Spaces:
Running
Running
Upload from nightly evaluation run
Browse files- languages.json +5 -5
- models.json +11 -0
- results.json +840 -0
languages.json
CHANGED
|
@@ -79,7 +79,7 @@
|
|
| 79 |
"family":"Indo-European",
|
| 80 |
"flores_path":"fra_Latn",
|
| 81 |
"fleurs_tag":"fr_fr",
|
| 82 |
-
"commonvoice_hours":
|
| 83 |
"commonvoice_locale":"fr",
|
| 84 |
"in_benchmark":true
|
| 85 |
},
|
|
@@ -163,7 +163,7 @@
|
|
| 163 |
"family":"Indo-European",
|
| 164 |
"flores_path":"deu_Latn",
|
| 165 |
"fleurs_tag":"de_de",
|
| 166 |
-
"commonvoice_hours":
|
| 167 |
"commonvoice_locale":"de",
|
| 168 |
"in_benchmark":true
|
| 169 |
},
|
|
@@ -1375,7 +1375,7 @@
|
|
| 1375 |
"family":"Turkic",
|
| 1376 |
"flores_path":"uig_Arab",
|
| 1377 |
"fleurs_tag":null,
|
| 1378 |
-
"commonvoice_hours":
|
| 1379 |
"commonvoice_locale":"ug",
|
| 1380 |
"in_benchmark":true
|
| 1381 |
},
|
|
@@ -3559,7 +3559,7 @@
|
|
| 3559 |
"family":"Abkhaz-Adyge",
|
| 3560 |
"flores_path":null,
|
| 3561 |
"fleurs_tag":null,
|
| 3562 |
-
"commonvoice_hours":
|
| 3563 |
"commonvoice_locale":"kbd",
|
| 3564 |
"in_benchmark":false
|
| 3565 |
},
|
|
@@ -4651,7 +4651,7 @@
|
|
| 4651 |
"family":"Abkhaz-Adyge",
|
| 4652 |
"flores_path":null,
|
| 4653 |
"fleurs_tag":null,
|
| 4654 |
-
"commonvoice_hours":
|
| 4655 |
"commonvoice_locale":"ady",
|
| 4656 |
"in_benchmark":false
|
| 4657 |
},
|
|
|
|
| 79 |
"family":"Indo-European",
|
| 80 |
"flores_path":"fra_Latn",
|
| 81 |
"fleurs_tag":"fr_fr",
|
| 82 |
+
"commonvoice_hours":1062.0,
|
| 83 |
"commonvoice_locale":"fr",
|
| 84 |
"in_benchmark":true
|
| 85 |
},
|
|
|
|
| 163 |
"family":"Indo-European",
|
| 164 |
"flores_path":"deu_Latn",
|
| 165 |
"fleurs_tag":"de_de",
|
| 166 |
+
"commonvoice_hours":1367.0,
|
| 167 |
"commonvoice_locale":"de",
|
| 168 |
"in_benchmark":true
|
| 169 |
},
|
|
|
|
| 1375 |
"family":"Turkic",
|
| 1376 |
"flores_path":"uig_Arab",
|
| 1377 |
"fleurs_tag":null,
|
| 1378 |
+
"commonvoice_hours":377.0,
|
| 1379 |
"commonvoice_locale":"ug",
|
| 1380 |
"in_benchmark":true
|
| 1381 |
},
|
|
|
|
| 3559 |
"family":"Abkhaz-Adyge",
|
| 3560 |
"flores_path":null,
|
| 3561 |
"fleurs_tag":null,
|
| 3562 |
+
"commonvoice_hours":67.0,
|
| 3563 |
"commonvoice_locale":"kbd",
|
| 3564 |
"in_benchmark":false
|
| 3565 |
},
|
|
|
|
| 4651 |
"family":"Abkhaz-Adyge",
|
| 4652 |
"flores_path":null,
|
| 4653 |
"fleurs_tag":null,
|
| 4654 |
+
"commonvoice_hours":22.0,
|
| 4655 |
"commonvoice_locale":"ady",
|
| 4656 |
"in_benchmark":false
|
| 4657 |
},
|
models.json
CHANGED
|
@@ -43,6 +43,17 @@
|
|
| 43 |
"license":"Mit",
|
| 44 |
"creation_date":1737331200000
|
| 45 |
},
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 46 |
{
|
| 47 |
"id":"google\/gemini-2.0-flash-001",
|
| 48 |
"name":"Gemini 2.0 Flash",
|
|
|
|
| 43 |
"license":"Mit",
|
| 44 |
"creation_date":1737331200000
|
| 45 |
},
|
| 46 |
+
{
|
| 47 |
+
"id":"deepseek\/deepseek-r1-0528",
|
| 48 |
+
"name":"R1 0528",
|
| 49 |
+
"provider_name":"DeepSeek",
|
| 50 |
+
"cost":0.0,
|
| 51 |
+
"hf_id":"deepseek-ai\/DeepSeek-R1-0528",
|
| 52 |
+
"size":684531386000.0,
|
| 53 |
+
"type":"Open",
|
| 54 |
+
"license":"Mit",
|
| 55 |
+
"creation_date":1748390400000
|
| 56 |
+
},
|
| 57 |
{
|
| 58 |
"id":"google\/gemini-2.0-flash-001",
|
| 59 |
"name":"Gemini 2.0 Flash",
|
results.json
CHANGED
|
@@ -3359,6 +3359,846 @@
|
|
| 3359 |
"metric":"chrf",
|
| 3360 |
"score":0.3710290799
|
| 3361 |
},
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 3362 |
{
|
| 3363 |
"model":"google\/gemini-2.0-flash-001",
|
| 3364 |
"bcp_47":"ar",
|
|
|
|
| 3359 |
"metric":"chrf",
|
| 3360 |
