Upload 2 files

elo_results_20230905.pkl

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2c2af81a8e5ebcfee37fb4828349ed037d392fe99dd8250f6e22e47d0a456bdf
-size 41671
+oid sha256:2bdbeeb5e205b9dfb105b4be02931591b8759bca7bb36d32189c53d8dc8d4453
+size 40474

leaderboard_table_20230905.csv

@@ -1,44 +1,44 @@
 Model,MT-bench (score),Arena Elo rating,MMLU,License,Link
-CodeLlama-34B-instruct,-,1030,-,Llama 2 Community,https://huggingface.co/codellama/CodeLlama-34b-Instruct-hf
-GPT-4,8.99,1192,0.864,Proprietary,https://openai.com/research/gpt-4
-Claude-2,8.06,1133,0.785,Proprietary,https://www.anthropic.com/index/claude-2
+CodeLlama-34B-instruct,-,1032,-,Llama 2 Community,https://huggingface.co/codellama/CodeLlama-34b-Instruct-hf
+GPT-4,8.99,1193,0.864,Proprietary,https://openai.com/research/gpt-4
+Claude-2,8.06,1134,0.785,Proprietary,https://www.anthropic.com/index/claude-2
 GPT-3.5-turbo,7.94,1118,0.700,Proprietary,https://openai.com/blog/chatgpt
-Claude-1,7.90,1160,0.770,Proprietary,https://www.anthropic.com/index/introducing-claude
-Claude-instant-1,7.85,1131,0.734,Proprietary,https://www.anthropic.com/index/introducing-claude
+Claude-1,7.90,1161,0.770,Proprietary,https://www.anthropic.com/index/introducing-claude
+Claude-instant-1,7.85,1130,0.734,Proprietary,https://www.anthropic.com/index/introducing-claude
 WizardLM-70b-v1.0,7.71,-,-,Llama 2 Community,https://huggingface.co/WizardLM/WizardLM-70B-V1.0
 WizardLM-13b-v1.2,7.20,1046,-,Llama 2 Community,https://huggingface.co/WizardLM/WizardLM-13B-V1.2
-Vicuna-33B,7.12,1095,0.592,Non-commercial,https://huggingface.co/lmsys/vicuna-33b-v1.3
+Vicuna-33B,7.12,1097,0.592,Non-commercial,https://huggingface.co/lmsys/vicuna-33b-v1.3
 WizardLM-30B,7.01,-,0.587,Non-commercial,https://huggingface.co/WizardLM/WizardLM-30B-V1.0
 Vicuna-13B-16k,6.92,-,0.545,Llama 2 Community,https://huggingface.co/lmsys/vicuna-13b-v1.5-16k
-Llama-2-70b-chat,6.86,1059,0.630,Llama 2 Community,https://huggingface.co/meta-llama/Llama-2-70b-chat-hf
+Llama-2-70b-chat,6.86,1060,0.630,Llama 2 Community,https://huggingface.co/meta-llama/Llama-2-70b-chat-hf
 WizardLM-13B-v1.1,6.76,-,0.500,Non-commercial,https://huggingface.co/WizardLM/WizardLM-13B-V1.1
-Llama-2-13b-chat,6.65,998,0.536,Llama 2 Community,https://huggingface.co/meta-llama/Llama-2-13b-chat-hf
+Llama-2-13b-chat,6.65,999,0.536,Llama 2 Community,https://huggingface.co/meta-llama/Llama-2-13b-chat-hf
 Vicuna-13B,6.57,1046,0.558,Llama 2 Community,https://huggingface.co/lmsys/vicuna-13b-v1.5
 Guanaco-33B,6.53,1036,0.576,Non-commercial,https://huggingface.co/timdettmers/guanaco-33b-merged
 Tulu-30B,6.43,-,0.581,Non-commercial,https://huggingface.co/allenai/tulu-30b
 Guanaco-65B,6.41,-,0.621,Non-commercial,https://huggingface.co/timdettmers/guanaco-65b-merged
 OpenAssistant-LLaMA-30B,6.41,-,0.560,Non-commercial,https://huggingface.co/OpenAssistant/oasst-sft-6-llama-30b-xor
-PaLM-Chat-Bison-001,6.40,1007,-,Proprietary,https://cloud.google.com/vertex-ai/docs/generative-ai/learn/models#foundation_models
