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.

942 models · page 4 of 20

OpenAI

GPT-4o (May 2024)

10 benchmarks · 13 observations

Explore results →

Microsoft

phi-3-medium 14B

12 benchmarks · 15 observations

Explore results →

Microsoft

phi-3-mini 3.8B

11 benchmarks · 14 observations

Explore results →

Microsoft

phi-3-small 7.4B

10 benchmarks · 10 observations

Explore results →

Microsoft

WizardLM-2 8x22B

3 benchmarks · 3 observations

Explore results →

OpenAI

GPT-4 Turbo (Apr 2024)

9 benchmarks · 12 observations

Explore results →

NVIDIA

Nemotron 4 15B

8 benchmarks · 8 observations

Explore results →

NVIDIA

StarCoder 2 3B

5 benchmarks · 5 observations

Explore results →

Google

Gemma 7B

22 benchmarks · 48 observations

Explore results →

Google

Gemma 2B

13 benchmarks · 13 observations

Explore results →

NVIDIA

StarCoder 2 15B

5 benchmarks · 5 observations

Explore results →

NVIDIA

StarCoder 2 7B

5 benchmarks · 5 observations

Explore results →

Google

Gemini 1.5 Pro (Feb 2024)

4 benchmarks · 5 observations

Explore results →

OpenAI

GPT-3.5 Turbo (Jan 2024)

10 benchmarks · 10 observations

Explore results →

OpenAI

GPT-4 Turbo (Nov 2023)

7 benchmarks · 7 observations

Explore results →

OpenAI

GPT-4 Turbo Preview (January 2024)

3 benchmarks · 4 observations

Explore results →

Google

Gemini 1.0 Pro Vision

1 benchmarks · 1 observations

Explore results →

Google

Gemini 1.0 Pro

9 benchmarks · 16 observations

Explore results →

Microsoft

Phi-2

10 benchmarks · 14 observations

Explore results →

OpenAI

GPT-3.5 Turbo (Nov 2023)

12 benchmarks · 12 observations

Explore results →

OpenAI

GPT-4V

11 benchmarks · 17 observations

Explore results →

OpenAI

GPT-4 Turbo Preview (Nov 2023)

3 benchmarks · 4 observations

Explore results →

OpenAI

GPT-3.5 Turbo Instruct

1 benchmarks · 2 observations

Explore results →

Microsoft

Phi-1.5

6 benchmarks · 6 observations

Explore results →

OpenAI

GPT-4 (Jun 2023)

12 benchmarks · 12 observations

Explore results →

OpenAI

GPT-3.5 Turbo (June 2023)

5 benchmarks · 6 observations

Explore results →

OpenAI

GPT-3.5 Turbo (Jun 2023)

1 benchmarks · 1 observations

Explore results →

OpenAI

Cerebras-GPT-13B

8 benchmarks · 9 observations

Explore results →

OpenAI

GPT-4 (Mar 2023)

8 benchmarks · 13 observations

Explore results →

OpenAI

davinci-003

2 benchmarks · 7 observations

Explore results →

OpenAI

GPT-NeoX-20B

8 benchmarks · 10 observations

Explore results →

Google

PaLM (540B)

12 benchmarks · 31 observations

Explore results →

OpenAI

davinci-002

5 benchmarks · 6 observations

Explore results →

OpenAI

InstructGPT 175B

12 benchmarks · 66 observations

Explore results →

OpenAI

InstructGPT 1.3B

2 benchmarks · 2 observations

Explore results →

OpenAI

InstructGPT 350M

2 benchmarks · 2 observations

Explore results →

OpenAI

InstructGPT 6B

2 benchmarks · 2 observations

Explore results →

Google

GLaM

4 benchmarks · 12 observations

Explore results →

NVIDIA

Megatron-Turing NLG 530B

5 benchmarks · 19 observations

Explore results →

OpenAI

GPT-J-6B

11 benchmarks · 15 observations

Explore results →

OpenAI

GPT-Neo-2.7B

8 benchmarks · 8 observations

Explore results →

OpenAI

GPT-3

4 benchmarks · 10 observations

Explore results →

OpenAI

GPT-3 6.7B

2 benchmarks · 2 observations

Explore results →

OpenAI

GPT-3 XL (babbage)

2 benchmarks · 2 observations

Explore results →

OpenAI

GPT-3 175B (davinci)

3 benchmarks · 4 observations

Explore results →

OpenAI

GPT-2 (1.5B)

7 benchmarks · 10 observations

Explore results →

Google

T5 (11B)

4 benchmarks · 5 observations

Explore results →

Google

T5-3B

3 benchmarks · 3 observations

Explore results →