"score":0.3710290799
|
| 3361 |
},
|
| 3362 |
+
{
|
| 3363 |
+
"model":"deepseek\/deepseek-r1-0528",
|
| 3364 |
+
"bcp_47":"ar",
|
| 3365 |
+
"task":"classification",
|
| 3366 |
+
"metric":"accuracy",
|
| 3367 |
+
"score":0.0
|
| 3368 |
+
},
|
| 3369 |
+
{
|
| 3370 |
+
"model":"deepseek\/deepseek-r1-0528",
|
| 3371 |
+
"bcp_47":"ar",
|
| 3372 |
+
"task":"mmlu",
|
| 3373 |
+
"metric":"accuracy",
|
| 3374 |
+
"score":0.0
|
| 3375 |
+
},
|
| 3376 |
+
{
|
| 3377 |
+
"model":"deepseek\/deepseek-r1-0528",
|
| 3378 |
+
"bcp_47":"ar",
|
| 3379 |
+
"task":"translation_from",
|
| 3380 |
+
"metric":"bleu",
|
| 3381 |
+
"score":0.2373672543
|
| 3382 |
+
},
|
| 3383 |
+
{
|
| 3384 |
+
"model":"deepseek\/deepseek-r1-0528",
|
| 3385 |
+
"bcp_47":"ar",
|
| 3386 |
+
"task":"translation_from",
|
| 3387 |
+
"metric":"chrf",
|
| 3388 |
+
"score":0.5260757727
|
| 3389 |
+
},
|
| 3390 |
+
{
|
| 3391 |
+
"model":"deepseek\/deepseek-r1-0528",
|
| 3392 |
+
"bcp_47":"ar",
|
| 3393 |
+
"task":"translation_to",
|
| 3394 |
+
"metric":"bleu",
|
| 3395 |
+
"score":0.3285274303
|
| 3396 |
+
},
|
| 3397 |
+
{
|
| 3398 |
+
"model":"deepseek\/deepseek-r1-0528",
|
| 3399 |
+
"bcp_47":"ar",
|
| 3400 |
+
"task":"translation_to",
|
| 3401 |
+
"metric":"chrf",
|
| 3402 |
+
"score":0.5590237808
|
| 3403 |
+
},
|
| 3404 |
+
{
|
| 3405 |
+
"model":"deepseek\/deepseek-r1-0528",
|
| 3406 |
+
"bcp_47":"bn",
|
| 3407 |
+
"task":"classification",
|
| 3408 |
+
"metric":"accuracy",
|
| 3409 |
+
"score":0.0
|
| 3410 |
+
},
|
| 3411 |
+
{
|
| 3412 |
+
"model":"deepseek\/deepseek-r1-0528",
|
| 3413 |
+
"bcp_47":"bn",
|
| 3414 |
+
"task":"mgsm",
|
| 3415 |
+
"metric":"accuracy",
|
| 3416 |
+
"score":0.4
|
| 3417 |
+
},
|
| 3418 |
+
{
|
| 3419 |
+
"model":"deepseek\/deepseek-r1-0528",
|
| 3420 |
+
"bcp_47":"bn",
|
| 3421 |
+
"task":"mmlu",
|
| 3422 |
+
"metric":"accuracy",
|
| 3423 |
+
"score":0.0
|
| 3424 |
+
},
|
| 3425 |
+
{
|
| 3426 |
+
"model":"deepseek\/deepseek-r1-0528",
|
| 3427 |
+
"bcp_47":"bn",
|
| 3428 |
+
"task":"translation_from",
|
| 3429 |
+
"metric":"bleu",
|
| 3430 |
+
"score":0.251982914
|
| 3431 |
+
},
|
| 3432 |
+
{
|
| 3433 |
+
"model":"deepseek\/deepseek-r1-0528",
|
| 3434 |
+
"bcp_47":"bn",
|
| 3435 |
+
"task":"translation_from",
|
| 3436 |
+
"metric":"chrf",
|
| 3437 |
+
"score":0.5269588388
|
| 3438 |
+
},
|
| 3439 |
+
{
|
| 3440 |
+
"model":"deepseek\/deepseek-r1-0528",
|
| 3441 |
+
"bcp_47":"bn",
|
| 3442 |
+
"task":"translation_to",
|
| 3443 |
+
"metric":"bleu",
|
| 3444 |
+
"score":0.3081294684
|
| 3445 |
+
},
|
| 3446 |
+
{
|
| 3447 |
+
"model":"deepseek\/deepseek-r1-0528",
|
| 3448 |
+
"bcp_47":"bn",
|
| 3449 |
+
"task":"translation_to",
|
| 3450 |
+
"metric":"chrf",
|
| 3451 |
+
"score":0.5221618044
|
| 3452 |
+
},
|
| 3453 |
+
{
|
| 3454 |
+
"model":"deepseek\/deepseek-r1-0528",
|
| 3455 |
+
"bcp_47":"de",
|
| 3456 |
+
"task":"classification",
|
| 3457 |
+
"metric":"accuracy",
|
| 3458 |
+
"score":0.0
|
| 3459 |
+
},
|
| 3460 |
+
{
|
| 3461 |
+
"model":"deepseek\/deepseek-r1-0528",
|
| 3462 |
+
"bcp_47":"de",
|
| 3463 |
+
"task":"mgsm",
|
| 3464 |
+
"metric":"accuracy",
|
| 3465 |
+
"score":0.4
|
| 3466 |
+
},
|
| 3467 |
+
{
|
| 3468 |
+
"model":"deepseek\/deepseek-r1-0528",
|
| 3469 |
+
"bcp_47":"de",
|
| 3470 |
+
"task":"mmlu",
|
| 3471 |
+
"metric":"accuracy",
|
| 3472 |
+
"score":0.0
|
| 3473 |
+
},
|
| 3474 |
+
{
|
| 3475 |
+
"model":"deepseek\/deepseek-r1-0528",
|
| 3476 |
+
"bcp_47":"de",
|
| 3477 |
+
"task":"translation_from",
|
| 3478 |
+
"metric":"bleu",
|
| 3479 |
+
"score":0.3226520344
|
| 3480 |
+
},
|
| 3481 |
+
{
|
| 3482 |
+
