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 31 of 70

Anthropic

Claude Computer Use 3.5

1 benchmarks · 1 observations

Explore results →

Anthropic

Claude Computer Use 3.7

1 benchmarks · 1 observations

Explore results →

Anthropic

Claude Fable 5 - None

1 benchmarks · 1 observations

Explore results →

Anthropic

Claude Fable 5 (Terminus 2)

1 benchmarks · 1 observations

Explore results →

Anthropic

Claude Fable 5 / Exa

1 benchmarks · 1 observations

Explore results →

Anthropic

Claude Fable 5 / Native

1 benchmarks · 1 observations

Explore results →

Anthropic

Claude Fable 5 + Claude Opus 4.8 + GPT-5.6 Sol + human collaborators

1 benchmarks · 1 observations

Explore results →

Anthropic

Claude Fable 5-high

1 benchmarks · 1 observations

Explore results →

Anthropic

Claude Fable 5-high-web-search-code-execution-128k†

1 benchmarks · 1 observations

Explore results →

Anthropic

Claude Fable 5-max-web-search-code-execution-128k†

1 benchmarks · 1 observations

Explore results →

Anthropic

Claude Fable 5.1 (Terminus 2)

1 benchmarks · 1 observations

Explore results →

Anthropic

Claude Fable 5.1 / Claude Code

1 benchmarks · 1 observations

Explore results →

Anthropic

Claude Fable 5.1-high

1 benchmarks · 1 observations

Explore results →

Anthropic

Claude Haiku 3.5

1 benchmarks · 2 observations

Explore results →

Anthropic

Claude Haiku 4-5-20251001 32K

1 benchmarks · 1 observations

Explore results →

Anthropic

Claude Haiku 4-5-20251001-1024†

1 benchmarks · 1 observations

Explore results →

Anthropic

Claude Haiku 4-5-20251001-thinking

1 benchmarks · 1 observations

Explore results →

Anthropic

Claude internal research model + human collaborators

1 benchmarks · 1 observations

Explore results →

Anthropic

Claude Opus 4-1-20250805 16K

1 benchmarks · 1 observations

Explore results →

Anthropic

Claude Opus 4-1-20250805 27K

1 benchmarks · 1 observations

Explore results →

Anthropic

Claude Opus 4-1-20250805 anthropic

1 benchmarks · 1 observations

Explore results →

Anthropic

Claude Opus 4-20250514 (no think)

1 benchmarks · 1 observations

Explore results →

Anthropic

Claude Opus 4-6 (CoWork)

1 benchmarks · 1 observations

Explore results →

Anthropic

Claude Opus 4-6-1024†

1 benchmarks · 1 observations

Explore results →

Anthropic

Claude Opus 4-7-1024†

1 benchmarks · 1 observations

Explore results →

Anthropic

Claude Opus 4-8-1024†

1 benchmarks · 1 observations

Explore results →

Anthropic

Claude Opus 4-8-adaptive-thinking-high-24000†

1 benchmarks · 1 observations

Explore results →

Anthropic

Claude Opus 4-8-adaptive-thinking-max-web-search-128000†

1 benchmarks · 1 observations

Explore results →

Anthropic

Claude Opus 4.5 (Nonthinking) (Terminus 2)

1 benchmarks · 1 observations

Explore results →

Anthropic

Claude Opus 4.5 (Thinking) (Terminus 2)

1 benchmarks · 1 observations

Explore results →

Anthropic

Claude Opus 4.6 (Mini-SWE)

1 benchmarks · 1 observations

Explore results →

Anthropic

Claude Opus 4.6 (Thinking) (Terminus 2)

1 benchmarks · 1 observations

Explore results →

Anthropic

Claude Opus 4.6 / AIBuildAI

1 benchmarks · 1 observations

Explore results →

Anthropic

Claude Opus 5 (Terminus 2)

1 benchmarks · 1 observations

Explore results →

Anthropic

Claude Opus 5 (xhigh) §

1 benchmarks · 1 observations

Explore results →

Anthropic

Claude Opus 5-5-max

1 benchmarks · 1 observations

Explore results →

Anthropic

Claude Opus 5-adaptive-thinking-max-web-search-code-execution-128k†

1 benchmarks · 1 observations

Explore results →

Anthropic

Claude Opus 5-high

1 benchmarks · 1 observations

Explore results →

Anthropic

Claude Opus 5.0

1 benchmarks · 8 observations

Explore results →

Anthropic

Claude Opus 5.5 (Terminus 2)

1 benchmarks · 1 observations

Explore results →

Anthropic

Claude Opus 5.5-high

1 benchmarks · 1 observations

Explore results →

Anthropic

Claude Sonnet 3.5

1 benchmarks · 1 observations

Explore results →

Anthropic

Claude Sonnet 4-5-20250929-1024†

1 benchmarks · 1 observations

Explore results →

Anthropic

Claude Sonnet 4-6-1024†

1 benchmarks · 1 observations

Explore results →

Anthropic

Claude Sonnet 4-6-adaptive-thinking-16000†

1 benchmarks · 1 observations

Explore results →

Anthropic

Claude Sonnet 4.5 (Thinking) (Terminus 2)

1 benchmarks · 1 observations

Explore results →

Anthropic

Claude Sonnet 5 (Cyber Range)

1 benchmarks · 1 observations

Explore results →

Anthropic

Claude Sonnet 5 (Terminus 2)

1 benchmarks · 1 observations

Explore results →