update 20241121
Browse files- elo_results_20241121.pkl +3 -0
- leaderboard_table_20241121.csv +209 -0
elo_results_20241121.pkl
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:610c77a4c4b47f1bb256a3dfa1808d5d32b5d9c819aa5f34b1aae857a959c303
|
3 |
+
size 4613615
|
leaderboard_table_20241121.csv
ADDED
@@ -0,0 +1,209 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
key,Model,MT-bench (score),MMLU,Knowledge cutoff date,License,Organization,Link
|
2 |
+
wizardlm-30b,WizardLM-30B,7.01,0.587,2023/6,Non-commercial,Microsoft,https://huggingface.co/WizardLM/WizardLM-30B-V1.0
|
3 |
+
vicuna-13b-16k,Vicuna-13B-16k,6.92,0.545,2023/7,Llama 2 Community,LMSYS,https://huggingface.co/lmsys/vicuna-13b-v1.5-16k
|
4 |
+
wizardlm-13b-v1.1,WizardLM-13B-v1.1,6.76,0.500,2023/7,Non-commercial,Microsoft,https://huggingface.co/WizardLM/WizardLM-13B-V1.1
|
5 |
+
tulu-30b,Tulu-30B,6.43,0.581,2023/6,Non-commercial,AllenAI/UW,https://huggingface.co/allenai/tulu-30b
|
6 |
+
guanaco-65b,Guanaco-65B,6.41,0.621,2023/5,Non-commercial,UW,https://huggingface.co/timdettmers/guanaco-65b-merged
|
7 |
+
openassistant-llama-30b,OpenAssistant-LLaMA-30B,6.41,0.560,2023/4,Non-commercial,OpenAssistant,https://huggingface.co/OpenAssistant/oasst-sft-6-llama-30b-xor
|
8 |
+
wizardlm-13b-v1.0,WizardLM-13B-v1.0,6.35,0.523,2023/5,Non-commercial,Microsoft,https://huggingface.co/WizardLM/WizardLM-13B-V1.0
|
9 |
+
vicuna-7b-16k,Vicuna-7B-16k,6.22,0.485,2023/7,Llama 2 Community,LMSYS,https://huggingface.co/lmsys/vicuna-7b-v1.5-16k
|
10 |
+
baize-v2-13b,Baize-v2-13B,5.75,0.489,2023/4,Non-commercial,UCSD,https://huggingface.co/project-baize/baize-v2-13b
|
11 |
+
xgen-7b-8k-inst,XGen-7B-8K-Inst,5.55,0.421,2023/7,Non-commercial,Salesforce,https://huggingface.co/Salesforce/xgen-7b-8k-inst
|
12 |
+
nous-hermes-13b,Nous-Hermes-13B,5.51,0.493,2023/6,Non-commercial,NousResearch,https://huggingface.co/NousResearch/Nous-Hermes-13b
|
13 |
+
mpt-30b-instruct,MPT-30B-Instruct,5.22,0.478,2023/6,CC-BY-SA 3.0,MosaicML,https://huggingface.co/mosaicml/mpt-30b-instruct
|
14 |
+
falcon-40b-instruct,Falcon-40B-Instruct,5.17,0.547,2023/5,Apache 2.0,TII,https://huggingface.co/tiiuae/falcon-40b-instruct
|
15 |
+
h2o-oasst-openllama-13b,H2O-Oasst-OpenLLaMA-13B,4.63,0.428,2023/6,Apache 2.0,h2oai,https://huggingface.co/h2oai/h2ogpt-gm-oasst1-en-2048-open-llama-13b
|
16 |
+
gpt-4-1106-preview,GPT-4-1106-preview,9.32,-,2023/4,Proprietary,OpenAI,https://openai.com/blog/new-models-and-developer-products-announced-at-devday
|
17 |
+
gpt-4-0314,GPT-4-0314,8.96,0.864,2021/9,Proprietary,OpenAI,https://openai.com/research/gpt-4
|
18 |
+
claude-1,Claude-1,7.90,0.770,-,Proprietary,Anthropic,https://www.anthropic.com/index/introducing-claude
|
19 |
+
gpt-4-0613,GPT-4-0613,9.18,-,2021/9,Proprietary,OpenAI,https://platform.openai.com/docs/models/gpt-4-and-gpt-4-turbo
|
20 |
+
claude-2.0,Claude-2.0,8.06,0.785,-,Proprietary,Anthropic,https://www.anthropic.com/index/claude-2
|
21 |
+
claude-2.1,Claude-2.1,8.18,-,-,Proprietary,Anthropic,https://www.anthropic.com/index/claude-2-1
|
22 |
+
gpt-3.5-turbo-0613,GPT-3.5-Turbo-0613,8.39,-,2021/9,Proprietary,OpenAI,https://platform.openai.com/docs/models/gpt-3-5
|
23 |
+
mixtral-8x7b-instruct-v0.1,Mixtral-8x7B-Instruct-v0.1,8.30,0.706,2023/12,Apache 2.0,Mistral,https://mistral.ai/news/mixtral-of-experts/
|
24 |
+
claude-instant-1,Claude-Instant-1,7.85,0.734,-,Proprietary,Anthropic,https://www.anthropic.com/index/introducing-claude
|
25 |
+
gpt-3.5-turbo-0314,GPT-3.5-Turbo-0314,7.94,0.700,2021/9,Proprietary,OpenAI,https://platform.openai.com/docs/models/gpt-3-5