"model":"deepseek\/deepseek-r1-0528",
|
| 3483 |
+
"bcp_47":"de",
|
| 3484 |
+
"task":"translation_from",
|
| 3485 |
+
"metric":"chrf",
|
| 3486 |
+
"score":0.5750653902
|
| 3487 |
+
},
|
| 3488 |
+
{
|
| 3489 |
+
"model":"deepseek\/deepseek-r1-0528",
|
| 3490 |
+
"bcp_47":"de",
|
| 3491 |
+
"task":"translation_to",
|
| 3492 |
+
"metric":"bleu",
|
| 3493 |
+
"score":0.3833943767
|
| 3494 |
+
},
|
| 3495 |
+
{
|
| 3496 |
+
"model":"deepseek\/deepseek-r1-0528",
|
| 3497 |
+
"bcp_47":"de",
|
| 3498 |
+
"task":"translation_to",
|
| 3499 |
+
"metric":"chrf",
|
| 3500 |
+
"score":0.5822540388
|
| 3501 |
+
},
|
| 3502 |
+
{
|
| 3503 |
+
"model":"deepseek\/deepseek-r1-0528",
|
| 3504 |
+
"bcp_47":"en",
|
| 3505 |
+
"task":"classification",
|
| 3506 |
+
"metric":"accuracy",
|
| 3507 |
+
"score":0.0
|
| 3508 |
+
},
|
| 3509 |
+
{
|
| 3510 |
+
"model":"deepseek\/deepseek-r1-0528",
|
| 3511 |
+
"bcp_47":"en",
|
| 3512 |
+
"task":"mgsm",
|
| 3513 |
+
"metric":"accuracy",
|
| 3514 |
+
"score":0.6
|
| 3515 |
+
},
|
| 3516 |
+
{
|
| 3517 |
+
"model":"deepseek\/deepseek-r1-0528",
|
| 3518 |
+
"bcp_47":"en",
|
| 3519 |
+
"task":"mmlu",
|
| 3520 |
+
"metric":"accuracy",
|
| 3521 |
+
"score":0.0
|
| 3522 |
+
},
|
| 3523 |
+
{
|
| 3524 |
+
"model":"deepseek\/deepseek-r1-0528",
|
| 3525 |
+
"bcp_47":"en",
|
| 3526 |
+
"task":"translation_from",
|
| 3527 |
+
"metric":"bleu",
|
| 3528 |
+
"score":0.5414890567
|
| 3529 |
+
},
|
| 3530 |
+
{
|
| 3531 |
+
"model":"deepseek\/deepseek-r1-0528",
|
| 3532 |
+
"bcp_47":"en",
|
| 3533 |
+
"task":"translation_from",
|
| 3534 |
+
"metric":"chrf",
|
| 3535 |
+
"score":0.6901603131
|
| 3536 |
+
},
|
| 3537 |
+
{
|
| 3538 |
+
"model":"deepseek\/deepseek-r1-0528",
|
| 3539 |
+
"bcp_47":"en",
|
| 3540 |
+
"task":"translation_to",
|
| 3541 |
+
"metric":"bleu",
|
| 3542 |
+
"score":0.65136344
|
| 3543 |
+
},
|
| 3544 |
+
{
|
| 3545 |
+
"model":"deepseek\/deepseek-r1-0528",
|
| 3546 |
+
"bcp_47":"en",
|
| 3547 |
+
"task":"translation_to",
|
| 3548 |
+
"metric":"chrf",
|
| 3549 |
+
"score":0.814288256
|
| 3550 |
+
},
|
| 3551 |
+
{
|
| 3552 |
+
"model":"deepseek\/deepseek-r1-0528",
|
| 3553 |
+
"bcp_47":"es",
|
| 3554 |
+
"task":"classification",
|
| 3555 |
+
"metric":"accuracy",
|
| 3556 |
+
"score":0.0
|
| 3557 |
+
},
|
| 3558 |
+
{
|
| 3559 |
+
"model":"deepseek\/deepseek-r1-0528",
|
| 3560 |
+
"bcp_47":"es",
|
| 3561 |
+
"task":"mgsm",
|
| 3562 |
+
"metric":"accuracy",
|
| 3563 |
+
"score":0.3
|
| 3564 |
+
},
|
| 3565 |
+
{
|
| 3566 |
+
"model":"deepseek\/deepseek-r1-0528",
|
| 3567 |
+
"bcp_47":"es",
|
| 3568 |
+
"task":"mmlu",
|
| 3569 |
+
"metric":"accuracy",
|
| 3570 |
+
"score":0.0
|
| 3571 |
+
},
|
| 3572 |
+
{
|
| 3573 |
+
"model":"deepseek\/deepseek-r1-0528",
|
| 3574 |
+
"bcp_47":"es",
|
| 3575 |
+
"task":"translation_from",
|
| 3576 |
+
"metric":"bleu",
|
| 3577 |
+
"score":0.2479212607
|
| 3578 |
+
},
|
| 3579 |
+
{
|
| 3580 |
+
"model":"deepseek\/deepseek-r1-0528",
|
| 3581 |
+
"bcp_47":"es",
|
| 3582 |
+
"task":"translation_from",
|
| 3583 |
+
"metric":"chrf",
|
| 3584 |
+
"score":0.4998884286
|
| 3585 |
+
},
|
| 3586 |
+
{
|
| 3587 |
+
"model":"deepseek\/deepseek-r1-0528",
|
| 3588 |
+
"bcp_47":"es",
|
| 3589 |
+
"task":"translation_to",
|
| 3590 |
+
"metric":"bleu",
|
| 3591 |
+
"score":0.2970650759
|
| 3592 |
+
},
|
| 3593 |
+
{
|
| 3594 |
+
"model":"deepseek\/deepseek-r1-0528",
|
| 3595 |
+
"bcp_47":"es",
|
| 3596 |
+
"task":"translation_to",
|
| 3597 |
+
"metric":"chrf",
|
| 3598 |
+
"score":0.5373052889
|
| 3599 |
+
},
|
| 3600 |
+
{
|
| 3601 |
+
"model":"deepseek\/deepseek-r1-0528",
|
| 3602 |
+
"bcp_47":"fr",
