
},
|
| 547 |
+
{
|
| 548 |
+
"target_language_name":"Kannada",
|
| 549 |
+
"bleu":60.0142028332,
|
| 550 |
+
"speakers":43600000.0
|
| 551 |
+
},
|
| 552 |
{
|
| 553 |
"target_language_name":"Kashmiri",
|
| 554 |
+
"bleu":22.3019416547,
|
| 555 |
"speakers":6900000.0
|
| 556 |
},
|
| 557 |
+
{
|
| 558 |
+
"target_language_name":"Kazakh",
|
| 559 |
+
"bleu":61.1251621375,
|
| 560 |
+
"speakers":13161980.0
|
| 561 |
+
},
|
| 562 |
+
{
|
| 563 |
+
"target_language_name":"Khmer",
|
| 564 |
+
"bleu":49.2098257043,
|
| 565 |
+
"speakers":16600000.0
|
| 566 |
+
},
|
| 567 |
+
{
|
| 568 |
+
"target_language_name":"Kimbundu",
|
| 569 |
+
"bleu":5.8523457224,
|
| 570 |
+
"speakers":0.0
|
| 571 |
+
},
|
| 572 |
+
{
|
| 573 |
+
"target_language_name":"Kinyarwanda",
|
| 574 |
+
"bleu":57.2410626756,
|
| 575 |
+
"speakers":12100000.0
|
| 576 |
+
},
|
| 577 |
+
{
|
| 578 |
+
"target_language_name":"Kituba (Democratic Republic of the Congo)",
|
| 579 |
+
"bleu":52.8484601602,
|
| 580 |
+
"speakers":0.0
|
| 581 |
+
},
|
| 582 |
+
{
|
| 583 |
+
"target_language_name":"Korean",
|
| 584 |
+
"bleu":43.6872285974,
|
| 585 |
+
"speakers":77300000.0
|
| 586 |
+
},
|
| 587 |
+
{
|
| 588 |
+
"target_language_name":"Kyrgyz",
|
| 589 |
+
"bleu":57.0824422453,
|
| 590 |
+
"speakers":4568480.0
|
| 591 |
+
},
|
| 592 |
+
{
|
| 593 |
+
"target_language_name":"Lao",
|
| 594 |
+
"bleu":60.0210909677,
|
| 595 |
+
"speakers":5225552.0
|
| 596 |
+
},
|
| 597 |
+
{
|
| 598 |
+
"target_language_name":"Latgalian",
|
| 599 |
+
"bleu":56.4843556524,
|
| 600 |
+
"speakers":200000.0
|
| 601 |
+
},
|
| 602 |
+
{
|
| 603 |
+
"target_language_name":"Ligurian",
|
| 604 |
+
"bleu":55.8530636302,
|
| 605 |
+
"speakers":500000.0
|
| 606 |
+
},
|
| 607 |
+
{
|
| 608 |
+
"target_language_name":"Limburgish",
|
| 609 |
+
"bleu":59.4485504982,
|
| 610 |
+
"speakers":1600000.0
|
| 611 |
+
},
|
| 612 |
{
|
| 613 |
"target_language_name":"Lingala",
|
| 614 |
+
"bleu":30.4322896531,
|
| 615 |
"speakers":20000000.0
|
| 616 |
},
|
| 617 |
+
{
|
| 618 |
+
"target_language_name":"Lithuanian",
|
| 619 |
+
"bleu":67.1625695571,
|
| 620 |
+
"speakers":4000000.0
|
| 621 |
+
},
|
| 622 |
+
{
|
| 623 |
+
"target_language_name":"Lombard",
|
| 624 |
+
"bleu":46.3884402674,
|
| 625 |
+
"speakers":3900000.0
|
| 626 |
+
},
|
| 627 |
+
{
|
| 628 |
+
"target_language_name":"Luba-Kasai",
|
| 629 |
+
"bleu":45.0655291655,
|
| 630 |
+
"speakers":6300000.0
|
| 631 |
+
},
|
| 632 |
+
{
|
| 633 |
+
"target_language_name":"Luxembourgish",
|
| 634 |
+
"bleu":70.8338190438,
|
| 635 |
+