|
26 |
+
tulu-2-dpo-70b,Tulu-2-DPO-70B,7.89,-,2023/11,AI2 ImpACT Low-risk,AllenAI/UW,https://huggingface.co/allenai/tulu-2-dpo-70b
|
27 |
+
yi-34b-chat,Yi-34B-Chat,-,0.735,2023/6,Yi License,01 AI,https://huggingface.co/01-ai/Yi-34B-Chat
|
28 |
+
gemini-pro,Gemini Pro,-,0.718,2023/4,Proprietary,Google,https://blog.google/technology/ai/gemini-api-developers-cloud/
|
29 |
+
gemini-pro-dev-api,Gemini-1.0-Pro-001,-,0.718,2023/4,Proprietary,Google,https://aistudio.google.com/app/prompts/new_chat?model=gemini-1.0-pro
|
30 |
+
bard-jan-24-gemini-pro,Gemini App (2024-01-24),-,-,Online,Proprietary,Google,https://gemini.google.com/app
|
31 |
+
wizardlm-70b,WizardLM-70B-v1.0,7.71,0.637,2023/8,Llama 2 Community,Microsoft,https://huggingface.co/WizardLM/WizardLM-70B-V1.0
|
32 |
+
vicuna-33b,Vicuna-33B,7.12,0.592,2023/8,Non-commercial,LMSYS,https://huggingface.co/lmsys/vicuna-33b-v1.3
|
33 |
+
starling-lm-7b-alpha,Starling-LM-7B-alpha,8.09,0.639,2023/11,CC-BY-NC-4.0,UC Berkeley,https://huggingface.co/berkeley-nest/Starling-LM-7B-alpha
|
34 |
+
pplx-70b-online,pplx-70B-online,-,-,Online,Proprietary,Perplexity AI,https://blog.perplexity.ai/blog/introducing-pplx-online-llms
|
35 |
+
openchat-3.5,OpenChat-3.5,7.81,0.643,2023/11,Apache-2.0,OpenChat,https://huggingface.co/openchat/openchat_3.5
|
36 |
+
openhermes-2.5-mistral-7b,OpenHermes-2.5-Mistral-7B,-,-,2023/11,Apache-2.0,NousResearch,https://huggingface.co/teknium/OpenHermes-2.5-Mistral-7B
|
37 |
+
gpt-3.5-turbo-1106,GPT-3.5-Turbo-1106,8.32,-,2021/9,Proprietary,OpenAI,https://platform.openai.com/docs/models/gpt-3-5
|
38 |
+
llama-2-70b-chat,Llama-2-70B-chat,6.86,0.630,2023/7,Llama 2 Community,Meta,https://huggingface.co/meta-llama/Llama-2-70b-chat-hf
|
39 |
+
solar-10.7b-instruct-v1.0,SOLAR-10.7B-Instruct-v1.0,7.58,0.662,2023/11,CC-BY-NC-4.0,Upstage AI,https://huggingface.co/upstage/SOLAR-10.7B-Instruct-v1.0
|
40 |
+
dolphin-2.2.1-mistral-7b,Dolphin-2.2.1-Mistral-7B,-,-,2023/10,Apache-2.0,Cognitive Computations,https://huggingface.co/ehartford/dolphin-2.2.1-mistral-7b
|
41 |
+
wizardlm-13b,WizardLM-13b-v1.2,7.20,0.527,2023/7,Llama 2 Community,Microsoft,https://huggingface.co/WizardLM/WizardLM-13B-V1.2
|
42 |
+
zephyr-7b-beta,Zephyr-7B-beta,7.34,0.614,2023/10,MIT,HuggingFace,https://huggingface.co/HuggingFaceH4/zephyr-7b-beta
|
43 |
+
mpt-30b-chat,MPT-30B-chat,6.39,0.504,2023/6,CC-BY-NC-SA-4.0,MosaicML,https://huggingface.co/mosaicml/mpt-30b-chat
|
44 |
+
vicuna-13b,Vicuna-13B,6.57,0.558,2023/7,Llama 2 Community,LMSYS,https://huggingface.co/lmsys/vicuna-13b-v1.5
|
45 |
+
qwen-14b-chat,Qwen-14B-Chat,6.96,0.665,2023/8,Qianwen LICENSE,Alibaba,https://huggingface.co/Qwen/Qwen-14B-Chat
|
46 |
+
zephyr-7b-alpha,Zephyr-7B-alpha,6.88,-,2023/10,MIT,HuggingFace,https://huggingface.co/HuggingFaceH4/zephyr-7b-alpha
|
47 |
+
codellama-34b-instruct,CodeLlama-34B-instruct,-,0.537,2023/7,Llama 2 Community,Meta,https://huggingface.co/codellama/CodeLlama-34b-Instruct-hf
|
48 |
+
falcon-180b-chat,falcon-180b-chat,-,0.680,2023/9,Falcon-180B TII License,TII,https://huggingface.co/tiiuae/falcon-180B-chat
|
49 |
+
guanaco-33b,Guanaco-33B,6.53,0.576,2023/5,Non-commercial,UW,https://huggingface.co/timdettmers/guanaco-33b-merged
|
50 |
+
llama-2-13b-chat,Llama-2-13b-chat,6.65,0.536,2023/7,Llama 2 Community,Meta,https://huggingface.co/meta-llama/Llama-2-13b-chat-hf
|
51 |
+
mistral-7b-instruct,Mistral-7B-Instruct-v0.1,6.84,0.554,2023/9,Apache 2.0,Mistral,https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.1
|
52 |
+
