Automated leaderboard update

docs/data_AlpacaEval/alpaca_eval_gpt4_leaderboard.csv

@@ -1,14 +1,15 @@
 name,win_rate,avg_length,link,samples,filter
 GPT-4 Turbo,97.69900497512438,2049,,https://github.com/tatsu-lab/alpaca_eval/blob/main/results/gpt4_turbo/model_outputs.json,minimal
+Mistral Medium,96.83229813664596,1500,https://mistral.ai/news/la-plateforme/,https://github.com/tatsu-lab/alpaca_eval/blob/main/results/mistral-medium/model_outputs.json,minimal
 XwinLM 70b V0.1,95.56803995,1775,https://github.com/Xwin-LM/Xwin-LM,https://github.com/tatsu-lab/alpaca_eval/blob/main/results/xwinlm-70b-v0.1/model_outputs.json,community
 PairRM+Tulu 2+DPO 70B (best-of-16),95.39800995024876,1607,https://huggingface.co/llm-blender/PairRM,https://github.com/tatsu-lab/alpaca_eval/blob/main/results/pairrm-tulu-2-70b/model_outputs.json,community
 GPT-4,95.27950311,1365,,https://github.com/tatsu-lab/alpaca_eval/blob/main/results/gpt4/model_outputs.json,minimal
 Tulu 2+DPO 70B,95.03105590062113,1418,https://huggingface.co/allenai/tulu-2-dpo-70b,https://github.com/tatsu-lab/alpaca_eval/blob/main/results/tulu-2-dpo-70b/model_outputs.json,community
+GPT-4 0314,94.78260869565216,1371,,,verified
 Mixtral 8x7B v0.1,94.78260869565216,1465,https://huggingface.co/mistralai/Mixtral-8x7B-Instruct-v0.1,https://github.com/tatsu-lab/alpaca_eval/blob/main/results/Mixtral-8x7B-Instruct-v0.1/model_outputs.json,minimal
-GPT-4 0314,94.78260869565216,1371,,https://github.com/tatsu-lab/alpaca_eval/blob/main/results/gpt4_0314/model_outputs.json,verified
 Yi 34B Chat,94.08468244084682,2123,https://huggingface.co/01-ai/Yi-34B-Chat,https://github.com/tatsu-lab/alpaca_eval/blob/main/results/Yi-34B-Chat/model_outputs.json,verified
 GPT-4 0613,93.78109452736318,1140,,https://github.com/tatsu-lab/alpaca_eval/blob/main/results/gpt4_0613/model_outputs.json,verified
-GPT 3.5 Turbo 0613,93.41614906832298,1328,,https://github.com/tatsu-lab/alpaca_eval/blob/main/results/gpt-3.5-turbo-16k-0613/model_outputs.json,verified
+GPT 3.5 Turbo 0613,93.41614906832298,1328,,,verified
 PairRM+Zephyr 7B Beta (best-of-16),93.40796019900498,1487,https://huggingface.co/llm-blender/PairRM,https://github.com/tatsu-lab/alpaca_eval/blob/main/results/pairrm-zephyr-7b-beta/model_outputs.json,community
 Mistral 7B v0.2,92.77708592777088,1676,https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.2,https://github.com/tatsu-lab/alpaca_eval/blob/main/results/Mistral-7B-Instruct-v0.2/model_outputs.json,minimal
 LLaMA2 Chat 70B,92.66169154,1790,https://ai.meta.com/llama/,https://github.com/tatsu-lab/alpaca_eval/blob/main/results/llama-2-70b-chat-hf/model_outputs.json,minimal
@@ -37,7 +38,7 @@ OpenChat V2-W 13B,87.12686567,1566,https://github.com/imoneoi/openchat,https://g
 Claude 2.1,87.0807453416149,1096,,https://github.com/tatsu-lab/alpaca_eval/blob/main/results/claude-2.1/model_outputs.json,minimal
 OpenBuddy-LLaMA-65B-v8,86.53366584,1162,https://huggingface.co/OpenBuddy/openbuddy-llama-65b-v8-bf16,https://github.com/tatsu-lab/alpaca_eval/blob/main/results/openbuddy-llama-65b-v8/model_outputs.json,community
 WizardLM 13B V1.1,86.31840796,1525,https://huggingface.co/WizardLM/WizardLM-13B-V1.1,https://github.com/tatsu-lab/alpaca_eval/blob/main/results/wizardlm-13b-v1.1/model_outputs.json,community
-GPT 3.5 Turbo 1106,86.25621890547264,796,,https://github.com/tatsu-lab/alpaca_eval/blob/main/results/gpt-3.5-turbo-1106/model_outputs.json,verified
+GPT 3.5 Turbo 1106,86.25621890547264,796,,,verified
 Zephyr 7B Alpha,85.7587064676617,1302,https://huggingface.co/HuggingFaceH4/zephyr-7b-alpha,https://github.com/tatsu-lab/alpaca_eval/blob/main/results/zephyr-7b-alpha/model_outputs.json,community
 OpenChat V2 13B,84.9689441,1564,https://github.com/imoneoi/openchat,https://github.com/tatsu-lab/alpaca_eval/blob/main/results/openchat-v2-13b/model_outputs.json,community
 Tulu 2+DPO 7B,84.22360248447205,1663,https://huggingface.co/allenai/tulu-2-dpo-7b,https://github.com/tatsu-lab/alpaca_eval/blob/main/results/tulu-2-dpo-7b/model_outputs.json,community

