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.

187 models · page 2 of 4

NVIDIA

Megatron-Turing NLG 530B

5 benchmarks · 19 observations

Explore results →

Mistral

Mistral (7B)

20 benchmarks · 36 observations

Explore results →

NVIDIA

Nemotron 3.5 Lightning

13 benchmarks · 13 observations

Explore results →

Mistral

Mistral Small 3.1 (03/2025)

11 benchmarks · 12 observations

Explore results →

Mistral

Magistral Medium 1.2 (09/2025)

10 benchmarks · 11 observations

Explore results →

Mistral

Magistral Small 1.2 (09/2025)

10 benchmarks · 11 observations

Explore results →

Mistral

Mistral Medium 3.1 (05/2025)

10 benchmarks · 11 observations

Explore results →

Mistral

Mistral-7B-Instruct-v0.2

9 benchmarks · 51 observations

Explore results →

Mistral

Mixtral-8x7B-Instruct-v0.1

9 benchmarks · 51 observations

Explore results →

Mistral

Mistral Large (11/2024)

8 benchmarks · 8 observations

Explore results →

Mistral

Mistral Small (02/2024)

8 benchmarks · 8 observations

Explore results →

Mistral

Mixtral 8×22B

8 benchmarks · 8 observations

Explore results →

Mistral

Mixtral-8x22B-Instruct-v0.1

7 benchmarks · 54 observations

Explore results →

NVIDIA

Llama 3.3 Nemotron Super

6 benchmarks · 12 observations

Explore results →

Mistral

Codestral-22B-v0.1

4 benchmarks · 4 observations

Explore results →

Mistral

Dolphin-2.6-mixtral-8x7b

4 benchmarks · 4 observations

Explore results →

Mistral

Mistral Large 2411

4 benchmarks · 4 observations

Explore results →

NVIDIA

Nemotron 4 340B

4 benchmarks · 4 observations

Explore results →

Mistral

Mistral Large (Mar 2024)

3 benchmarks · 3 observations

Explore results →

Mistral

Mistral-7B-Instruct-v0.3

3 benchmarks · 6 observations

Explore results →

Mistral

Mistral-Nemo-Instruct-2407

3 benchmarks · 11 observations

Explore results →

Mistral

MistralHermes-CodePro-7B-v1

3 benchmarks · 3 observations

Explore results →

Mistral

speechless-code-mistral-7B-v1.0

3 benchmarks · 3 observations

Explore results →

Mistral

Devstral 2

2 benchmarks · 2 observations

Explore results →

Mistral

MetaMath-Mistral

2 benchmarks · 2 observations

Explore results →

Mistral

Ministral-8B-Instruct-2410

2 benchmarks · 4 observations

Explore results →

Mistral

Mistral / Small

2 benchmarks · 4 observations

Explore results →

Mistral

Mistral Large 2 (2407)

2 benchmarks · 7 observations

Explore results →

Mistral

Mistral Medium 3.5 (Terminus 2)

2 benchmarks · 2 observations

Explore results →

Mistral

Mistral-7B-Instruct

2 benchmarks · 2 observations

Explore results →

Mistral

Mistral-codealpaca-7B

2 benchmarks · 2 observations

Explore results →

Mistral

Mistral-Large-2

2 benchmarks · 3 observations

Explore results →

Mistral

mistral-medium-latest

2 benchmarks · 2 observations

Explore results →

Mistral

Mistral-v0.1-7b

2 benchmarks · 9 observations

Explore results →

Mistral

Mixtral-8x7B-Inst

2 benchmarks · 19 observations

Explore results →

Mistral

Mixtral-8x7b-Instruct

2 benchmarks · 3 observations

Explore results →

Mistral

RLHFlow-PRM-Mistral-8B

2 benchmarks · 2 observations

Explore results →

Mistral

activation-beacon-mistral-7b

1 benchmarks · 54 observations

Explore results →

Mistral

BioMistral

1 benchmarks · 17 observations

Explore results →

Mistral

Codestral 25.01

1 benchmarks · 1 observations

Explore results →

Mistral

Codestral-22B-v0.1-Q4 K M

1 benchmarks · 1 observations

Explore results →

Mistral

codestral-2405

1 benchmarks · 1 observations

Explore results →

Mistral

codestral-2508

1 benchmarks · 1 observations

Explore results →

Mistral

codestral:22b-v0.1-q8 0

1 benchmarks · 1 observations

Explore results →

NVIDIA

GatorTronGPT University of Florida & NVIDIA (Peng et al. 2023)

1 benchmarks · 1 observations

Explore results →

Mistral

HarmB-Mistral

1 benchmarks · 2 observations

Explore results →

Mistral

InternLM2-math-plus-mixtral8*22B

1 benchmarks · 1 observations

Explore results →

NVIDIA

Llama 3.1-Nemotron-70B-Instruct-HF

1 benchmarks · 1 observations

Explore results →