Add LLama 4 e Deepseek V3 results

README.md

@@ -56,6 +56,7 @@ models:
   - AI-Sweden-Models/gpt-sw3-40b
   - AI-Sweden-Models/gpt-sw3-6.7b
   - AI-Sweden-Models/gpt-sw3-6.7b-v2
+  - AIDC-AI/Marco-LLM-ES
   - AXCXEPT/EZO-Qwen2.5-32B-Instruct
   - AdaptLLM/finance-LLM
   - AdaptLLM/finance-LLM-13B
@@ -80,6 +81,8 @@ models:
   - BAAI/Infinity-Instruct-7M-0729-Llama3_1-8B
   - BAAI/Infinity-Instruct-7M-Gen-Llama3_1-8B
   - BAAI/OPI-Llama-3.1-8B-Instruct
+  - BSC-LT/salamandra-2b
+  - BSC-LT/salamandra-7b
   - Bruno/Caramelinho
   - Bruno/Caramelo_7B
   - CausalLM/34b-beta
@@ -548,6 +551,7 @@ models:
   - deepseek-ai/DeepSeek-R1-Distill-Qwen-7B
   - deepseek-ai/DeepSeek-V2-Lite
   - deepseek-ai/DeepSeek-V2-Lite-Chat
+  - deepseek-ai/DeepSeek-V3-0324
   - deepseek-ai/deepseek-llm-7b-base
   - deepseek-ai/deepseek-moe-16b-base
   - deepseek-ai/deepseek-moe-16b-chat
@@ -744,6 +748,8 @@ models:
   - meta-llama/Llama-3.2-3B-Instruct
   - meta-llama/Llama-3.2-90B-Vision-Instruct
   - meta-llama/Llama-3.3-70B-Instruct
+  - meta-llama/Llama-4-Maverick-17B-128E-Instruct
+  - meta-llama/Llama-4-Scout-17B-16E-Instruct
   - meta-llama/Meta-Llama-3-70B
   - meta-llama/Meta-Llama-3-70B-Instruct
   - meta-llama/Meta-Llama-3-8B