pplx-7b-online,pplx-7B-online,-,-,Online,Proprietary,Perplexity AI,https://blog.perplexity.ai/blog/introducing-pplx-online-llms
|
53 |
+
llama-2-7b-chat,Llama-2-7B-chat,6.27,0.458,2023/7,Llama 2 Community,Meta,https://huggingface.co/meta-llama/Llama-2-7b-chat-hf
|
54 |
+
vicuna-7b,Vicuna-7B,6.17,0.498,2023/7,Llama 2 Community,LMSYS,https://huggingface.co/lmsys/vicuna-7b-v1.5
|
55 |
+
palm-2,PaLM-Chat-Bison-001,6.40,-,2021/6,Proprietary,Google,https://cloud.google.com/vertex-ai/docs/generative-ai/learn/models#foundation_models
|
56 |
+
koala-13b,Koala-13B,5.35,0.447,2023/4,Non-commercial,UC Berkeley,https://bair.berkeley.edu/blog/2023/04/03/koala/
|
57 |
+
chatglm3-6b,ChatGLM3-6B,-,-,2023/10,Apache-2.0,Tsinghua,https://huggingface.co/THUDM/chatglm3-6b
|
58 |
+
gpt4all-13b-snoozy,GPT4All-13B-Snoozy,5.41,0.430,2023/3,Non-commercial,Nomic AI,https://huggingface.co/nomic-ai/gpt4all-13b-snoozy
|
59 |
+
mpt-7b-chat,MPT-7B-Chat,5.42,0.320,2023/5,CC-BY-NC-SA-4.0,MosaicML,https://huggingface.co/mosaicml/mpt-7b-chat
|
60 |
+
chatglm2-6b,ChatGLM2-6B,4.96,0.455,2023/6,Apache-2.0,Tsinghua,https://huggingface.co/THUDM/chatglm2-6b
|
61 |
+
RWKV-4-Raven-14B,RWKV-4-Raven-14B,3.98,0.256,2023/4,Apache 2.0,RWKV,https://huggingface.co/BlinkDL/rwkv-4-raven
|
62 |
+
alpaca-13b,Alpaca-13B,4.53,0.481,2023/3,Non-commercial,Stanford,https://crfm.stanford.edu/2023/03/13/alpaca.html
|
63 |
+
oasst-pythia-12b,OpenAssistant-Pythia-12B,4.32,0.270,2023/4,Apache 2.0,OpenAssistant,https://huggingface.co/OpenAssistant/oasst-sft-4-pythia-12b-epoch-3.5
|
64 |
+
chatglm-6b,ChatGLM-6B,4.50,0.361,2023/3,Non-commercial,Tsinghua,https://huggingface.co/THUDM/chatglm-6b
|
65 |
+
fastchat-t5-3b,FastChat-T5-3B,3.04,0.477,2023/4,Apache 2.0,LMSYS,https://huggingface.co/lmsys/fastchat-t5-3b-v1.0
|
66 |
+
stablelm-tuned-alpha-7b,StableLM-Tuned-Alpha-7B,2.75,0.244,2023/4,CC-BY-NC-SA-4.0,Stability AI,https://huggingface.co/stabilityai/stablelm-tuned-alpha-7b
|
67 |
+
dolly-v2-12b,Dolly-V2-12B,3.28,0.257,2023/4,MIT,Databricks,https://huggingface.co/databricks/dolly-v2-12b
|
68 |
+
llama-13b,LLaMA-13B,2.61,0.470,2023/2,Non-commercial,Meta,https://arxiv.org/abs/2302.13971
|
69 |
+
mistral-medium,Mistral Medium,8.61,0.753,-,Proprietary,Mistral,https://mistral.ai/news/la-plateforme/
|
70 |
+
llama2-70b-steerlm-chat,NV-Llama2-70B-SteerLM-Chat,7.54,0.685,2023/11,Llama 2 Community,Nvidia,https://huggingface.co/nvidia/Llama2-70B-SteerLM-Chat
|
71 |
+
stripedhyena-nous-7b,StripedHyena-Nous-7B,-,-,2023/12,Apache 2.0,Together AI,https://huggingface.co/togethercomputer/StripedHyena-Nous-7B
|
72 |
+
deepseek-llm-67b-chat,DeepSeek-LLM-67B-Chat,-,0.713,2023/11,DeepSeek License,DeepSeek AI,https://huggingface.co/deepseek-ai/deepseek-llm-67b-chat
|
73 |
+
gpt-4-0125-preview,GPT-4-0125-preview,-,-,2023/12,Proprietary,OpenAI,https://openai.com/blog/new-models-and-developer-products-announced-at-devday
|
74 |
+
qwen1.5-72b-chat,Qwen1.5-72B-Chat,8.61,0.775,2024/2,Qianwen LICENSE,Alibaba,https://qwenlm.github.io/blog/qwen1.5/
|
75 |
+
qwen1.5-7b-chat,Qwen1.5-7B-Chat,7.6,0.610,2024/2,Qianwen LICENSE,Alibaba,https://qwenlm.github.io/blog/qwen1.5/
|
76 |
+
qwen1.5-4b-chat,Qwen1.5-4B-Chat,-,0.561,2024/2,Qianwen LICENSE,Alibaba,https://qwenlm.github.io/blog/qwen1.5/
|
77 |
+
openchat-3.5-0106,OpenChat-3.5-0106,7.8,0.658,2024/1,Apache-2.0,OpenChat,https://huggingface.co/openchat/openchat-3.5-0106
|
78 |
+
nous-hermes-2-mixtral-8x7b-dpo,Nous-Hermes-2-Mixtral-8x7B-DPO,-,-,2024/1,Apache-2.0,NousResearch,https://huggingface.co/NousResearch/Nous-Hermes-2-Mixtral-8x7B-DPO
|
79 |
+
gpt-3.5-turbo-0125,GPT-3.5-Turbo-0125,-,-,2021/9,Proprietary,OpenAI,https://platform.openai.com/docs/models/gpt-3-5-turbo
