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.

581 models · page 2 of 13

Google

Gemini 2.5 Pro

30 benchmarks · 52 observations

Explore results →

Google

Gemini 2.5 Pro (Jun 2025)

22 benchmarks · 33 observations

Explore results →

Google

Gemini 2.5 Pro Preview (Jun 2025)

19 benchmarks · 29 observations

Explore results →

Google

Gemini 2.5 Flash (May 2025)

10 benchmarks · 19 observations

Explore results →

Google

Gemini 2.5 Flash (Reasoning)

1 benchmarks · 1 observations

Explore results →

Google

Gemini 2.5 Pro (May 2025)

1 benchmarks · 1 observations

Explore results →

Google

Gemini 2.5 Pro Preview (May' 25)

1 benchmarks · 1 observations

Explore results →

Google

Gemini 2.5 Flash Preview (Apr 2025)

6 benchmarks · 6 observations

Explore results →

Google

Gemini 2.5 Flash (Apr 2025)

4 benchmarks · 4 observations

Explore results →

Google

Gemini 2.5 Flash Preview (Reasoning)

1 benchmarks · 1 observations

Explore results →

Meta

Llama 4 Maverick

43 benchmarks · 65 observations

Explore results →

Meta

Llama 4 Scout

28 benchmarks · 39 observations

Explore results →

Meta

Llama 4 Maverick (FP8)

4 benchmarks · 4 observations

Explore results →

Google

Gemini 2.5 Pro Preview (Mar 2025)

7 benchmarks · 7 observations

Explore results →

Google

Gemini 2.5 Pro (Mar 2025)

3 benchmarks · 3 observations

Explore results →

Google

Gemini 2.5 Pro Exp (Mar 2025)

10 benchmarks · 10 observations

Explore results →

Google

Gemini 2.5 Pro Preview (Mar' 25)

2 benchmarks · 2 observations

Explore results →

Google

Gemma 3 27B

14 benchmarks · 17 observations

Explore results →

Google

Gemma 3 12B

8 benchmarks · 8 observations

Explore results →

Google

Gemma 3 4B

6 benchmarks · 6 observations

Explore results →

Google

Gemma 3 1B

2 benchmarks · 2 observations

Explore results →

Microsoft

Phi-4 Mini

2 benchmarks · 2 observations

Explore results →

Google

Gemini 2.0 Flash (Feb 2025)

14 benchmarks · 14 observations

Explore results →

Google

Gemini 2.0 Pro Exp (Feb 2025)

6 benchmarks · 6 observations

Explore results →

Google

Gemini 2.0 Flash-Lite

3 benchmarks · 4 observations

Explore results →

Google

Gemini 2.0 Pro

2 benchmarks · 2 observations

Explore results →

Google

Gemini 2.0 Flash Thinking Exp

11 benchmarks · 11 observations

Explore results →

Google

Gemini 2.0 Flash Thinking (Jan 2025)

1 benchmarks · 1 observations

Explore results →

Microsoft

Phi-4

9 benchmarks · 11 observations

Explore results →

Google

Gemini 2.0 Flash (Dec 2024)

6 benchmarks · 9 observations

Explore results →

Meta

Llama 3.3 70B

16 benchmarks · 17 observations

Explore results →

Google

Gemini 1.5 Flash 8B

3 benchmarks · 3 observations

Explore results →

Google

Gemini 1.5 Pro (Sept 2024)

13 benchmarks · 13 observations

Explore results →

Google

Gemini 1.5 Flash (Sep 2024)

11 benchmarks · 11 observations

Explore results →

Meta

Llama 3.2 90B

8 benchmarks · 8 observations

Explore results →

Meta

Llama 3.2 1B

5 benchmarks · 5 observations

Explore results →

Meta

Llama 3.2 3B

3 benchmarks · 3 observations

Explore results →

Meta

Llama 3.2 11B

2 benchmarks · 2 observations

Explore results →

Microsoft

Phi-3.5-MoE

3 benchmarks · 3 observations

Explore results →

Microsoft

Phi-3.5-mini

3 benchmarks · 3 observations

Explore results →

Microsoft

Phi-3.5-vision-instruct

2 benchmarks · 2 observations

Explore results →

Meta

Dracarys2-Llama-3.1-70B-Instruct

1 benchmarks · 1 observations

Explore results →

Meta

Llama 3.1-405B

22 benchmarks · 26 observations

Explore results →

Meta

Llama 3.1-8B

22 benchmarks · 30 observations

Explore results →

Meta

Llama 3.1-70B

19 benchmarks · 22 observations

Explore results →

Google

Gemma 2 9B

12 benchmarks · 12 observations

Explore results →

Google

Gemma 2 27B

10 benchmarks · 10 observations

Explore results →

Meta

Hermes 2 Theta Llama-3 70B

3 benchmarks · 3 observations

Explore results →