"speakers":391200.0
|
| 636 |
+
},
|
| 637 |
+
{
|
| 638 |
+
"target_language_name":"Macedonian",
|
| 639 |
+
"bleu":72.2733471437,
|
| 640 |
+
"speakers":2000000.0
|
| 641 |
+
},
|
| 642 |
+
{
|
| 643 |
+
"target_language_name":"Magahi",
|
| 644 |
+
"bleu":58.5474221546,
|
| 645 |
+
"speakers":20700000.0
|
| 646 |
+
},
|
| 647 |
+
{
|
| 648 |
+
"target_language_name":"Maithili",
|
| 649 |
+
"bleu":54.6530071391,
|
| 650 |
+
"speakers":33900000.0
|
| 651 |
+
},
|
| 652 |
+
{
|
| 653 |
+
"target_language_name":"Malayalam",
|
| 654 |
+
"bleu":64.0655894091,
|
| 655 |
+
"speakers":37100000.0
|
| 656 |
+
},
|
| 657 |
+
{
|
| 658 |
+
"target_language_name":"Maltese",
|
| 659 |
+
"bleu":80.0866777263,
|
| 660 |
+
"speakers":570000.0
|
| 661 |
+
},
|
| 662 |
+
{
|
| 663 |
+
"target_language_name":"Maori",
|
| 664 |
+
"bleu":54.8319935643,
|
| 665 |
+
"speakers":160000.0
|
| 666 |
+
},
|
| 667 |
+
{
|
| 668 |
+
"target_language_name":"Marathi",
|
| 669 |
+
"bleu":57.4434090711,
|
| 670 |
+
"speakers":83100000.0
|
| 671 |
+
},
|
| 672 |
+
{
|
| 673 |
+
"target_language_name":"Meitei",
|
| 674 |
+
"bleu":41.2619945571,
|
| 675 |
+
"speakers":1470000.0
|
| 676 |
+
},
|
| 677 |
+
{
|
| 678 |
+
"target_language_name":"Minangkabau",
|
| 679 |
+
"bleu":50.7407956197,
|
| 680 |
+
"speakers":5530000.0
|
| 681 |
+
},
|
| 682 |
+
{
|
| 683 |
+
"target_language_name":"Mizo",
|
| 684 |
+
"bleu":51.6558017488,
|
| 685 |
+
"speakers":500000.0
|
| 686 |
+
},
|
| 687 |
+
{
|
| 688 |
+
"target_language_name":"Moore",
|
| 689 |
+
"bleu":32.8458097983,
|
| 690 |
+
"speakers":7600000.0
|
| 691 |
+
},
|
| 692 |
+
{
|
| 693 |
+
"target_language_name":"Nepali",
|
| 694 |
+
"bleu":55.2919347352,
|
| 695 |
+
"speakers":0.0
|
| 696 |
+
},
|
| 697 |
{
|
| 698 |
"target_language_name":"Nuer",
|
| 699 |
+
"bleu":16.5796987951,
|
| 700 |
"speakers":900000.0
|
| 701 |
},
|
| 702 |
+
{
|
| 703 |
+
"target_language_name":"N\u2019Ko",
|
| 704 |
+
"bleu":32.483490799,
|
| 705 |
+
"speakers":0.0
|
| 706 |
+
},
|
| 707 |
+
{
|
| 708 |
+
"target_language_name":"Occitan",
|
| 709 |
+
"bleu":71.532740184,
|
| 710 |
+
"speakers":542000.0
|
| 711 |
+
},
|
| 712 |
+
{
|
| 713 |
+
"target_language_name":"Odia",
|
| 714 |
+
"bleu":57.3628096518,
|
| 715 |
+
"speakers":34500000.0
|
| 716 |
+
},
|
| 717 |
+
{
|
| 718 |
+
"target_language_name":"Pangasinan",
|
| 719 |
+
"bleu":56.0048183827,
|
| 720 |
+
"speakers":1100000.0
|
| 721 |
+
},
|
| 722 |
+
{
|
| 723 |
+
"target_language_name":"Papiamentu",
|
| 724 |
+
"bleu":69.7955328133,
|
| 725 |
+
"speakers":321300.0
|
| 726 |