|
80 |
+
mistral-next,Mistral-Next,-,-,-,Proprietary,Mistral,https://chat.mistral.ai/chat
|
81 |
+
mistral-large-2402,Mistral-Large-2402,-,0.812,-,Proprietary,Mistral,https://mistral.ai/news/mistral-large/
|
82 |
+
gemma-7b-it,Gemma-7B-it,-,0.643,2024/2,Gemma license,Google,https://huggingface.co/google/gemma-7b-it
|
83 |
+
gemma-2b-it,Gemma-2B-it,-,0.423,2024/2,Gemma license,Google,https://huggingface.co/google/gemma-2b-it
|
84 |
+
mistral-7b-instruct-v0.2,Mistral-7B-Instruct-v0.2,7.6,-,2023/12,Apache-2.0,Mistral,https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.2
|
85 |
+
claude-3-sonnet-20240229,Claude 3 Sonnet,-,0.790,2023/8,Proprietary,Anthropic,https://www.anthropic.com/news/claude-3-family
|
86 |
+
claude-3-opus-20240229,Claude 3 Opus,-,0.868,2023/8,Proprietary,Anthropic,https://www.anthropic.com/news/claude-3-family
|
87 |
+
codellama-70b-instruct,CodeLlama-70B-instruct,-,-,2024/1,Llama 2 Community,Meta,https://huggingface.co/codellama/CodeLlama-70b-hf
|
88 |
+
olmo-7b-instruct,OLMo-7B-instruct,-,-,2024/2,Apache-2.0,Allen AI,https://huggingface.co/allenai/OLMo-7B-Instruct
|
89 |
+
claude-3-haiku-20240307,Claude 3 Haiku,-,0.752,2023/8,Proprietary,Anthropic,https://www.anthropic.com/news/claude-3-family
|
90 |
+
starling-lm-7b-beta,Starling-LM-7B-beta,8.12,-,2024/3,Apache-2.0,Nexusflow,https://huggingface.co/Nexusflow/Starling-LM-7B-beta
|
91 |
+
command-r,Command R (04-2024),-,-,2024/3,CC-BY-NC-4.0,Cohere,https://txt.cohere.com/command-r
|
92 |
+
qwen1.5-14b-chat,Qwen1.5-14B-Chat,7.91,0.676,2024/2,Qianwen LICENSE,Alibaba,https://qwenlm.github.io/blog/qwen1.5/
|
93 |
+
qwen1.5-32b-chat,Qwen1.5-32B-Chat,8.30,0.734,2024/2,Qianwen LICENSE,Alibaba,https://qwenlm.github.io/blog/qwen1.5-32b/
|
94 |
+
command-r-plus,Command R+ (04-2024),-,-,2024/3,CC-BY-NC-4.0,Cohere,https://txt.cohere.com/command-r-plus-microsoft-azure/
|
95 |
+
gemma-1.1-7b-it,Gemma-1.1-7B-it,-,0.643,2024/2,Gemma license,Google,https://huggingface.co/google/gemma-1.1-7b-it
|
96 |
+
dbrx-instruct-preview,DBRX-Instruct-Preview,-,0.737,2023/12,DBRX LICENSE,Databricks,https://www.databricks.com/blog/introducing-dbrx-new-state-art-open-llm
|
97 |
+
gpt-4-turbo-2024-04-09,GPT-4-Turbo-2024-04-09,-,-,2023/12,Proprietary,OpenAI,https://platform.openai.com/docs/models/gpt-4-turbo-and-gpt-4
|
98 |
+
gemma-1.1-2b-it,Gemma-1.1-2b-it,-,0.643,2024/2,Gemma license,Google,https://huggingface.co/google/gemma-1.1-2b-it
|
99 |
+
reka-flash-21b-20240226,Reka-Flash-21B,-,0.735,2023/11,Proprietary,Reka AI,https://www.reka.ai/news/reka-flash-efficient-and-capable-multimodal-language-models
|
100 |
+
reka-flash-21b-20240226-online,Reka-Flash-21B-online,-,-,Online,Proprietary,Reka AI,https://docs.reka.ai/http-api.html#generation
|
101 |
+
zephyr-orpo-141b-A35b-v0.1,Zephyr-ORPO-141b-A35b-v0.1,-,-,2024/4,Apache 2.0,HuggingFace,https://huggingface.co/HuggingFaceH4/zephyr-orpo-141b-A35b-v0.1
|
102 |
+
mixtral-8x22b-instruct-v0.1,Mixtral-8x22b-Instruct-v0.1,-,0.778,2024/4,Apache 2.0,Mistral,https://mistral.ai/news/mixtral-8x22b/
|
103 |
+
llama-3-70b-instruct,Llama-3-70B-Instruct,-,0.820,2023/12,Llama 3 Community,Meta,https://llama.meta.com/llama3/
|
104 |
+
llama-3-8b-instruct,Llama-3-8B-Instruct,-,0.684,2023/3,Llama 3 Community,Meta,https://llama.meta.com/llama3/
|
105 |
+
gemini-1.5-pro-api-0409-preview,Gemini-1.5-Pro-Preview-0409,-,0.819,2023/11,Proprietary,Google,https://blog.google/technology/ai/google-gemini-next-generation-model-february-2024/
|
106 |
+
