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.
354 models · page 4 of 8
gemini-1.5-flash-latest
2 benchmarks · 2 observations
Explore results →gemini-2.5-flash (Thinking)*
2 benchmarks · 2 observations
Explore results →gemini-2.5-pro (Thinking)*
2 benchmarks · 2 observations
Explore results →Gemini-3.0 Pro
2 benchmarks · 3 observations
Explore results →Gemini-Pro-Vision
2 benchmarks · 4 observations
Explore results →Gemma-2-9b-it
2 benchmarks · 4 observations
Explore results →Gemma-7B-Instruct
2 benchmarks · 4 observations
Explore results →PaliGemma-mix-3B
2 benchmarks · 3 observations
Explore results →Microsoft
Phi-3-medium-128k-instruct
2 benchmarks · 55 observations
Explore results →Microsoft
Phi-3-mini-128k-instruct
2 benchmarks · 55 observations
Explore results →Microsoft
Phi3.5-Vision-4B
2 benchmarks · 3 observations
Explore results →Microsoft
wizardlm-13b / v1.2
2 benchmarks · 3 observations
Explore results →CHASE-SQL + Gemini Google Cloud [Pourreza et al. '24]
1 benchmarks · 1 observations
Explore results →CodeGemma-7B-Instruct
1 benchmarks · 2 observations
Explore results →Flan-PaLM (3-shot) Google Research & DeepMind (Singhal et al. 2022)
1 benchmarks · 1 observations
Explore results →Gemini 1.0 Pro 002
1 benchmarks · 1 observations
Explore results →Gemini 1.5 Flash 08/27
1 benchmarks · 1 observations
Explore results →Gemini 1.5 Pro 08/27
1 benchmarks · 1 observations
Explore results →Gemini 2.0 Flash (February 2025)
1 benchmarks · 1 observations
Explore results →Gemini 2.0 Flash Lite Preview
1 benchmarks · 1 observations
Explore results →Gemini 2.0 Flash Reasoning
1 benchmarks · 4 observations
Explore results →Gemini 2.0 Flash Thinking (January 2025)
1 benchmarks · 1 observations
Explore results →Gemini 2.0 Flash Thinking Experimental
1 benchmarks · 1 observations
Explore results →Gemini 2.0 Pro Experimental (Feb 2025)
1 benchmarks · 1 observations
Explore results →Gemini 2.0 Pro Experimental (February 2025)
1 benchmarks · 1 observations
Explore results →Gemini 2.5 Flash (April 2025)
1 benchmarks · 1 observations
Explore results →Gemini 2.5 Flash Preview (9/25) (Thinking) (Terminus 2)
1 benchmarks · 1 observations
Explore results →Gemini 2.5 Pro (03-25)
1 benchmarks · 1 observations
Explore results →Gemini 2.5 Pro (06-05)
1 benchmarks · 1 observations
Explore results →Gemini 2.5 Pro (Terminus 2)
1 benchmarks · 1 observations
Explore results →Gemini 2.5 Pro Preview
1 benchmarks · 1 observations
Explore results →Gemini 2.5 Pro Preview 05-06
1 benchmarks · 1 observations
Explore results →Gemini 3 Deep Think (2/26)
1 benchmarks · 1 observations
Explore results →Gemini 3 Pro (11/25) (Terminus 2)
1 benchmarks · 1 observations
Explore results →Gemini 3.0 Flash
1 benchmarks · 1 observations
Explore results →Gemini 3.1 Pro Custom Tools
1 benchmarks · 1 observations
Explore results →Gemini 3.5 Flash (Gemini CLI)
1 benchmarks · 1 observations
Explore results →Gemini 3.5 Flash / Exa
1 benchmarks · 1 observations
Explore results →Gemini 3.5 Flash / Native
1 benchmarks · 1 observations
Explore results →Gemini 3.5 Flash Lite (Terminus 2)
1 benchmarks · 1 observations
Explore results →Gemini 3.6 Flash (Terminus 2)
1 benchmarks · 1 observations
Explore results →Gemini 3.7 Flash (Terminus 2)
1 benchmarks · 1 observations
Explore results →Gemini 3.8 Flash (Terminus 2)
1 benchmarks · 1 observations
Explore results →Gemini 3.8 Flash / Antigravity
1 benchmarks · 1 observations
Explore results →Gemini 4 Argon (Terminus 2)
1 benchmarks · 1 observations
Explore results →Gemini 4 Carbon
1 benchmarks · 54 observations
Explore results →Gemini Argon 4
1 benchmarks · 1 observations
Explore results →Gemini Pro v1.5
1 benchmarks · 1 observations
Explore results →