|
| 3603 |
+
"task":"classification",
|
| 3604 |
+
"metric":"accuracy",
|
| 3605 |
+
"score":0.0
|
| 3606 |
+
},
|
| 3607 |
+
{
|
| 3608 |
+
"model":"deepseek\/deepseek-r1-0528",
|
| 3609 |
+
"bcp_47":"fr",
|
| 3610 |
+
"task":"mgsm",
|
| 3611 |
+
"metric":"accuracy",
|
| 3612 |
+
"score":0.5
|
| 3613 |
+
},
|
| 3614 |
+
{
|
| 3615 |
+
"model":"deepseek\/deepseek-r1-0528",
|
| 3616 |
+
"bcp_47":"fr",
|
| 3617 |
+
"task":"mmlu",
|
| 3618 |
+
"metric":"accuracy",
|
| 3619 |
+
"score":0.0
|
| 3620 |
+
},
|
| 3621 |
+
{
|
| 3622 |
+
"model":"deepseek\/deepseek-r1-0528",
|
| 3623 |
+
"bcp_47":"fr",
|
| 3624 |
+
"task":"translation_from",
|
| 3625 |
+
"metric":"bleu",
|
| 3626 |
+
"score":0.3186845256
|
| 3627 |
+
},
|
| 3628 |
+
{
|
| 3629 |
+
"model":"deepseek\/deepseek-r1-0528",
|
| 3630 |
+
"bcp_47":"fr",
|
| 3631 |
+
"task":"translation_from",
|
| 3632 |
+
"metric":"chrf",
|
| 3633 |
+
"score":0.5933794038
|
| 3634 |
+
},
|
| 3635 |
+
{
|
| 3636 |
+
"model":"deepseek\/deepseek-r1-0528",
|
| 3637 |
+
"bcp_47":"fr",
|
| 3638 |
+
"task":"translation_to",
|
| 3639 |
+
"metric":"bleu",
|
| 3640 |
+
"score":0.4349494723
|
| 3641 |
+
},
|
| 3642 |
+
{
|
| 3643 |
+
"model":"deepseek\/deepseek-r1-0528",
|
| 3644 |
+
"bcp_47":"fr",
|
| 3645 |
+
"task":"translation_to",
|
| 3646 |
+
"metric":"chrf",
|
| 3647 |
+
"score":0.6079740627
|
| 3648 |
+
},
|
| 3649 |
+
{
|
| 3650 |
+
"model":"deepseek\/deepseek-r1-0528",
|
| 3651 |
+
"bcp_47":"hi",
|
| 3652 |
+
"task":"classification",
|
| 3653 |
+
"metric":"accuracy",
|
| 3654 |
+
"score":0.0
|
| 3655 |
+
},
|
| 3656 |
+
{
|
| 3657 |
+
"model":"deepseek\/deepseek-r1-0528",
|
| 3658 |
+
"bcp_47":"hi",
|
| 3659 |
+
"task":"mmlu",
|
| 3660 |
+
"metric":"accuracy",
|
| 3661 |
+
"score":0.0
|
| 3662 |
+
},
|
| 3663 |
+
{
|
| 3664 |
+
"model":"deepseek\/deepseek-r1-0528",
|
| 3665 |
+
"bcp_47":"hi",
|
| 3666 |
+
"task":"translation_from",
|
| 3667 |
+
"metric":"bleu",
|
| 3668 |
+
"score":0.3564149867
|
| 3669 |
+
},
|
| 3670 |
+
{
|
| 3671 |
+
"model":"deepseek\/deepseek-r1-0528",
|
| 3672 |
+
"bcp_47":"hi",
|
| 3673 |
+
"task":"translation_from",
|
| 3674 |
+
"metric":"chrf",
|
| 3675 |
+
"score":0.5972656918
|
| 3676 |
+
},
|
| 3677 |
+
{
|
| 3678 |
+
"model":"deepseek\/deepseek-r1-0528",
|
| 3679 |
+
"bcp_47":"hi",
|
| 3680 |
+
"task":"translation_to",
|
| 3681 |
+
"metric":"bleu",
|
| 3682 |
+
"score":0.3029237977
|
| 3683 |
+
},
|
| 3684 |
+
{
|
| 3685 |
+
"model":"deepseek\/deepseek-r1-0528",
|
| 3686 |
+
"bcp_47":"hi",
|
| 3687 |
+
"task":"translation_to",
|
| 3688 |
+
"metric":"chrf",
|
| 3689 |
+
"score":0.5276781303
|
| 3690 |
+
},
|
| 3691 |
+
{
|
| 3692 |
+
"model":"deepseek\/deepseek-r1-0528",
|
| 3693 |
+
"bcp_47":"id",
|
| 3694 |
+
"task":"classification",
|
| 3695 |
+
"metric":"accuracy",
|
| 3696 |
+
"score":0.0
|
| 3697 |
+
},
|
| 3698 |
+
{
|
| 3699 |
+
"model":"deepseek\/deepseek-r1-0528",
|
| 3700 |
+
"bcp_47":"id",
|
| 3701 |
+
"task":"mmlu",
|
| 3702 |
+
"metric":"accuracy",
|
| 3703 |
+
"score":0.0
|
| 3704 |
+
},
|
| 3705 |
+
{
|
| 3706 |
+
"model":"deepseek\/deepseek-r1-0528",
|
| 3707 |
+
"bcp_47":"id",
|
| 3708 |
+
"task":"translation_from",
|
| 3709 |
+
"metric":"bleu",
|
| 3710 |
+
"score":0.2876911945
|
| 3711 |
+
},
|
| 3712 |
+
{
|
| 3713 |
+
"model":"deepseek\/deepseek-r1-0528",
|
| 3714 |
+
"bcp_47":"id",
|
| 3715 |
+
"task":"translation_from",
|
| 3716 |
+
"metric":"chrf",
|
| 3717 |
+
"score":0.5482159609
|
| 3718 |
+
},
|
| 3719 |
+
{
|
| 3720 |
+
"model":"deepseek\/deepseek-r1-0528",
|
| 3721 |
+
"bcp_47":"id",
|
| 3722 |
+
"task":"translation_to",
|
| 3723 |
+