+
},
|
| 727 |
{
|
| 728 |
"target_language_name":"Polish",
|
| 729 |
+
"bleu":61.8768399674,
|
| 730 |
"speakers":40200000.0
|
| 731 |
},
|
| 732 |
+
{
|
| 733 |
+
"target_language_name":"Portuguese",
|
| 734 |
+
"bleu":77.4978074222,
|
| 735 |
+
"speakers":254300000.0
|
| 736 |
+
},
|
| 737 |
+
{
|
| 738 |
+
"target_language_name":"Romanian",
|
| 739 |
+
"bleu":76.4907159035,
|
| 740 |
+
"speakers":24300000.0
|
| 741 |
+
},
|
| 742 |
+
{
|
| 743 |
+
"target_language_name":"Rundi",
|
| 744 |
+
"bleu":48.943513629,
|
| 745 |
+
"speakers":10800000.0
|
| 746 |
+
},
|
| 747 |
+
{
|
| 748 |
+
"target_language_name":"Russian",
|
| 749 |
+
"bleu":71.1489441039,
|
| 750 |
+
"speakers":171428900.0
|
| 751 |
+
},
|
| 752 |
+
{
|
| 753 |
+
"target_language_name":"Samoan",
|
| 754 |
+
"bleu":56.7138831423,
|
| 755 |
+
"speakers":415720.0
|
| 756 |
+
},
|
| 757 |
{
|
| 758 |
"target_language_name":"Sango",
|
| 759 |
+
"bleu":34.8754222657,
|
| 760 |
"speakers":4600000.0
|
| 761 |
},
|
| 762 |
+
{
|
| 763 |
+
"target_language_name":"Sanskrit",
|
| 764 |
+
"bleu":32.7813249911,
|
| 765 |
+
"speakers":49736.0
|
| 766 |
+
},
|
| 767 |
+
{
|
| 768 |
+
"target_language_name":"Santhali",
|
| 769 |
+
"bleu":31.5119247269,
|
| 770 |
+
"speakers":7200000.0
|
| 771 |
+
},
|
| 772 |
+
{
|
| 773 |
+
"target_language_name":"Sardinian",
|
| 774 |
+
"bleu":62.6903914771,
|
| 775 |
+
"speakers":1300000.0
|
| 776 |
+
},
|
| 777 |
+
{
|
| 778 |
+
"target_language_name":"Scottish Gaelic",
|
| 779 |
+
"bleu":62.6044371338,
|
| 780 |
+
"speakers":60130.0
|
| 781 |
+
},
|
| 782 |
{
|
| 783 |
"target_language_name":"Serbian",
|
| 784 |
+
"bleu":69.9691396176,
|
| 785 |
"speakers":9000000.0
|
| 786 |
+
},
|
| 787 |
+
{
|
| 788 |
+
"target_language_name":"Setswana",
|
| 789 |
+
"bleu":55.2288890228,
|
| 790 |
+
"speakers":4500000.0
|
| 791 |
+
},
|
| 792 |
+
{
|
| 793 |
+
"target_language_name":"Shan",
|
| 794 |
+
"bleu":29.2129948577,
|
| 795 |
+
"speakers":3000000.0
|
| 796 |
+
},
|
| 797 |
+
{
|
| 798 |
+
"target_language_name":"Shona",
|
| 799 |
+
"bleu":51.5592191405,
|
| 800 |
+
"speakers":9023000.0
|
| 801 |
+
},
|
| 802 |
+
{
|
| 803 |
+
"target_language_name":"Sicilian",
|
| 804 |
+
"bleu":58.5895359443,
|
| 805 |
+
"speakers":4700000.0
|
| 806 |
+
},
|
| 807 |
+
{
|
| 808 |
+
"target_language_name":"Silesian",
|
| 809 |
+
"bleu":56.7836392069,
|
| 810 |
+
"speakers":522000.0
|
| 811 |
+
},
|
| 812 |
+
{
|
| 813 |
+
"target_language_name":"Sindhi",
|
| 814 |
+
"bleu":48.1876056648,
|
| 815 |
+
"speakers":25000000.0
|
| 816 |
+
},
|