phi-3-mini-128k-instruct,Phi-3-Mini-128k-Instruct,-,0.681,2023/10,MIT,Microsoft,https://azure.microsoft.com/en-us/blog/introducing-phi-3-redefining-whats-possible-with-slms/
|
107 |
+
snowflake-arctic-instruct,Snowflake Arctic Instruct,-,0.673,2024/4,Apache 2.0,Snowflake,https://www.snowflake.com/blog/arctic-open-efficient-foundation-language-models-snowflake/
|
108 |
+
qwen-max-0428,Qwen-Max-0428,-,-,-,Proprietary,Alibaba,https://help.aliyun.com/zh/dashscope/developer-reference/api-details
|
109 |
+
qwen1.5-110b-chat,Qwen1.5-110B-Chat,8.88,0.804,2024/4,Qianwen LICENSE,Alibaba,https://qwenlm.github.io/blog/qwen1.5-110b/
|
110 |
+
reka-core-20240501,Reka-Core-20240501,-,0.832,-,Proprietary,Reka AI,https://www.reka.ai/news/reka-core-our-frontier-class-multimodal-language-model
|
111 |
+
gpt-4o-2024-05-13,GPT-4o-2024-05-13,-,0.887,2023/10,Proprietary,OpenAI,https://openai.com/index/hello-gpt-4o/
|
112 |
+
phi-3-mini-4k-instruct,Phi-3-Mini-4k-Instruct,-,0.688,2023/10,MIT,Microsoft,https://huggingface.co/microsoft/Phi-3-mini-4k-instruct
|
113 |
+
yi-large-preview,Yi-Large-preview,-,-,Unknown,Proprietary,01 AI,https://platform.lingyiwanwu.com/docs#%E6%A8%A1%E5%9E%8B
|
114 |
+
glm-4-0116,GLM-4-0116,-,-,Unknown,Proprietary,Zhipu AI,https://open.bigmodel.cn/
|
115 |
+
gemini-advanced-0514,Gemini Advanced App (2024-05-14),-,-,Online,Proprietary,Google,https://gemini.google.com/advanced
|
116 |
+
gemini-1.5-pro-api-0514,Gemini-1.5-Pro-001,-,0.859,2023/11,Proprietary,Google,https://aistudio.google.com/app/prompts/new_chat?model=gemini-1.5-pro
|
117 |
+
gemini-1.5-pro-001,Gemini-1.5-Pro-001,-,0.859,2023/11,Proprietary,Google,https://aistudio.google.com/app/prompts/new_chat?model=gemini-1.5-pro
|
118 |
+
gemini-1.5-flash-api-0514,Gemini-1.5-Flash-001,-,0.789,2023/11,Proprietary,Google,https://aistudio.google.com/app/prompts/new_chat?model=gemini-1.5-flash
|
119 |
+
gemini-1.5-flash-001,Gemini-1.5-Flash-001,-,0.789,2023/11,Proprietary,Google,https://aistudio.google.com/app/prompts/new_chat?model=gemini-1.5-flash
|
120 |
+
yi-34b-chat,Yi-34B-Chat,-,0.735,2023/6,Yi License,01 AI,https://huggingface.co/01-ai/Yi-34B-Chat
|
121 |
+
yi-1.5-34b-chat,Yi-1.5-34B-Chat,-,0.768,2024/5,Apache-2.0,01 AI,https://huggingface.co/01-ai/Yi-1.5-34B-Chat
|
122 |
+
phi-3-small-8k-instruct,Phi-3-Small-8k-Instruct,-,0.757,2023/10,MIT,Microsoft,https://huggingface.co/microsoft/Phi-3-small-8k-instruct
|
123 |
+
phi-3-medium-4k-instruct,Phi-3-Medium-4k-Instruct,-,0.780,2023/10,MIT,Microsoft,https://huggingface.co/microsoft/Phi-3-medium-4k-instruct
|
124 |
+
qwen2-72b-instruct,Qwen2-72B-Instruct,9.12,0.842,2024/6,Qianwen LICENSE,Alibaba,https://qwenlm.github.io/blog/qwen2/
|
125 |
+
yi-large,Yi-Large,-,-,Unknown,Proprietary,01 AI,https://platform.01.ai/docs#models-and-pricing
|
126 |
+
nemotron-4-340b-instruct,Nemotron-4-340B-Instruct,-,-,2023/6,NVIDIA Open Model,Nvidia,https://huggingface.co/nvidia/Nemotron-4-340B-Instruct
|
127 |
+
reka-flash-preview-20240611,Reka-Flash-Preview-20240611,-,-,-,Proprietary,Reka AI,https://docs.reka.ai/http-api.html#generation
|
128 |
+
glm-4-0520,GLM-4-0520,-,-,Unknown,Proprietary,Zhipu AI,https://open.bigmodel.cn/dev/api#language
|
129 |
+
deepseek-coder-v2,DeepSeek-Coder-V2-Instruct,-,-,2024/6,DeepSeek License,DeepSeek AI,https://huggingface.co/deepseek-ai/DeepSeek-Coder-V2-Instruct
|
130 |
+
claude-3-5-sonnet-20240620,Claude 3.5 Sonnet (20240620),-,0.887,2024/4,Proprietary,Anthropic,https://www.anthropic.com/news/claude-3-5-sonnet
|
131 |
+
gemma-2-27b-it,Gemma-2-27B-it,-,-,2024/6,Gemma license,Google,https://aistudio.google.com/app/prompts/new_chat?model=gemma-2-27b-it