-MPT-30B-chat,6.39,1042,0.504,CC-BY-NC-SA-4.0,https://huggingface.co/mosaicml/mpt-30b-chat
+PaLM-Chat-Bison-001,6.40,1008,-,Proprietary,https://cloud.google.com/vertex-ai/docs/generative-ai/learn/models#foundation_models
+MPT-30B-chat,6.39,1043,0.504,CC-BY-NC-SA-4.0,https://huggingface.co/mosaicml/mpt-30b-chat
 WizardLM-13B-v1.0,6.35,-,0.523,Non-commercial,https://huggingface.co/WizardLM/WizardLM-13B-V1.0
 Llama-2-7b-chat,6.27,979,0.458,Llama 2 Community,https://huggingface.co/meta-llama/Llama-2-7b-chat-hf
 Vicuna-7B-16k,6.22,-,0.485,Llama 2 Community,https://huggingface.co/lmsys/vicuna-7b-v1.5-16k
-Vicuna-7B,6.17,1002,0.498,Llama 2 Community,https://huggingface.co/lmsys/vicuna-7b-v1.5
+Vicuna-7B,6.17,1003,0.498,Llama 2 Community,https://huggingface.co/lmsys/vicuna-7b-v1.5
 Baize-v2-13B,5.75,-,0.489,Non-commercial,https://huggingface.co/project-baize/baize-v2-13b
 XGen-7B-8K-Inst,5.55,-,0.421,Non-commercial,https://huggingface.co/Salesforce/xgen-7b-8k-inst
 Nous-Hermes-13B,5.51,-,0.493,Non-commercial,https://huggingface.co/NousResearch/Nous-Hermes-13b
 MPT-7B-Chat,5.42,943,0.320,CC-BY-NC-SA-4.0,https://huggingface.co/mosaicml/mpt-7b-chat
-GPT4All-13B-Snoozy,5.41,963,0.430,Non-commercial,https://huggingface.co/nomic-ai/gpt4all-13b-snoozy
+GPT4All-13B-Snoozy,5.41,964,0.430,Non-commercial,https://huggingface.co/nomic-ai/gpt4all-13b-snoozy
 Koala-13B,5.35,979,0.447,Non-commercial,https://bair.berkeley.edu/blog/2023/04/03/koala/
 MPT-30B-Instruct,5.22,-,0.478,CC-BY-SA 3.0,https://huggingface.co/mosaicml/mpt-30b-instruct
 Falcon-40B-Instruct,5.17,-,0.547,Apache 2.0,https://huggingface.co/tiiuae/falcon-40b-instruct
-ChatGLM2-6B,4.96,964,0.455,Apache-2.0,https://huggingface.co/THUDM/chatglm2-6b
+ChatGLM2-6B,4.96,965,0.455,Apache-2.0,https://huggingface.co/THUDM/chatglm2-6b
 H2O-Oasst-OpenLLaMA-13B,4.63,-,0.428,Apache 2.0,https://huggingface.co/h2oai/h2ogpt-gm-oasst1-en-2048-open-llama-13b
-Alpaca-13B,4.53,918,0.481,Non-commercial,https://crfm.stanford.edu/2023/03/13/alpaca.html
+Alpaca-13B,4.53,919,0.481,Non-commercial,https://crfm.stanford.edu/2023/03/13/alpaca.html
 ChatGLM-6B,4.50,896,0.361,Non-commercial,https://huggingface.co/THUDM/chatglm-6b
 OpenAssistant-Pythia-12B,4.32,911,0.270,Apache 2.0,https://huggingface.co/OpenAssistant/oasst-sft-4-pythia-12b-epoch-3.5
 RWKV-4-Raven-14B,3.98,939,0.256,Apache 2.0,https://huggingface.co/BlinkDL/rwkv-4-raven
-Dolly-V2-12B,3.28,837,0.257,MIT,https://huggingface.co/databricks/dolly-v2-12b
-FastChat-T5-3B,3.04,887,0.477,Apache 2.0,https://huggingface.co/lmsys/fastchat-t5-3b-v1.0
-StableLM-Tuned-Alpha-7B,2.75,858,0.244,CC-BY-NC-SA-4.0,https://huggingface.co/stabilityai/stablelm-tuned-alpha-7b
-LLaMA-13B,2.61,813,0.470,Non-commercial,https://arxiv.org/abs/2302.13971
+Dolly-V2-12B,3.28,838,0.257,MIT,https://huggingface.co/databricks/dolly-v2-12b
+FastChat-T5-3B,3.04,888,0.477,Apache 2.0,https://huggingface.co/lmsys/fastchat-t5-3b-v1.0
+StableLM-Tuned-Alpha-7B,2.75,859,0.244,CC-BY-NC-SA-4.0,https://huggingface.co/stabilityai/stablelm-tuned-alpha-7b
+LLaMA-13B,2.61,814,0.470,Non-commercial,https://arxiv.org/abs/2302.13971