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.
411 models · page 6 of 9
gemini-2.5-flash-preview-05-20 (no think)
1 benchmarks · 1 observations
Explore results →Gemini-2.5-Pro / CAIR MLE-STAR-Pro-1.0
1 benchmarks · 1 observations
Explore results →Gemini-2.5-Pro / CAIR MLE-STAR-Pro-1.5
1 benchmarks · 1 observations
Explore results →Gemini-2.5-Pro / Famou-Agent
1 benchmarks · 1 observations
Explore results →Gemini-2.5-Pro / Famou-Agent 2.0
1 benchmarks · 1 observations
Explore results →gemini-2.5-pro-preview-06-05 (32k think)
1 benchmarks · 1 observations
Explore results →gemini-2.5-pro-preview-06-05 (default think)
1 benchmarks · 1 observations
Explore results →Gemini-3-Flash (Mini-SWE)
1 benchmarks · 1 observations
Explore results →gemini-3-flash-preview-high
1 benchmarks · 1 observations
Explore results →gemini-3-pro-preview (Thinking)*
1 benchmarks · 1 observations
Explore results →Gemini-3-Pro-Preview / CAIR MARS
1 benchmarks · 1 observations
Explore results →Gemini-3-Pro-Preview / CAIR MARS+
1 benchmarks · 1 observations
Explore results →Gemini-3-Pro-Preview / Famou-Agent 2.0
1 benchmarks · 1 observations
Explore results →Gemini-3-Pro-Preview / MLEvolve
1 benchmarks · 1 observations
Explore results →gemini-3-pro-preview-high
1 benchmarks · 1 observations
Explore results →Gemini-3-Pro-Preview1 / Leeroo
1 benchmarks · 1 observations
Explore results →Gemini-3-Pro-Preview1 / PiEvolve (Fractal AI Research)
1 benchmarks · 2 observations
Explore results →gemini-3.1-flash-lite-preview-high
1 benchmarks · 1 observations
Explore results →gemini-3.1-flash-live-preview (Thinking)†
1 benchmarks · 1 observations
Explore results →gemini-3.1-flash-live-preview†
1 benchmarks · 3 observations
Explore results →Gemini-3.1-Pro (Mini-SWE)
1 benchmarks · 1 observations
Explore results →gemini-3.1-pro-preview-high
1 benchmarks · 1 observations
Explore results →gemini-3.1-pro-preview-high-web-search†
1 benchmarks · 1 observations
Explore results →gemini-3.5-flash-high
1 benchmarks · 1 observations
Explore results →gemini-3.5-flash-lite-high
1 benchmarks · 1 observations
Explore results →gemini-3.6-flash-high
1 benchmarks · 1 observations
Explore results →gemini-3.6-flash-medium-web-search-code-execution†
1 benchmarks · 1 observations
Explore results →gemini-3.7-flash-high
1 benchmarks · 1 observations
Explore results →gemini-3.7-flash-high-web-search-code-execution†
1 benchmarks · 1 observations
Explore results →gemini-3.8-flash-high
1 benchmarks · 1 observations
Explore results →gemini-4-argon-high
1 benchmarks · 1 observations
Explore results →gemini-4-argon-low
1 benchmarks · 1 observations
Explore results →gemini-exp-1114
1 benchmarks · 1 observations
Explore results →gemini-exp-1121
1 benchmarks · 1 observations
Explore results →Gemini-Exp-114
1 benchmarks · 1 observations
Explore results →gemini-exp-1206
1 benchmarks · 1 observations
Explore results →gemini-exp-1206 (diff)
1 benchmarks · 1 observations
Explore results →gemini-exp-1206 (whole)
1 benchmarks · 1 observations
Explore results →Gemini-Flash-1.5
1 benchmarks · 1 observations
Explore results →Gemini-Pro-V [44]
1 benchmarks · 1 observations
Explore results →Gemini-Pro-Vision [42] / -
1 benchmarks · 1 observations
Explore results →GeminiPro-Vision[41]
1 benchmarks · 1 observations
Explore results →GeminiPro-Vision[41] (GeminiPro[41])
1 benchmarks · 1 observations
Explore results →GeminiPro1-5
1 benchmarks · 1 observations
Explore results →GeminiProVision
1 benchmarks · 1 observations
Explore results →Gemma 2
1 benchmarks · 2 observations
Explore results →Gemma 4 31B IT (Terminus 2)
1 benchmarks · 1 observations
Explore results →Gemma 4 E2B
1 benchmarks · 1 observations
Explore results →