|
132 |
+
gemma-2-9b-it,Gemma-2-9B-it,-,-,2024/6,Gemma license,Google,https://aistudio.google.com/app/prompts/new_chat?model=gemma-2-9b-it
|
133 |
+
llava-v1.6-34b,LLaVA-v1.6-34B,-,-,2024/1,Apache 2.0,LLaVA,https://llava-vl.github.io/blog/2024-01-30-llava-next/
|
134 |
+
phi-3-mini-4k-instruct-june-2024,Phi-3-Mini-4K-Instruct-June-24,-,0.709,2023/10,MIT,Microsoft,https://huggingface.co/microsoft/Phi-3-mini-4k-instruct
|
135 |
+
deepseek-v2-api-0628,Deepseek-v2-API-0628,-,-,-,DeepSeek,DeepSeek AI,https://platform.deepseek.com/api-docs/updates#deepseek-chat
|
136 |
+
cogvlm2-llama3-chat-19b,CogVLM2-llama3-chat-19b,-,-,2024/7,CogVLM2,Zhipu AI,https://huggingface.co/THUDM/cogvlm2-llama3-chat-19B
|
137 |
+
gpt-4o-mini-2024-07-18,GPT-4o-mini-2024-07-18,-,0.820,2023/10,Proprietary,OpenAI,https://openai.com/index/gpt-4o-mini-advancing-cost-efficient-intelligence/
|
138 |
+
llama-3.1-405b-instruct-fp8,Meta-Llama-3.1-405B-Instruct-fp8,-,0.886,2023/12,Llama 3.1 Community,Meta,https://ai.meta.com/blog/meta-llama-3-1/
|
139 |
+
llama-3.1-405b-instruct-bf16,Meta-Llama-3.1-405B-Instruct-bf16,-,0.886,2023/12,Llama 3.1 Community,Meta,https://ai.meta.com/blog/meta-llama-3-1/
|
140 |
+
llama-3.1-405b-instruct,Meta-Llama-3.1-405B-Instruct-fp8,-,0.886,2023/12,Llama 3.1 Community,Meta,https://ai.meta.com/blog/meta-llama-3-1/
|
141 |
+
llama-3.1-70b-instruct,Meta-Llama-3.1-70B-Instruct,-,0.860,2023/12,Llama 3.1 Community,Meta,https://ai.meta.com/blog/meta-llama-3-1/
|
142 |
+
llama-3.1-8b-instruct,Meta-Llama-3.1-8B-Instruct,-,0.730,2023/12,Llama 3.1 Community,Meta,https://ai.meta.com/blog/meta-llama-3-1/
|
143 |
+
athene-70b-0725,Athene-70B,-,-,2024/7,CC-BY-NC-4.0,NexusFlow,https://huggingface.co/Nexusflow/Athene-70B
|
144 |
+
internvl2-26b,InternVL2-26B,-,-,2024/7,MIT,OpenGVLab,https://internvl.github.io/blog/2024-07-02-InternVL-2.0/
|
145 |
+
gemma-2-2b-it,Gemma-2-2b-it,-,0.513,2024/7,Gemma license,Google,https://aistudio.google.com/app/prompts/new_chat?model=gemma-2-2b-it
|
146 |
+
glm-4-air,GLM-4-AIR,-,-,Unknown,Proprietary,Zhipu AI,https://open.bigmodel.cn/
|
147 |
+
snorkel-mistral-pairrm-dpo,Snorkel-Mistral-PairRM-DPO,-,-,2024/5,Apache 2.0,Snorkel AI,https://huggingface.co/snorkelai/Snorkel-Mistral-PairRM-DPO
|
148 |
+
mistral-large-2407,Mistral-Large-2407,-,-,2024/7,Mistral Research,Mistral,https://mistral.ai/news/mistral-large-2407/
|
149 |
+
gemini-1.5-pro-exp-0801,Gemini-1.5-Pro-Exp-0801,-,-,2023/11,Proprietary,Google,https://aistudio.google.com/app/prompts/new_chat?model=gemini-1.5-pro-exp-0801
|
150 |
+
reka-core-20240722,Reka-Core-20240722,-,-,-,Proprietary,Reka AI,https://docs.reka.ai/available-models
|
151 |
+
reka-flash-20240722,Reka-Flash-20240722,-,-,-,Proprietary,Reka AI,https://docs.reka.ai/available-models
|
152 |
+
deepseek-coder-v2-0724,Deepseek-Coder-v2-0724,-,-,-,Proprietary,DeepSeek,https://platform.deepseek.com/api-docs/updates/#version-2024-07-24
|
153 |
+
chatgpt-4o-latest,ChatGPT-4o-latest (2024-08-08),-,-,2023/10,Proprietary,OpenAI,https://x.com/OpenAIDevs/status/1823510395619000525
|
154 |
+
chatgpt-4o-latest-20240808,ChatGPT-4o-latest (2024-08-08),-,-,2023/10,Proprietary,OpenAI,https://x.com/OpenAIDevs/status/1823510395619000525
|
155 |
+
gpt-4o-2024-08-06,GPT-4o-2024-08-06,-,-,2023/10,Proprietary,OpenAI,https://platform.openai.com/docs/models/gpt-4o
|
156 |
+
jamba-1.5-large,Jamba-1.5-Large,-,0.812,2024/3,Jamba Open,AI21 Labs,https://www.ai21.com/jamba
|
157 |
+
jamba-1.5-mini,Jamba-1.5-Mini,-,0.697,2024/3,Jamba Open,AI21 Labs,https://www.ai21.com/jamba
|
158 |
+