"metric":"bleu",
|
| 3724 |
+
"score":0.2940448188
|
| 3725 |
+
},
|
| 3726 |
+
{
|
| 3727 |
+
"model":"deepseek\/deepseek-r1-0528",
|
| 3728 |
+
"bcp_47":"id",
|
| 3729 |
+
"task":"translation_to",
|
| 3730 |
+
"metric":"chrf",
|
| 3731 |
+
"score":0.5448923741
|
| 3732 |
+
},
|
| 3733 |
+
{
|
| 3734 |
+
"model":"deepseek\/deepseek-r1-0528",
|
| 3735 |
+
"bcp_47":"ja",
|
| 3736 |
+
"task":"classification",
|
| 3737 |
+
"metric":"accuracy",
|
| 3738 |
+
"score":0.0
|
| 3739 |
+
},
|
| 3740 |
+
{
|
| 3741 |
+
"model":"deepseek\/deepseek-r1-0528",
|
| 3742 |
+
"bcp_47":"ja",
|
| 3743 |
+
"task":"mgsm",
|
| 3744 |
+
"metric":"accuracy",
|
| 3745 |
+
"score":0.4
|
| 3746 |
+
},
|
| 3747 |
+
{
|
| 3748 |
+
"model":"deepseek\/deepseek-r1-0528",
|
| 3749 |
+
"bcp_47":"ja",
|
| 3750 |
+
"task":"mmlu",
|
| 3751 |
+
"metric":"accuracy",
|
| 3752 |
+
"score":0.0
|
| 3753 |
+
},
|
| 3754 |
+
{
|
| 3755 |
+
"model":"deepseek\/deepseek-r1-0528",
|
| 3756 |
+
"bcp_47":"ja",
|
| 3757 |
+
"task":"translation_from",
|
| 3758 |
+
"metric":"bleu",
|
| 3759 |
+
"score":0.1827387853
|
| 3760 |
+
},
|
| 3761 |
+
{
|
| 3762 |
+
"model":"deepseek\/deepseek-r1-0528",
|
| 3763 |
+
"bcp_47":"ja",
|
| 3764 |
+
"task":"translation_from",
|
| 3765 |
+
"metric":"chrf",
|
| 3766 |
+
"score":0.4769620326
|
| 3767 |
+
},
|
| 3768 |
+
{
|
| 3769 |
+
"model":"deepseek\/deepseek-r1-0528",
|
| 3770 |
+
"bcp_47":"ja",
|
| 3771 |
+
"task":"translation_to",
|
| 3772 |
+
"metric":"bleu",
|
| 3773 |
+
"score":0.0613359658
|
| 3774 |
+
},
|
| 3775 |
+
{
|
| 3776 |
+
"model":"deepseek\/deepseek-r1-0528",
|
| 3777 |
+
"bcp_47":"ja",
|
| 3778 |
+
"task":"translation_to",
|
| 3779 |
+
"metric":"chrf",
|
| 3780 |
+
"score":0.2105103816
|
| 3781 |
+
},
|
| 3782 |
+
{
|
| 3783 |
+
"model":"deepseek\/deepseek-r1-0528",
|
| 3784 |
+
"bcp_47":"jv",
|
| 3785 |
+
"task":"classification",
|
| 3786 |
+
"metric":"accuracy",
|
| 3787 |
+
"score":0.0
|
| 3788 |
+
},
|
| 3789 |
+
{
|
| 3790 |
+
"model":"deepseek\/deepseek-r1-0528",
|
| 3791 |
+
"bcp_47":"jv",
|
| 3792 |
+
"task":"translation_from",
|
| 3793 |
+
"metric":"bleu",
|
| 3794 |
+
"score":0.2802837747
|
| 3795 |
+
},
|
| 3796 |
+
{
|
| 3797 |
+
"model":"deepseek\/deepseek-r1-0528",
|
| 3798 |
+
"bcp_47":"jv",
|
| 3799 |
+
"task":"translation_from",
|
| 3800 |
+
"metric":"chrf",
|
| 3801 |
+
"score":0.4893845985
|
| 3802 |
+
},
|
| 3803 |
+
{
|
| 3804 |
+
"model":"deepseek\/deepseek-r1-0528",
|
| 3805 |
+
"bcp_47":"jv",
|
| 3806 |
+
"task":"translation_to",
|
| 3807 |
+
"metric":"bleu",
|
| 3808 |
+
"score":0.1179961209
|
| 3809 |
+
},
|
| 3810 |
+
{
|
| 3811 |
+
"model":"deepseek\/deepseek-r1-0528",
|
| 3812 |
+
"bcp_47":"jv",
|
| 3813 |
+
"task":"translation_to",
|
| 3814 |
+
"metric":"chrf",
|
| 3815 |
+
"score":0.3697436656
|
| 3816 |
+
},
|
| 3817 |
+
{
|
| 3818 |
+
"model":"deepseek\/deepseek-r1-0528",
|
| 3819 |
+
"bcp_47":"mr",
|
| 3820 |
+
"task":"classification",
|
| 3821 |
+
"metric":"accuracy",
|
| 3822 |
+
"score":0.0
|
| 3823 |
+
},
|
| 3824 |
+
{
|
| 3825 |
+
"model":"deepseek\/deepseek-r1-0528",
|
| 3826 |
+
"bcp_47":"mr",
|
| 3827 |
+
"task":"translation_from",
|
| 3828 |
+
"metric":"bleu",
|
| 3829 |
+
"score":0.1520275352
|
| 3830 |
+
},
|
| 3831 |
+
{
|
| 3832 |
+
"model":"deepseek\/deepseek-r1-0528",
|
| 3833 |
+
"bcp_47":"mr",
|
| 3834 |
+
"task":"translation_from",
|
| 3835 |
+
"metric":"chrf",
|
| 3836 |
+
"score":0.3905524229
|
| 3837 |
+
},
|
| 3838 |
+
{
|
| 3839 |
+
"model":"deepseek\/deepseek-r1-0528",
|
| 3840 |
+
"bcp_47":"mr",
|
| 3841 |
+
"task":"translation_to",
|
| 3842 |
+
"metric":"bleu",
|
| 3843 |
