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.
552 models · page 1 of 12
Anthropic
Claude Haiku 5.5
72 benchmarks · 168 observations
Explore results →Anthropic
Claude Haiku 5.5 (none)
2 benchmarks · 2 observations
Explore results →Anthropic
Claude Haiku 5.5 (unknown)
2 benchmarks · 2 observations
Explore results →Gemini 4 Argon
106 benchmarks · 205 observations
Explore results →Gemini 4 Argon (unknown)
3 benchmarks · 3 observations
Explore results →Gemini 4 Argon (minimal)
1 benchmarks · 1 observations
Explore results →Anthropic
Claude Sonnet 5.5
71 benchmarks · 164 observations
Explore results →Anthropic
Claude Sonnet 5.5 (unknown)
1 benchmarks · 1 observations
Explore results →Anthropic
Claude Opus 5.5
127 benchmarks · 292 observations
Explore results →Anthropic
Claude Opus 5.5 (unknown)
2 benchmarks · 2 observations
Explore results →Gemini 3.8 Flash
96 benchmarks · 141 observations
Explore results →Gemini 3.8 Flash (unknown)
7 benchmarks · 7 observations
Explore results →Anthropic
Claude Fable 5.1
130 benchmarks · 307 observations
Explore results →Anthropic
Claude Fable 5.1 (unknown)
6 benchmarks · 6 observations
Explore results →Gemini 3.7 Flash
50 benchmarks · 72 observations
Explore results →Gemini 3.7 Flash (unknown)
4 benchmarks · 4 observations
Explore results →Anthropic
Claude Opus 5
93 benchmarks · 167 observations
Explore results →Anthropic
Claude Opus 5 (unknown)
4 benchmarks · 4 observations
Explore results →Gemini 3.6 Flash
49 benchmarks · 71 observations
Explore results →Gemini 3.5 Flash-Lite
40 benchmarks · 55 observations
Explore results →Anthropic
Claude Sonnet 5
60 benchmarks · 95 observations
Explore results →Anthropic
Claude Fable 5
82 benchmarks · 128 observations
Explore results →Anthropic
Claude Fable 5 (unknown)
7 benchmarks · 7 observations
Explore results →Anthropic
Claude Opus 4.8
79 benchmarks · 119 observations
Explore results →Gemini 3.5 Flash
64 benchmarks · 83 observations
Explore results →Gemini 3.5 Flash (Minimal)
1 benchmarks · 1 observations
Explore results →AI co-mathematician
2 benchmarks · 2 observations
Explore results →Anthropic
Claude Opus 4.7
61 benchmarks · 89 observations
Explore results →Anthropic
Claude Opus 4.7 (unknown)
8 benchmarks · 8 observations
Explore results →Gemini Robotics-ER 1.6 Preview
1 benchmarks · 1 observations
Explore results →Anthropic
Claude Mythos Preview (Early)
2 benchmarks · 4 observations
Explore results →Gemma 4 31B IT
16 benchmarks · 16 observations
Explore results →Gemma 4 26B A4B
9 benchmarks · 9 observations
Explore results →Gemma 4 31B (Reasoning)
1 benchmarks · 1 observations
Explore results →Gemini 3.1 Flash-Lite
17 benchmarks · 24 observations
Explore results →Gemini 3.1 Pro Preview
55 benchmarks · 74 observations
Explore results →Gemini 3.1 Pro
30 benchmarks · 37 observations
Explore results →Anthropic
Claude Sonnet 4.6
61 benchmarks · 83 observations
Explore results →Gemini 3 Deep Think
3 benchmarks · 6 observations
Explore results →Anthropic
Claude Opus 4.6
85 benchmarks · 150 observations
Explore results →Gemini 3 Flash Preview
29 benchmarks · 45 observations
Explore results →Gemini 3 Flash
6 benchmarks · 6 observations
Explore results →Gemini 3 Flash Preview (Reasoning)
5 benchmarks · 5 observations
Explore results →Gemini 3 Flash Preview (Non-reasoning)
1 benchmarks · 1 observations
Explore results →Anthropic
Claude Opus 4.5
59 benchmarks · 121 observations
Explore results →Anthropic
Claude Opus 4.5 (Reasoning)
5 benchmarks · 5 observations
Explore results →Gemini 3 Pro Preview
41 benchmarks · 51 observations
Explore results →Gemini-3 Pro
29 benchmarks · 34 observations
Explore results →