MODEL DIRECTORY
Follow the model.
See the evidence.
Benchmark results, evaluation settings and disclosed training methods—collected in one place for each model.
3,335 reported models and checkpoint variants. Scores keep their original units and sources.
3,335 models · page 18 of 70
Meta
Llama 3-V 70B
4 benchmarks · 4 observations
Explore results →Meta
Llama 3-V 8B
4 benchmarks · 4 observations
Explore results →Meta
Llama 3.1 Instruct Turbo (405B)
4 benchmarks · 8 observations
Explore results →Meta
Llama 3.1 Instruct Turbo (8B)
4 benchmarks · 4 observations
Explore results →Reported model
MiniGPT-4
4 benchmarks · 10 observations
Explore results →Mistral
Mistral Large 2411
4 benchmarks · 4 observations
Explore results →NVIDIA
Nemotron 4 340B
4 benchmarks · 4 observations
Explore results →OpenAI
o3-high
4 benchmarks · 4 observations
Explore results →OpenAI
o3-mini-high
4 benchmarks · 4 observations
Explore results →OpenAI
OpenAI o1-preview
4 benchmarks · 8 observations
Explore results →Reported model
OpenCoder-8B-Instruct
4 benchmarks · 4 observations
Explore results →Reported model
PaLM 8B
4 benchmarks · 7 observations
Explore results →Microsoft
Phi-2 2.7b*
4 benchmarks · 4 observations
Explore results →Qwen
Qwen1.5-7B-Chat
4 benchmarks · 5 observations
Explore results →Qwen
Qwen2-VL-72B
4 benchmarks · 6 observations
Explore results →Qwen
Qwen2-VL-7B
4 benchmarks · 5 observations
Explore results →Reported model
SOLAR-10.7B-Instruct-v1.0
4 benchmarks · 4 observations
Explore results →Reported model
Starcoder2-15B-Instruct-v0.1
4 benchmarks · 4 observations
Explore results →OpenAI
text-davinci-003 / -
4 benchmarks · 13 observations
Explore results →Reported model
Yi-VL-34B
4 benchmarks · 6 observations
Explore results →Reported model
Zephyr β-7B
4 benchmarks · 5 observations
Explore results →Anthropic
Anthropic-LM v4-s3 (52B)
3 benchmarks · 3 observations
Explore results →Reported model
AquilaChat2 34B
3 benchmarks · 6 observations
Explore results →Reported model
Artigenz-Coder-DS-6.7B
3 benchmarks · 3 observations
Explore results →Reported model
BLOOMZ (7B)
3 benchmarks · 7 observations
Explore results →Reported model
Chinese-Alpaca-Plus-13B
3 benchmarks · 3 observations
Explore results →Anthropic
Claude
3 benchmarks · 12 observations
Explore results →Anthropic
Claude Sonnet 3.5 (June 2024)
3 benchmarks · 3 observations
Explore results →Anthropic
claude-3-haiku (Mar 2024)
3 benchmarks · 3 observations
Explore results →Anthropic
claude-3-opus (Mar 2024)
3 benchmarks · 3 observations
Explore results →Anthropic
claude-3-sonnet (Mar 2024)
3 benchmarks · 3 observations
Explore results →Anthropic
Claude3-Opus
3 benchmarks · 5 observations
Explore results →Reported model
code-millenials-34B
3 benchmarks · 3 observations
Explore results →Reported model
CodeGen-16B
3 benchmarks · 3 observations
Explore results →Reported model
CodeGen-2B
3 benchmarks · 3 observations
Explore results →Meta
CodeLlama-70B
3 benchmarks · 3 observations
Explore results →Reported model
CodeT5+-16B
3 benchmarks · 3 observations
Explore results →Reported model
CodeT5+-2B
3 benchmarks · 3 observations
Explore results →Reported model
CodeT5+-6B
3 benchmarks · 3 observations
Explore results →Cohere
Cohere Command beta (52.4B)
3 benchmarks · 3 observations
Explore results →Cohere
Cohere Command beta (6.1B)
3 benchmarks · 3 observations
Explore results →Cohere
Cohere large v20220720 (13.1B)
3 benchmarks · 3 observations
Explore results →Cohere
Cohere medium v20220720 (6.1B)
3 benchmarks · 3 observations
Explore results →Cohere
Cohere medium v20221108 (6.1B)
3 benchmarks · 3 observations
Explore results →Cohere
Cohere small v20220720 (410M)
3 benchmarks · 3 observations
Explore results →Cohere
Cohere xlarge v20220609 (52.4B)
3 benchmarks · 3 observations
Explore results →Cohere
Cohere xlarge v20221108 (52.4B)
3 benchmarks · 3 observations
Explore results →Reported model
Composer 2.5 (Cursor CLI)
3 benchmarks · 3 observations
Explore results →