minicpm-v-2_6,MiniCPM-v 2_6,-,-,2024/7,Apache 2.0,OpenBMB,https://huggingface.co/openbmb/MiniCPM-V-2_6
|
159 |
+
phi-3-vision-128k-instruct,Phi-3-Vision-128K-Instruct,-,-,2024/3,MIT,Microsoft,https://huggingface.co/microsoft/Phi-3-vision-128k-instruct
|
160 |
+
grok-2-2024-08-13,Grok-2-08-13,-,-,2024/3,Proprietary,xAI,https://x.ai/blog/grok-2
|
161 |
+
grok-2-mini-2024-08-13,Grok-2-Mini-08-13,-,-,2024/3,Proprietary,xAI,https://x.ai/blog/grok-2
|
162 |
+
gemini-1.5-pro-exp-0827,Gemini-1.5-Pro-Exp-0827,-,-,2023/11,Proprietary,Google,https://aistudio.google.com/app/prompts/new_chat?model=gemini-1.5-pro-exp-0827
|
163 |
+
gemini-1.5-flash-exp-0827,Gemini-1.5-Flash-Exp-0827,-,-,2023/11,Proprietary,Google,https://aistudio.google.com/app/prompts/new_chat?model=gemini-1.5-flash-exp-0827
|
164 |
+
gemini-1.5-flash-8b-exp-0827,Gemini-1.5-Flash-8B-Exp-0827,-,-,2023/11,Proprietary,Google,https://aistudio.google.com/app/prompts/new_chat?model=gemini-1.5-flash-8b-exp-0827
|
165 |
+
internvl2-4b,InternVL2-4b,-,-,2024/7,MIT,OpenGVLab,https://internvl.github.io/blog/2024-07-02-InternVL-2.0/
|
166 |
+
command-r-plus-08-2024,Command R+ (08-2024),-,-,2024/8,CC-BY-NC-4.0,Cohere,https://docs.cohere.com/docs/command-r-plus#model-details
|
167 |
+
command-r-08-2024,Command R (08-2024),-,-,2024/8,CC-BY-NC-4.0,Cohere,https://docs.cohere.com/docs/command-r-plus#model-details
|
168 |
+
gemma-2-9b-it-simpo,Gemma-2-9B-it-SimPO,-,-,2024/7,MIT,Princeton,https://huggingface.co/princeton-nlp/gemma-2-9b-it-SimPO
|
169 |
+
yi-vision,Yi-Vision,-,-,2024/7,Proprietary,01 AI,https://platform.01.ai/docs#models-and-pricing
|
170 |
+
llava-onevision-qwen2-72b-ov,LLaVA-OneVision-qwen2-72B-ov-sft,-,-,2024/8,Apache 2.0,LLaVA,https://huggingface.co/lmms-lab/llava-onevision-qwen2-72b-ov
|
171 |
+
phi-3.5-vision-instruct,Phi-3.5-vision-instruct,-,-,2024/8,MIT,Microsoft,https://huggingface.co/microsoft/Phi-3.5-vision-instruct
|
172 |
+
deepseek-v2.5,Deepseek-v2.5,-,-,-,DeepSeek,DeepSeek,https://huggingface.co/deepseek-ai/DeepSeek-V2.5
|
173 |
+
qwen-plus-0828,Qwen-Plus-0828,-,-,-,Proprietary,Alibaba,https://help.aliyun.com/zh/model-studio/getting-started/models
|
174 |
+
qwen2-vl-7b-instruct,Qwen2-VL-7B-Instruct,-,-,-,Apache 2.0,Aliaba,https://huggingface.co/Qwen/Qwen2-VL-7B-Instruct
|
175 |
+
qwen-vl-max-0809,Qwen2-VL-72B,-,-,-,Proprietary,Alibaba,https://qwenlm.github.io/zh/blog/qwen2-vl/
|
176 |
+
chatgpt-4o-latest-20240903,ChatGPT-4o-latest (2024-09-03),-,-,2023/10,Proprietary,OpenAI,https://help.openai.com/en/articles/9624314-model-release-notes
|
177 |
+
o1-preview,o1-preview,-,-,2023/10,Proprietary,OpenAI,https://platform.openai.com/docs/models/o1
|
178 |
+
o1-mini,o1-mini,-,-,2023/10,Proprietary,OpenAI,https://platform.openai.com/docs/models/o1
|
179 |
+
qwen2.5-72b-instruct,Qwen2.5-72B-Instruct,-,-,2024/9,Qwen,Alibaba,https://qwenlm.github.io/blog/qwen2.5/
|
180 |
+
internlm2_5-20b-chat,InternLM2.5-20B-chat,-,-,2024/8,Other,InternLM,https://huggingface.co/internlm/internlm2_5-20b-chat
|
181 |
+
llama-3.2-3b-instruct,Meta-Llama-3.2-3B-Instruct,-,-,2023/12,Llama 3.2,Meta,https://ai.meta.com/blog/llama-3-2-connect-2024-vision-edge-mobile-devices/
|
182 |
+
llama-3.2-1b-instruct,Meta-Llama-3.2-1B-Instruct,-,-,2023/12,Llama 3.2,Meta,https://ai.meta.com/blog/llama-3-2-connect-2024-vision-edge-mobile-devices/
|
183 |
+
llama-3.2-vision-90b-instruct,Llama-3.2-90B-Vision-Instruct,-,-,2023/11,Llama 3.2,Meta,https://ai.meta.com/blog/llama-3-2-connect-2024-vision-edge-mobile-devices/
|
184 |
+