| 817 |
+
{
|
| 818 |
+
"target_language_name":"Sinhala",
|
| 819 |
+
"bleu":56.7567311796,
|
| 820 |
+
"speakers":15300000.0
|
| 821 |
+
},
|
| 822 |
+
{
|
| 823 |
+
"target_language_name":"Slovak",
|
| 824 |
+
"bleu":67.9284804086,
|
| 825 |
+
"speakers":6000000.0
|
| 826 |
+
},
|
| 827 |
+
{
|
| 828 |
+
"target_language_name":"Slovene",
|
| 829 |
+
"bleu":72.5691270757,
|
| 830 |
+
"speakers":2400000.0
|
| 831 |
+
},
|
| 832 |
+
{
|
| 833 |
+
"target_language_name":"Somali",
|
| 834 |
+
"bleu":55.3706496473,
|
| 835 |
+
"speakers":16200000.0
|
| 836 |
+
},
|
| 837 |
+
{
|
| 838 |
+
"target_language_name":"Spanish",
|
| 839 |
+
"bleu":63.8467073379,
|
| 840 |
+
"speakers":485000000.0
|
| 841 |
+
},
|
| 842 |
+
{
|
| 843 |
+
"target_language_name":"Sunda",
|
| 844 |
+
"bleu":56.4065999104,
|
| 845 |
+
"speakers":32400000.0
|
| 846 |
+
},
|
| 847 |
+
{
|
| 848 |
+
"target_language_name":"Swahili",
|
| 849 |
+
"bleu":73.5199042142,
|
| 850 |
+
"speakers":82300000.0
|
| 851 |
+
},
|
| 852 |
+
{
|
| 853 |
+
"target_language_name":"Swati",
|
| 854 |
+
"bleu":52.7746096439,
|
| 855 |
+
"speakers":2034200.0
|
| 856 |
+
},
|
| 857 |
+
{
|
| 858 |
+
"target_language_name":"Swedish",
|
| 859 |
+
"bleu":77.421610247,
|
| 860 |
+
"speakers":9244250.0
|
| 861 |
+
},
|
| 862 |
+
{
|
| 863 |
+
"target_language_name":"Tajik",
|
| 864 |
+
"bleu":60.9783684158,
|
| 865 |
+
"speakers":14000000.0
|
| 866 |
+
},
|
| 867 |
+
{
|
| 868 |
+
"target_language_name":"Tamasheq",
|
| 869 |
+
"bleu":18.4319889721,
|
| 870 |
+
"speakers":500000.0
|
| 871 |
+
},
|
| 872 |
+
{
|
| 873 |
+
"target_language_name":"Tamil",
|
| 874 |
+
"bleu":65.7863221054,
|
| 875 |
+
"speakers":75000000.0
|
| 876 |
+
},
|
| 877 |
+
{
|
| 878 |
+
"target_language_name":"Tatar",
|
| 879 |
+
"bleu":60.3447467213,
|
| 880 |
+
"speakers":5427318.0
|
| 881 |
+
},
|
| 882 |
+
{
|
| 883 |
+
"target_language_name":"Telugu",
|
| 884 |
+
"bleu":61.6352457629,
|
| 885 |
+
"speakers":82000000.0
|
| 886 |
+
},
|
| 887 |
+
{
|
| 888 |
+
"target_language_name":"Thai",
|
| 889 |
+
"bleu":62.8125360944,
|
| 890 |
+
"speakers":40000000.0
|
| 891 |
+
},
|
| 892 |
+
{
|
| 893 |
+
"target_language_name":"Tigrigna",
|
| 894 |
+
"bleu":32.8711961703,
|
| 895 |
+
"speakers":7507780.0
|
| 896 |
+
},
|
| 897 |
+
{
|
| 898 |
+
"target_language_name":"Tok Pisin",
|
| 899 |
+
"bleu":56.5407760367,
|
| 900 |
+
"speakers":4000000.0
|
| 901 |
+
},
|
| 902 |
+
{
|
| 903 |
+
"target_language_name":"Tsonga",
|
| 904 |
+
"bleu":58.3516573597,
|
| 905 |
+
"speakers":13000000.0
|
| 906 |
+
},
|
| 907 |