+
"score":0.0999041852
|
| 3844 |
+
},
|
| 3845 |
+
{
|
| 3846 |
+
"model":"deepseek\/deepseek-r1-0528",
|
| 3847 |
+
"bcp_47":"mr",
|
| 3848 |
+
"task":"translation_to",
|
| 3849 |
+
"metric":"chrf",
|
| 3850 |
+
"score":0.3246573528
|
| 3851 |
+
},
|
| 3852 |
+
{
|
| 3853 |
+
"model":"deepseek\/deepseek-r1-0528",
|
| 3854 |
+
"bcp_47":"pa",
|
| 3855 |
+
"task":"classification",
|
| 3856 |
+
"metric":"accuracy",
|
| 3857 |
+
"score":0.0
|
| 3858 |
+
},
|
| 3859 |
+
{
|
| 3860 |
+
"model":"deepseek\/deepseek-r1-0528",
|
| 3861 |
+
"bcp_47":"pa",
|
| 3862 |
+
"task":"translation_from",
|
| 3863 |
+
"metric":"bleu",
|
| 3864 |
+
"score":0.361635926
|
| 3865 |
+
},
|
| 3866 |
+
{
|
| 3867 |
+
"model":"deepseek\/deepseek-r1-0528",
|
| 3868 |
+
"bcp_47":"pa",
|
| 3869 |
+
"task":"translation_from",
|
| 3870 |
+
"metric":"chrf",
|
| 3871 |
+
"score":0.5409988692
|
| 3872 |
+
},
|
| 3873 |
+
{
|
| 3874 |
+
"model":"deepseek\/deepseek-r1-0528",
|
| 3875 |
+
"bcp_47":"pa",
|
| 3876 |
+
"task":"translation_to",
|
| 3877 |
+
"metric":"bleu",
|
| 3878 |
+
"score":0.3917357782
|
| 3879 |
+
},
|
| 3880 |
+
{
|
| 3881 |
+
"model":"deepseek\/deepseek-r1-0528",
|
| 3882 |
+
"bcp_47":"pa",
|
| 3883 |
+
"task":"translation_to",
|
| 3884 |
+
"metric":"chrf",
|
| 3885 |
+
"score":0.5329271965
|
| 3886 |
+
},
|
| 3887 |
+
{
|
| 3888 |
+
"model":"deepseek\/deepseek-r1-0528",
|
| 3889 |
+
"bcp_47":"pt",
|
| 3890 |
+
"task":"classification",
|
| 3891 |
+
"metric":"accuracy",
|
| 3892 |
+
"score":0.0
|
| 3893 |
+
},
|
| 3894 |
+
{
|
| 3895 |
+
"model":"deepseek\/deepseek-r1-0528",
|
| 3896 |
+
"bcp_47":"pt",
|
| 3897 |
+
"task":"mmlu",
|
| 3898 |
+
"metric":"accuracy",
|
| 3899 |
+
"score":0.0
|
| 3900 |
+
},
|
| 3901 |
+
{
|
| 3902 |
+
"model":"deepseek\/deepseek-r1-0528",
|
| 3903 |
+
"bcp_47":"pt",
|
| 3904 |
+
"task":"translation_from",
|
| 3905 |
+
"metric":"bleu",
|
| 3906 |
+
"score":0.3390879053
|
| 3907 |
+
},
|
| 3908 |
+
{
|
| 3909 |
+
"model":"deepseek\/deepseek-r1-0528",
|
| 3910 |
+
"bcp_47":"pt",
|
| 3911 |
+
"task":"translation_from",
|
| 3912 |
+
"metric":"chrf",
|
| 3913 |
+
"score":0.5804013742
|
| 3914 |
+
},
|
| 3915 |
+
{
|
| 3916 |
+
"model":"deepseek\/deepseek-r1-0528",
|
| 3917 |
+
"bcp_47":"pt",
|
| 3918 |
+
"task":"translation_to",
|
| 3919 |
+
"metric":"bleu",
|
| 3920 |
+
"score":0.3506563803
|
| 3921 |
+
},
|
| 3922 |
+
{
|
| 3923 |
+
"model":"deepseek\/deepseek-r1-0528",
|
| 3924 |
+
"bcp_47":"pt",
|
| 3925 |
+
"task":"translation_to",
|
| 3926 |
+
"metric":"chrf",
|
| 3927 |
+
"score":0.5763378703
|
| 3928 |
+
},
|
| 3929 |
+
{
|
| 3930 |
+
"model":"deepseek\/deepseek-r1-0528",
|
| 3931 |
+
"bcp_47":"ru",
|
| 3932 |
+
"task":"classification",
|
| 3933 |
+
"metric":"accuracy",
|
| 3934 |
+
"score":0.0
|
| 3935 |
+
},
|
| 3936 |
+
{
|
| 3937 |
+
"model":"deepseek\/deepseek-r1-0528",
|
| 3938 |
+
"bcp_47":"ru",
|
| 3939 |
+
"task":"mgsm",
|
| 3940 |
+
"metric":"accuracy",
|
| 3941 |
+
"score":0.6
|
| 3942 |
+
},
|
| 3943 |
+
{
|
| 3944 |
+
"model":"deepseek\/deepseek-r1-0528",
|
| 3945 |
+
"bcp_47":"ru",
|
| 3946 |
+
"task":"mmlu",
|
| 3947 |
+
"metric":"accuracy",
|
| 3948 |
+
"score":0.0
|
| 3949 |
+
},
|
| 3950 |
+
{
|
| 3951 |
+
"model":"deepseek\/deepseek-r1-0528",
|
| 3952 |
+
"bcp_47":"ru",
|
| 3953 |
+
"task":"translation_from",
|
| 3954 |
+
"metric":"bleu",
|
| 3955 |
+
"score":0.2246840158
|
| 3956 |
+
},
|
| 3957 |
+
{
|
| 3958 |
+
"model":"deepseek\/deepseek-r1-0528",
|
| 3959 |
+
"bcp_47":"ru",
|
| 3960 |
+
"task":"translation_from",
|
| 3961 |
+
"metric":"chrf",
|
| 3962 |
+
"score":0.5244113055
|
| 3963 |
+