llama-3.2-vision-11b-instruct,Llama-3.2-11B-Vision-Instruct,-,-,2023/11,Llama 3.2,Meta,https://ai.meta.com/blog/llama-3-2-connect-2024-vision-edge-mobile-devices/
|
185 |
+
pixtral-12b-2409,Pixtral-12B-2409,-,-,2024/9,Apache 2.0,Mistral,https://mistral.ai/news/pixtral-12b/
|
186 |
+
qwen2-vl-72b,Qwen2-VL-72b-Instruct,-,-,2024/9,Qwen,Alibaba,https://qwenlm.github.io/zh/blog/qwen2-vl/
|
187 |
+
gemini-1.5-pro-002,Gemini-1.5-Pro-002,-,-,-,Proprietary,Google,https://aistudio.google.com/app/prompts/new_chat?instructions=lmsys&model=gemini-1.5-pro-002
|
188 |
+
gemini-1.5-flash-002,Gemini-1.5-Flash-002,-,-,-,Proprietary,Google,https://aistudio.google.com/app/prompts/new_chat?instructions=lmsys&model=gemini-1.5-flash-002
|
189 |
+
gemini-1.5-flash-8b-001,Gemini-1.5-Flash-8B-001,-,-,-,Proprietary,Google,https://aistudio.google.com/app/prompts/new_chat?instructions=lmsys&model=gemini-1.5-flash-8b
|
190 |
+
glm-4-plus,GLM-4-Plus,-,-,-,Proprietary,Zhipu AI,https://bigmodel.cn/dev/howuse/glm-4
|
191 |
+
yi-lightning,Yi-Lightning,-,-,-,Proprietary,01 AI,https://platform.lingyiwanwu.com/docs#%E6%A8%A1%E5%9E%8B%E4%B8%8E%E8%AE%A1%E8%B4%B9
|
192 |
+
yi-lightning-lite,Yi-Lightning-lite,-,-,-,Proprietary,01 AI,https://platform.lingyiwanwu.com/docs#%E6%A8%A1%E5%9E%8B%E4%B8%8E%E8%AE%A1%E8%B4%B9
|
193 |
+
qwen-max-0919,Qwen-Max-0919,-,-,-,Qwen,Alibaba,https://help.aliyun.com/zh/dashscope/developer-reference/model-introduction
|
194 |
+
llama-3.1-nemotron-70b-instruct,Llama-3.1-Nemotron-70B-Instruct,-,-,2023/12,Llama 3.1,Nvidia,https://huggingface.co/nvidia/Llama-3.1-Nemotron-70B-Instruct
|
195 |
+
llama-3.1-nemotron-51b-instruct,Llama-3.1-Nemotron-51B-Instruct,-,-,2023/12,Llama 3.1,Nvidia,https://huggingface.co/nvidia/Llama-3_1-Nemotron-51B-Instruct
|
196 |
+
claude-3-5-sonnet-20241022,Claude 3.5 Sonnet (20241022),-,0.887,2024/4,Proprietary,Anthropic,https://www.anthropic.com/news/3-5-models-and-computer-use
|
197 |
+
molmo-72b-0924,Molmo-72B-0924,-,-,-,Apache 2.0,AI2,https://huggingface.co/allenai/Molmo-72B-0924
|
198 |
+
molmo-7b-d-0924,Molmo-7B-D-0924,-,-,-,Apache 2.0,AI2,https://huggingface.co/allenai/Molmo-7B-D-0924
|
199 |
+
reka-core-20240904,Reka-Core-20240904,-,-,-,Proprietary,Reka AI,https://docs.reka.ai/available-models
|
200 |
+
reka-flash-20240904,Reka-Flash-20240904,-,-,-,Proprietary,Reka AI,https://docs.reka.ai/available-models
|
201 |
+
hunyuan-standard-256k,Hunyuan-Standard-256K,-,-,-,Proprietary,Tencent,https://cloud.tencent.com/document/product/1729/104753
|
202 |
+
ministral-8b-2410,Ministral-8B-2410,-,-,-,MRL,Mistral,https://huggingface.co/mistralai/Ministral-8B-Instruct-2410
|
203 |
+
gemini-exp-1114,Gemini-Exp-1114,-,-,-,Proprietary,Google,https://aistudio.google.com/app/prompts/new_chat?instructions=lmsys-1114&model=gemini-exp-1114
|
204 |
+
chatgpt-4o-latest-20241120,ChatGPT-4o-latest (2024-11-20),-,-,-,Proprietary,OpenAI,https://help.openai.com/en/articles/9624314-model-release-notes
|
205 |
+
qwen2.5-coder-32b-instruct,Qwen2.5-Coder-32B-Instruct,-,-,-,Apache 2.0,Alibaba,https://huggingface.co/Qwen/Qwen2.5-Coder-32B-Instruct
|
206 |
+
granite-3.0-8b-instruct,Granite-3.0-8B-Instruct,-,-,-,Apache 2.0,IBM,https://huggingface.co/ibm-granite/granite-3.0-8b-instruct
|
207 |
+
granite-3.0-2b-instruct,Granite-3.0-2B-Instruct,-,-,-,Apache 2.0,IBM,https://huggingface.co/ibm-granite/granite-3.0-2b-instruct
|
208 |
+
gemini-exp-1121,Gemini-Exp-1121,-,-,-,Proprietary,Google,https://aistudio.google.com/app/prompts/new_chat?instructions=lmsys-1121&model=gemini-exp-1121
|
209 |
+
step-1v-32k,Step-1V-32K,-,-,-,Proprietary,StepFun,https://platform.stepfun.com/docs/llm/vision
|