external_models_results.json

@@ -443,6 +443,29 @@
         "result_metrics_average": 0.8836610214313025,
         "result_metrics_npm": 0.8134610556797854
     },
+    {
+        "model": "deepSeek-v3-0324",
+        "name": "deepseek-ai/DeepSeek-V3-0324 (API)",
+        "link": "https://huggingface.co/deepseek-ai/DeepSeek-V3-0324",
+        "date": "2025-04-03",
+        "status": "full",
+        "main_language": "English",
+        "model_type": "chat",
+        "params": 685.0,
+        "result_metrics": {
+            "enem_challenge": 0.8901329601119664,
+            "bluex": 0.8414464534075105,
+            "oab_exams": 0.7148063781321184,
+            "assin2_sts": 0.8145997097875548,
+            "assin2_rte": 0.9421860387625551,
+            "faquad_nli": 0.796751127001399,
+            "hatebr_offensive": 0.9060129756724185,
+            "portuguese_hate_speech": 0.7262480672025753,
+            "tweetsentbr": 0.7037326638925795
+        },
+        "result_metrics_average": 0.8151018193300753,
+        "result_metrics_npm": 0.7165435243787625
+    },
     {
         "model": "qwen2-5-vl-72b-instruct",
         "name": "Qwen/Qwen2.5-VL-72B-Instruct (API)",
@@ -538,7 +561,7 @@
         "model": "claude-3-7-sonnet-20250219",
         "name": "Claude 3.7 Sonnet (2025-02-19)",
         "link": "https://www.anthropic.com/",
-        "date": "2025-04-03",
+        "date": "2025-04-04",
         "status": "full",
         "main_language": "English",
         "model_type": "proprietary",
@@ -555,5 +578,51 @@
         },
         "result_metrics_average": 0.8448598450650201,
         "result_metrics_npm": 0.7622301724524201
+    },
+    {
+        "model": "llama-4-scout-16e",
+        "name": "meta-llama/Llama-4-Scout-17B-16E-Instruct (Groq API)",
+        "link": "https://huggingface.co/meta-llama/Llama-4-Scout-17B-16E-Instruct",
+        "date": "2025-04-05",
+        "status": "full",
+        "main_language": "English",
+        "model_type": "chat",
+        "params": 109.0,
+        "result_metrics": {
+            "enem_challenge": 0.8054583624912526,
+            "bluex": 0.721835883171071,
+            "oab_exams": 0.6815489749430524,
+            "assin2_sts": 0.7741640227983941,
+            "assin2_rte": 0.9312877465954967,
+            "faquad_nli": 0.8567037452287072,
+            "hatebr_offensive": 0.8813700069483281,
+            "portuguese_hate_speech": 0.7009183720501475,
+            "tweetsentbr": 0.7277278145615887
+        },
+        "result_metrics_average": 0.7867794365320042,
+        "result_metrics_npm": 0.6811274967601382
+    },
+    {
+        "model": "llama-4-maverick-128e",
+        "name": "meta-llama/Llama-4-Maverick-17B-128E-Instruct (FireworksAI API)",
+        "link": "https://huggingface.co/meta-llama/Llama-4-Maverick-17B-128E-Instruct",
+        "date": "2025-04-05",
+        "status": "full",
+        "main_language": "English",
+        "model_type": "chat",
+        "params": 402.0,
+        "result_metrics": {
+            "enem_challenge": 0.8775367389783065,
+            "bluex": 0.8122392211404729,
+            "oab_exams": 0.7284738041002278,
+            "assin2_sts": 0.7333246903202654,
+            "assin2_rte": 0.9329419027588105,
+            "faquad_nli": 0.7823695413019562,
+            "hatebr_offensive": 0.9047550357833591,
+            "portuguese_hate_speech": 0.7231286908077994,
+            "tweetsentbr": 0.7165294511353842
+        },
+        "result_metrics_average": 0.8012554529251759,
+        "result_metrics_npm": 0.6997802853383734
     }
 ]

model_list.txt

@@ -27,6 +27,7 @@
   - AI-Sweden-Models/gpt-sw3-40b
   - AI-Sweden-Models/gpt-sw3-6.7b
   - AI-Sweden-Models/gpt-sw3-6.7b-v2
+  - AIDC-AI/Marco-LLM-ES
   - AXCXEPT/EZO-Qwen2.5-32B-Instruct
   - AdaptLLM/finance-LLM
   - AdaptLLM/finance-LLM-13B
@@ -51,6 +52,8 @@
   - BAAI/Infinity-Instruct-7M-0729-Llama3_1-8B
   - BAAI/Infinity-Instruct-7M-Gen-Llama3_1-8B
   - BAAI/OPI-Llama-3.1-8B-Instruct
+  - BSC-LT/salamandra-2b
+  - BSC-LT/salamandra-7b
   - Bruno/Caramelinho
   - Bruno/Caramelo_7B
   - CausalLM/34b-beta
@@ -519,6 +522,7 @@
   - deepseek-ai/DeepSeek-R1-Distill-Qwen-7B
   - deepseek-ai/DeepSeek-V2-Lite
   - deepseek-ai/DeepSeek-V2-Lite-Chat
+  - deepseek-ai/DeepSeek-V3-0324
   - deepseek-ai/deepseek-llm-7b-base
   - deepseek-ai/deepseek-moe-16b-base
   - deepseek-ai/deepseek-moe-16b-chat
@@ -715,6 +719,8 @@
   - meta-llama/Llama-3.2-3B-Instruct
   - meta-llama/Llama-3.2-90B-Vision-Instruct
   - meta-llama/Llama-3.3-70B-Instruct
+  - meta-llama/Llama-4-Maverick-17B-128E-Instruct
+  - meta-llama/Llama-4-Scout-17B-16E-Instruct
   - meta-llama/Meta-Llama-3-70B
   - meta-llama/Meta-Llama-3-70B-Instruct
   - meta-llama/Meta-Llama-3-8B