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.
321 models · page 7 of 7
google/gemini-3.1-pro-preview@reasoning=low
1 benchmarks · 4 observations
Explore results →google/gemini-3.5-flash-lite@reasoning=minimal
1 benchmarks · 4 observations
Explore results →google/gemini-3.5-flash-lite@reasoning=xhigh
1 benchmarks · 4 observations
Explore results →google/gemini-3.5-flash@reasoning=minimal
1 benchmarks · 4 observations
Explore results →google/gemini-3.5-flash@reasoning=xhigh
1 benchmarks · 4 observations
Explore results →google/gemini-3.6-flash@reasoning=minimal
1 benchmarks · 4 observations
Explore results →google/gemini-3.6-flash@reasoning=xhigh
1 benchmarks · 4 observations
Explore results →google/gemini-3.7-flash@reasoning=max
1 benchmarks · 4 observations
Explore results →google/gemini-3.7-flash@reasoning=minimal
1 benchmarks · 4 observations
Explore results →google/gemini-4-argon@reasoning=high
1 benchmarks · 2 observations
Explore results →google/gemini-4-argon@reasoning=low
1 benchmarks · 2 observations
Explore results →google/gemma-3-27b-it@reasoning=default
1 benchmarks · 4 observations
Explore results →google/gemma-4-26b-a4b-it@reasoning=none
1 benchmarks · 4 observations
Explore results →google/gemma-4-26b-a4b-it@reasoning=xhigh
1 benchmarks · 4 observations
Explore results →google/gemma-4-31b-it@reasoning=high
1 benchmarks · 4 observations
Explore results →google/gemma-4-31b-it@reasoning=none
1 benchmarks · 4 observations
Explore results →GRM-Gemma-2B
1 benchmarks · 1 observations
Explore results →Med-PaLM 2 Google Research & DeepMind (Singhal et al. 2023)
1 benchmarks · 1 observations
Explore results →nicolinho/QRM-Gemma-2-27B
1 benchmarks · 1 observations
Explore results →Amazon
Nova 2 (Pro)
1 benchmarks · 1 observations
Explore results →Amazon
Nova Lite
1 benchmarks · 1 observations
Explore results →Amazon
nova-2-lite-v1
1 benchmarks · 1 observations
Explore results →PalM
1 benchmarks · 2 observations
Explore results →QUVI-3 + Gemini-3-pro-preview DAQUV
1 benchmarks · 1 observations
Explore results →Reasoning-SQL 14B Google Cloud / Stanford [Pourreza et al. '25]
1 benchmarks · 1 observations
Explore results →RECAP + Gemini Google Cloud
1 benchmarks · 1 observations
Explore results →ShikaiChen/LDL-Reward-Gemma-2-27B-v0.1
1 benchmarks · 1 observations
Explore results →Skywork/Skywork-Reward-Gemma-2-27B
1 benchmarks · 1 observations
Explore results →Skywork/Skywork-Reward-Gemma-2-27B-v0.2
1 benchmarks · 1 observations
Explore results →Amazon
Spektr-SQL Amazon Ads - SpektrBot [Kishore Kumar et al.]
1 benchmarks · 1 observations
Explore results →Amazon
Spektr-SQL Amazon Ads-SpektrBot [Ravi Shankar et al.]
1 benchmarks · 1 observations
Explore results →Spider-Agent + Gemini-2.0-Pro
1 benchmarks · 1 observations
Explore results →VertexAI Evaluation (Gemini-1.5-pro)
1 benchmarks · 1 observations
Explore results →