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 28 of 70
Anthropic
anthropic/claude-opus-4-20250514*
1 benchmarks · 1 observations
Explore results →Anthropic
anthropic/claude-opus-4.1@reasoning=high
1 benchmarks · 4 observations
Explore results →Anthropic
anthropic/claude-opus-4.1@reasoning=none
1 benchmarks · 4 observations
Explore results →Anthropic
anthropic/claude-opus-4.5@reasoning=high
1 benchmarks · 4 observations
Explore results →Anthropic
anthropic/claude-opus-4.5@reasoning=none
1 benchmarks · 4 observations
Explore results →Anthropic
anthropic/claude-opus-4.6@reasoning=high
1 benchmarks · 4 observations
Explore results →Anthropic
anthropic/claude-opus-4.6@reasoning=none
1 benchmarks · 4 observations
Explore results →Anthropic
anthropic/claude-opus-4.7@reasoning=max
1 benchmarks · 4 observations
Explore results →Anthropic
anthropic/claude-opus-4.7@reasoning=none
1 benchmarks · 4 observations
Explore results →Anthropic
anthropic/claude-opus-4.8@reasoning=none
1 benchmarks · 4 observations
Explore results →Anthropic
anthropic/claude-opus-4.8@reasoning=xhigh
1 benchmarks · 4 observations
Explore results →Anthropic
anthropic/claude-opus-4@reasoning=default
1 benchmarks · 4 observations
Explore results →Anthropic
anthropic/claude-opus-5.5@reasoning=low
1 benchmarks · 4 observations
Explore results →Anthropic
anthropic/claude-opus-5.5@reasoning=max
1 benchmarks · 4 observations
Explore results →Anthropic
anthropic/claude-opus-5@reasoning=low
1 benchmarks · 4 observations
Explore results →Anthropic
anthropic/claude-opus-5@reasoning=xhigh
1 benchmarks · 4 observations
Explore results →Anthropic
anthropic/claude-sonnet-4.5@reasoning=high
1 benchmarks · 4 observations
Explore results →Anthropic
anthropic/claude-sonnet-4.5@reasoning=none
1 benchmarks · 4 observations
Explore results →Anthropic
anthropic/claude-sonnet-4.6@reasoning=high
1 benchmarks · 4 observations
Explore results →Anthropic
anthropic/claude-sonnet-4.6@reasoning=none
1 benchmarks · 4 observations
Explore results →Anthropic
anthropic/claude-sonnet-4@reasoning=high
1 benchmarks · 4 observations
Explore results →Anthropic
anthropic/claude-sonnet-4@reasoning=none
1 benchmarks · 4 observations
Explore results →Anthropic
anthropic/claude-sonnet-5.5@reasoning=low
1 benchmarks · 2 observations
Explore results →Anthropic
anthropic/claude-sonnet-5.5@reasoning=max
1 benchmarks · 2 observations
Explore results →Anthropic
anthropic/claude-sonnet-5@reasoning=low
1 benchmarks · 4 observations
Explore results →Anthropic
anthropic/claude-sonnet-5@reasoning=max
1 benchmarks · 4 observations
Explore results →Reported model
APEX-SQL LIGHTSPEED [Cao et al. '25]
1 benchmarks · 1 observations
Explore results →Reported model
AraGPT2 (1.7B)
1 benchmarks · 1 observations
Explore results →Reported model
AraT5 (220M)
1 benchmarks · 1 observations
Explore results →Reported model
AraT5v2 (220M)
1 benchmarks · 1 observations
Explore results →Reported model
arcee-ai/trinity-large-thinking@reasoning=minimal
1 benchmarks · 4 observations
Explore results →Reported model
arcee-ai/trinity-large-thinking@reasoning=xhigh
1 benchmarks · 4 observations
Explore results →OpenAI
Arcwise + GPT-4o Arcwise
1 benchmarks · 1 observations
Explore results →OpenAI
Arena-Hard Judge (GPT-4o)
1 benchmarks · 1 observations
Explore results →OpenAI
AskData + GPT-4o AT&T CDO - DSAIR [Shkapenyuk et al. '25]
1 benchmarks · 1 observations
Explore results →Reported model
AskData AT&T CDO - DSAIR [Shkapenyuk et al. '25]
1 benchmarks · 1 observations
Explore results →Reported model
AssemblyAI Universal-3.5 Pro
1 benchmarks · 1 observations
Explore results →Reported model
Athene-RM-70B
1 benchmarks · 1 observations
Explore results →Reported model
Athene-RM-8B
1 benchmarks · 1 observations
Explore results →Reported model
Auto-J-13b
1 benchmarks · 1 observations
Explore results →OpenAI
AutoGPT (GPT4 backend)
1 benchmarks · 3 observations
Explore results →DeepSeek
AutoLink + DeepSeek-R1 HUST VLR Lab [Wang et al. '25]
1 benchmarks · 2 observations
Explore results →Cohere
Aya-expanse-32b
1 benchmarks · 1 observations
Explore results →Cohere
Aya-expanse-8b
1 benchmarks · 1 observations
Explore results →OpenAI
babbage (1.3B)
1 benchmarks · 1 observations
Explore results →Reported model
Baichuan-13B*
1 benchmarks · 1 observations
Explore results →Reported model
Baichuan-7B*
1 benchmarks · 1 observations
Explore results →Reported model
Baichuan2-Chat 13B (8-shot)
1 benchmarks · 1 observations
Explore results →