+
{
|
| 908 |
+
"target_language_name":"Tumbuka",
|
| 909 |
+
"bleu":44.0490017392,
|
| 910 |
+
"speakers":2680000.0
|
| 911 |
+
},
|
| 912 |
+
{
|
| 913 |
+
"target_language_name":"Turkish",
|
| 914 |
+
"bleu":67.1600625676,
|
| 915 |
+
"speakers":82231620.0
|
| 916 |
+
},
|
| 917 |
+
{
|
| 918 |
+
"target_language_name":"Turkmen",
|
| 919 |
+
"bleu":60.5593705936,
|
| 920 |
+
"speakers":16000000.0
|
| 921 |
+
},
|
| 922 |
+
{
|
| 923 |
+
"target_language_name":"Twi",
|
| 924 |
+
"bleu":44.7976562068,
|
| 925 |
+
"speakers":3000000.0
|
| 926 |
+
},
|
| 927 |
+
{
|
| 928 |
+
"target_language_name":"Ukrainian",
|
| 929 |
+
"bleu":68.0976232544,
|
| 930 |
+
"speakers":34710100.0
|
| 931 |
+
},
|
| 932 |
+
{
|
| 933 |
+
"target_language_name":"Umbundu",
|
| 934 |
+
"bleu":21.0802775597,
|
| 935 |
+
"speakers":6000000.0
|
| 936 |
+
},
|
| 937 |
+
{
|
| 938 |
+
"target_language_name":"Urdu",
|
| 939 |
+
"bleu":61.1255457272,
|
| 940 |
+
"speakers":94022900.0
|
| 941 |
+
},
|
| 942 |
+
{
|
| 943 |
+
"target_language_name":"Uyghur",
|
| 944 |
+
"bleu":53.5346877103,
|
| 945 |
+
"speakers":10400000.0
|
| 946 |
+
},
|
| 947 |
+
{
|
| 948 |
+
"target_language_name":"Venetian",
|
| 949 |
+
"bleu":60.6140876271,
|
| 950 |
+
"speakers":2000000.0
|
| 951 |
+
},
|
| 952 |
+
{
|
| 953 |
+
"target_language_name":"Vietnamese",
|
| 954 |
+
"bleu":70.3560749464,
|
| 955 |
+
"speakers":76000000.0
|
| 956 |
+
},
|
| 957 |
+
{
|
| 958 |
+
"target_language_name":"Waray-Waray",
|
| 959 |
+
"bleu":66.3850231243,
|
| 960 |
+
"speakers":3100000.0
|
| 961 |
+
},
|
| 962 |
+
{
|
| 963 |
+
"target_language_name":"Welsh",
|
| 964 |
+
"bleu":83.3437724474,
|
| 965 |
+
"speakers":977366.0
|
| 966 |
+
},
|
| 967 |
+
{
|
| 968 |
+
"target_language_name":"Wolof",
|
| 969 |
+
"bleu":42.6430127569,
|
| 970 |
+
"speakers":3700000.0
|
| 971 |
+
},
|
| 972 |
+
{
|
| 973 |
+
"target_language_name":"Xhosa",
|
| 974 |
+
"bleu":55.4688091009,
|
| 975 |
+
"speakers":11000000.0
|
| 976 |
+
},
|
| 977 |
+
{
|
| 978 |
+
"target_language_name":"Yoruba",
|
| 979 |
+
"bleu":34.2642542268,
|
| 980 |
+
"speakers":40000000.0
|
| 981 |
+
},
|
| 982 |
+
{
|
| 983 |
+
"target_language_name":"Zulu",
|
| 984 |
+
"bleu":59.1762078389,
|
| 985 |
+
"speakers":15700000.0
|
| 986 |
+
},
|
| 987 |
+
{
|
| 988 |
+
"target_language_name":"nno",
|
| 989 |
+
"bleu":71.8615646296,
|
| 990 |
+
"speakers":0.0
|
| 991 |
+
},
|
| 992 |
+
{
|
| 993 |
+
"target_language_name":"\u00c9w\u00e9",
|
| 994 |
+
"bleu":41.6614038791,
|
| 995 |
+
"speakers":3000000.0
|
| 996 |
}
|
| 997 |
]
|