},
|
| 3964 |
+
{
|
| 3965 |
+
"model":"deepseek\/deepseek-r1-0528",
|
| 3966 |
+
"bcp_47":"ru",
|
| 3967 |
+
"task":"translation_to",
|
| 3968 |
+
"metric":"bleu",
|
| 3969 |
+
"score":0.3594079605
|
| 3970 |
+
},
|
| 3971 |
+
{
|
| 3972 |
+
"model":"deepseek\/deepseek-r1-0528",
|
| 3973 |
+
"bcp_47":"ru",
|
| 3974 |
+
"task":"translation_to",
|
| 3975 |
+
"metric":"chrf",
|
| 3976 |
+
"score":0.5726823578
|
| 3977 |
+
},
|
| 3978 |
+
{
|
| 3979 |
+
"model":"deepseek\/deepseek-r1-0528",
|
| 3980 |
+
"bcp_47":"sw",
|
| 3981 |
+
"task":"classification",
|
| 3982 |
+
"metric":"accuracy",
|
| 3983 |
+
"score":0.0
|
| 3984 |
+
},
|
| 3985 |
+
{
|
| 3986 |
+
"model":"deepseek\/deepseek-r1-0528",
|
| 3987 |
+
"bcp_47":"sw",
|
| 3988 |
+
"task":"mgsm",
|
| 3989 |
+
"metric":"accuracy",
|
| 3990 |
+
"score":0.2
|
| 3991 |
+
},
|
| 3992 |
+
{
|
| 3993 |
+
"model":"deepseek\/deepseek-r1-0528",
|
| 3994 |
+
"bcp_47":"sw",
|
| 3995 |
+
"task":"mmlu",
|
| 3996 |
+
"metric":"accuracy",
|
| 3997 |
+
"score":0.0
|
| 3998 |
+
},
|
| 3999 |
+
{
|
| 4000 |
+
"model":"deepseek\/deepseek-r1-0528",
|
| 4001 |
+
"bcp_47":"sw",
|
| 4002 |
+
"task":"translation_from",
|
| 4003 |
+
"metric":"bleu",
|
| 4004 |
+
"score":0.2074916818
|
| 4005 |
+
},
|
| 4006 |
+
{
|
| 4007 |
+
"model":"deepseek\/deepseek-r1-0528",
|
| 4008 |
+
"bcp_47":"sw",
|
| 4009 |
+
"task":"translation_from",
|
| 4010 |
+
"metric":"chrf",
|
| 4011 |
+
"score":0.4529002152
|
| 4012 |
+
},
|
| 4013 |
+
{
|
| 4014 |
+
"model":"deepseek\/deepseek-r1-0528",
|
| 4015 |
+
"bcp_47":"sw",
|
| 4016 |
+
"task":"translation_to",
|
| 4017 |
+
"metric":"bleu",
|
| 4018 |
+
"score":0.3320288719
|
| 4019 |
+
},
|
| 4020 |
+
{
|
| 4021 |
+
"model":"deepseek\/deepseek-r1-0528",
|
| 4022 |
+
"bcp_47":"sw",
|
| 4023 |
+
"task":"translation_to",
|
| 4024 |
+
"metric":"chrf",
|
| 4025 |
+
"score":0.6201778863
|
| 4026 |
+
},
|
| 4027 |
+
{
|
| 4028 |
+
"model":"deepseek\/deepseek-r1-0528",
|
| 4029 |
+
"bcp_47":"te",
|
| 4030 |
+
"task":"classification",
|
| 4031 |
+
"metric":"accuracy",
|
| 4032 |
+
"score":0.0
|
| 4033 |
+
},
|
| 4034 |
+
{
|
| 4035 |
+
"model":"deepseek\/deepseek-r1-0528",
|
| 4036 |
+
"bcp_47":"te",
|
| 4037 |
+
"task":"mgsm",
|
| 4038 |
+
"metric":"accuracy",
|
| 4039 |
+
"score":0.3
|
| 4040 |
+
},
|
| 4041 |
+
{
|
| 4042 |
+
"model":"deepseek\/deepseek-r1-0528",
|
| 4043 |
+
"bcp_47":"te",
|
| 4044 |
+
"task":"mmlu",
|
| 4045 |
+
"metric":"accuracy",
|
| 4046 |
+
"score":0.0
|
| 4047 |
+
},
|
| 4048 |
+
{
|
| 4049 |
+
"model":"deepseek\/deepseek-r1-0528",
|
| 4050 |
+
"bcp_47":"te",
|
| 4051 |
+
"task":"translation_from",
|
| 4052 |
+
"metric":"bleu",
|
| 4053 |
+
"score":0.3219720359
|
| 4054 |
+
},
|
| 4055 |
+
{
|
| 4056 |
+
"model":"deepseek\/deepseek-r1-0528",
|
| 4057 |
+
"bcp_47":"te",
|
| 4058 |
+
"task":"translation_from",
|
| 4059 |
+
"metric":"chrf",
|
| 4060 |
+
"score":0.5542555367
|
| 4061 |
+
},
|
| 4062 |
+
{
|
| 4063 |
+
"model":"deepseek\/deepseek-r1-0528",
|
| 4064 |
+
"bcp_47":"te",
|
| 4065 |
+
"task":"translation_to",
|
| 4066 |
+
"metric":"bleu",
|
| 4067 |
+
"score":0.2813682269
|
| 4068 |
+
},
|
| 4069 |
+
{
|
| 4070 |
+
"model":"deepseek\/deepseek-r1-0528",
|
| 4071 |
+
"bcp_47":"te",
|
| 4072 |
+
"task":"translation_to",
|
| 4073 |
+
"metric":"chrf",
|
| 4074 |
+
"score":0.5156714123
|
| 4075 |
+
},
|
| 4076 |
+
{
|
| 4077 |
+
"model":"deepseek\/deepseek-r1-0528",
|
| 4078 |
+
"bcp_47":"ur",
|
| 4079 |
+
"task":"classification",
|
| 4080 |
+
"metric":"accuracy",
|
| 4081 |
+
"score":0.0
|
| 4082 |
+
},
|
| 4083 |
+
{
|
| 4084 |
+
"model":"deepseek\/deepseek-r1-0528",