docs/data_AlpacaEval_2/weighted_alpaca_eval_gpt4_turbo_leaderboard.csv

@@ -2,7 +2,7 @@ name,win_rate,avg_length,link,samples,filter
 GPT-4 Turbo,50.0,2049,,https://github.com/tatsu-lab/alpaca_eval/blob/main/results/gpt4_turbo/model_outputs.json,minimal
 Yi 34B Chat,29.65994671879504,2123,https://huggingface.co/01-ai/Yi-34B-Chat,https://github.com/tatsu-lab/alpaca_eval/blob/main/results/Yi-34B-Chat/model_outputs.json,minimal
 GPT-4,23.576789314782605,1365,,https://github.com/tatsu-lab/alpaca_eval/blob/main/results/gpt4/model_outputs.json,minimal
-GPT-4 0314,22.07325892871952,1371,,https://github.com/tatsu-lab/alpaca_eval/blob/main/results/gpt4_0314/model_outputs.json,verified
+GPT-4 0314,22.07325892871952,1371,,,verified
 Mistral Medium,21.855772543461345,1500,https://mistral.ai/news/la-plateforme/,https://github.com/tatsu-lab/alpaca_eval/blob/main/results/mistral-medium/model_outputs.json,minimal
 XwinLM 70b V0.1,21.812957073994184,1775,https://github.com/Xwin-LM/Xwin-LM,https://github.com/tatsu-lab/alpaca_eval/blob/main/results/xwinlm-70b-v0.1/model_outputs.json,community
 Evo v2 7B,20.83411302254932,1754,https://evolusion.ai,https://github.com/tatsu-lab/alpaca_eval/blob/main/results/evo-v2-7b/model_outputs.json,community
@@ -17,7 +17,7 @@ GPT-4 0613,15.755038087701964,1140,,https://github.com/tatsu-lab/alpaca_eval/blo
 Claude 2.1,15.733506736409938,1096,,https://github.com/tatsu-lab/alpaca_eval/blob/main/results/claude-2.1/model_outputs.json,minimal
 Evo 7B,15.577437399431057,1774,,https://github.com/tatsu-lab/alpaca_eval/blob/main/results/evo-7b/model_outputs.json,community
 Mistral 7B v0.2,14.722772657714286,1676,https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.2,https://github.com/tatsu-lab/alpaca_eval/blob/main/results/Mistral-7B-Instruct-v0.2/model_outputs.json,minimal
-GPT 3.5 Turbo 0613,14.132390707727575,1328,,https://github.com/tatsu-lab/alpaca_eval/blob/main/results/gpt-3.5-turbo-16k-0613/model_outputs.json,verified
+GPT 3.5 Turbo 0613,14.132390707727575,1328,,,verified
 LLaMA2 Chat 70B,13.871009062248447,1790,https://ai.meta.com/llama/,https://github.com/tatsu-lab/alpaca_eval/blob/main/results/llama-2-70b-chat-hf/model_outputs.json,minimal
 UltraLM 13B V2.0 (best-of-16),13.853373471264224,1720,https://huggingface.co/openbmb/UltraRM-13b,https://github.com/tatsu-lab/alpaca_eval/blob/main/results/ultralm-13b-v2.0-best-of-16/model_outputs.json,community
 PairRM+Tulu 2+DPO 13B (best-of-16),13.831901016808686,1454,https://huggingface.co/llm-blender/PairRM,https://github.com/tatsu-lab/alpaca_eval/blob/main/results/pairrm-tulu-2-13b/model_outputs.json,community
@@ -41,7 +41,7 @@ GPT 3.5 Turbo 0301,9.622453295105588,827,,https://github.com/tatsu-lab/alpaca_ev
 OpenChat V2-W 13B,9.615344158366243,1566,https://github.com/imoneoi/openchat,https://github.com/tatsu-lab/alpaca_eval/blob/main/results/openchat-v2-w-13b/model_outputs.json,community
 Humpback LLaMa 65B,9.42513904779845,1232,https://arxiv.org/abs/2308.06259,https://github.com/tatsu-lab/alpaca_eval/blob/main/results/humpback-llama-65b/model_outputs.json,community
 airoboros 65B,9.388950149698426,1512,https://huggingface.co/jondurbin/airoboros-65b-gpt4-1.2,https://github.com/tatsu-lab/alpaca_eval/blob/main/results/airoboros-65b/model_outputs.json,community
-GPT 3.5 Turbo 1106,9.177964562109176,796,,https://github.com/tatsu-lab/alpaca_eval/blob/main/results/gpt-3.5-turbo-1106/model_outputs.json,verified
+GPT 3.5 Turbo 1106,9.177964562109176,796,,,verified
 airoboros 33B,9.053160396238688,1514,https://huggingface.co/jondurbin/airoboros-33b-gpt4-1.2,https://github.com/tatsu-lab/alpaca_eval/blob/main/results/airoboros-33b/model_outputs.json,community
 OpenBuddy-LLaMA-65B-v8,8.770650150929061,1162,https://huggingface.co/OpenBuddy/openbuddy-llama-65b-v8-bf16,https://github.com/tatsu-lab/alpaca_eval/blob/main/results/openbuddy-llama-65b-v8/model_outputs.json,community
 GPT-3.5,8.564313096485627,1018,,https://github.com/tatsu-lab/alpaca_eval/blob/main/results/gpt35_turbo_instruct/model_outputs.json,community