|
| 4085 |
+
"bcp_47":"ur",
|
| 4086 |
+
"task":"translation_from",
|
| 4087 |
+
"metric":"bleu",
|
| 4088 |
+
"score":0.2049672714
|
| 4089 |
+
},
|
| 4090 |
+
{
|
| 4091 |
+
"model":"deepseek\/deepseek-r1-0528",
|
| 4092 |
+
"bcp_47":"ur",
|
| 4093 |
+
"task":"translation_from",
|
| 4094 |
+
"metric":"chrf",
|
| 4095 |
+
"score":0.4409541903
|
| 4096 |
+
},
|
| 4097 |
+
{
|
| 4098 |
+
"model":"deepseek\/deepseek-r1-0528",
|
| 4099 |
+
"bcp_47":"ur",
|
| 4100 |
+
"task":"translation_to",
|
| 4101 |
+
"metric":"bleu",
|
| 4102 |
+
"score":0.291136983
|
| 4103 |
+
},
|
| 4104 |
+
{
|
| 4105 |
+
"model":"deepseek\/deepseek-r1-0528",
|
| 4106 |
+
"bcp_47":"ur",
|
| 4107 |
+
"task":"translation_to",
|
| 4108 |
+
"metric":"chrf",
|
| 4109 |
+
"score":0.4722890493
|
| 4110 |
+
},
|
| 4111 |
+
{
|
| 4112 |
+
"model":"deepseek\/deepseek-r1-0528",
|
| 4113 |
+
"bcp_47":"vi",
|
| 4114 |
+
"task":"classification",
|
| 4115 |
+
"metric":"accuracy",
|
| 4116 |
+
"score":0.0
|
| 4117 |
+
},
|
| 4118 |
+
{
|
| 4119 |
+
"model":"deepseek\/deepseek-r1-0528",
|
| 4120 |
+
"bcp_47":"vi",
|
| 4121 |
+
"task":"mmlu",
|
| 4122 |
+
"metric":"accuracy",
|
| 4123 |
+
"score":0.0
|
| 4124 |
+
},
|
| 4125 |
+
{
|
| 4126 |
+
"model":"deepseek\/deepseek-r1-0528",
|
| 4127 |
+
"bcp_47":"vi",
|
| 4128 |
+
"task":"translation_from",
|
| 4129 |
+
"metric":"bleu",
|
| 4130 |
+
"score":0.290841669
|
| 4131 |
+
},
|
| 4132 |
+
{
|
| 4133 |
+
"model":"deepseek\/deepseek-r1-0528",
|
| 4134 |
+
"bcp_47":"vi",
|
| 4135 |
+
"task":"translation_from",
|
| 4136 |
+
"metric":"chrf",
|
| 4137 |
+
"score":0.5420316418
|
| 4138 |
+
},
|
| 4139 |
+
{
|
| 4140 |
+
"model":"deepseek\/deepseek-r1-0528",
|
| 4141 |
+
"bcp_47":"vi",
|
| 4142 |
+
"task":"translation_to",
|
| 4143 |
+
"metric":"bleu",
|
| 4144 |
+
"score":0.4456194272
|
| 4145 |
+
},
|
| 4146 |
+
{
|
| 4147 |
+
"model":"deepseek\/deepseek-r1-0528",
|
| 4148 |
+
"bcp_47":"vi",
|
| 4149 |
+
"task":"translation_to",
|
| 4150 |
+
"metric":"chrf",
|
| 4151 |
+
"score":0.6359307779
|
| 4152 |
+
},
|
| 4153 |
+
{
|
| 4154 |
+
"model":"deepseek\/deepseek-r1-0528",
|
| 4155 |
+
"bcp_47":"zh",
|
| 4156 |
+
"task":"classification",
|
| 4157 |
+
"metric":"accuracy",
|
| 4158 |
+
"score":0.0
|
| 4159 |
+
},
|
| 4160 |
+
{
|
| 4161 |
+
"model":"deepseek\/deepseek-r1-0528",
|
| 4162 |
+
"bcp_47":"zh",
|
| 4163 |
+
"task":"mgsm",
|
| 4164 |
+
"metric":"accuracy",
|
| 4165 |
+
"score":0.7
|
| 4166 |
+
},
|
| 4167 |
+
{
|
| 4168 |
+
"model":"deepseek\/deepseek-r1-0528",
|
| 4169 |
+
"bcp_47":"zh",
|
| 4170 |
+
"task":"mmlu",
|
| 4171 |
+
"metric":"accuracy",
|
| 4172 |
+
"score":0.0
|
| 4173 |
+
},
|
| 4174 |
+
{
|
| 4175 |
+
"model":"deepseek\/deepseek-r1-0528",
|
| 4176 |
+
"bcp_47":"zh",
|
| 4177 |
+
"task":"translation_from",
|
| 4178 |
+
"metric":"bleu",
|
| 4179 |
+
"score":0.2199013913
|
| 4180 |
+
},
|
| 4181 |
+
{
|
| 4182 |
+
"model":"deepseek\/deepseek-r1-0528",
|
| 4183 |
+
"bcp_47":"zh",
|
| 4184 |
+
"task":"translation_from",
|
| 4185 |
+
"metric":"chrf",
|
| 4186 |
+
"score":0.4962775874
|
| 4187 |
+
},
|
| 4188 |
+
{
|
| 4189 |
+
"model":"deepseek\/deepseek-r1-0528",
|
| 4190 |
+
"bcp_47":"zh",
|
| 4191 |
+
"task":"translation_to",
|
| 4192 |
+
"metric":"bleu",
|
| 4193 |
+
"score":0.1813558493
|
| 4194 |
+
},
|
| 4195 |
+
{
|
| 4196 |
+
"model":"deepseek\/deepseek-r1-0528",
|
| 4197 |
+
"bcp_47":"zh",
|
| 4198 |
+
"task":"translation_to",
|
| 4199 |
+
"metric":"chrf",
|
| 4200 |
+
"score":0.3079482476
|
| 4201 |
+
},
|
| 4202 |
{
|
| 4203 |
"model":"google\/gemini-2.0-flash-001",
|
| 4204 |
"bcp_47":"ar",
|