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.
337 models · page 2 of 8
DeepSeek
DeepSeek R1 0528 (May '25)
3 benchmarks · 3 observations
Explore results →Mistral
Mistral Medium 3
10 benchmarks · 10 observations
Explore results →DeepSeek
DeepSeek V3 (Mar 2025)
15 benchmarks · 16 observations
Explore results →Mistral
Mistral Small 3.1
8 benchmarks · 10 observations
Explore results →Mistral
Mistral Small 3
4 benchmarks · 6 observations
Explore results →DeepSeek
DeepSeek-R1
51 benchmarks · 92 observations
Explore results →DeepSeek
DeepSeek-R1-Distill-Llama-70B
6 benchmarks · 11 observations
Explore results →DeepSeek
DeepSeek-R1-Distill-Qwen-32B
5 benchmarks · 7 observations
Explore results →DeepSeek
DeepSeek-R1-Distill-Qwen-14B
3 benchmarks · 3 observations
Explore results →DeepSeek
DeepSeek-R1-Distill-Qwen-1.5B
2 benchmarks · 2 observations
Explore results →Mistral
Codestral
2 benchmarks · 4 observations
Explore results →DeepSeek
DeepSeek V3
45 benchmarks · 84 observations
Explore results →NVIDIA
NVILA 8B
2 benchmarks · 2 observations
Explore results →Mistral
Mistral Large 2 (Nov 2024)
7 benchmarks · 7 observations
Explore results →Mistral
Pixtral Large
1 benchmarks · 1 observations
Explore results →Mistral
Ministral 3B
5 benchmarks · 5 observations
Explore results →Mistral
Ministral 8B
3 benchmarks · 3 observations
Explore results →Mistral
Pixtral 12B
3 benchmarks · 4 observations
Explore results →Mistral
Mistral Small v24.09
1 benchmarks · 1 observations
Explore results →DeepSeek
DeepSeek V2.5 (Sep 2024)
1 benchmarks · 1 observations
Explore results →Mistral
Mistral Large 2 (Jul 2024)
8 benchmarks · 8 observations
Explore results →Mistral
Mistral NeMo
7 benchmarks · 7 observations
Explore results →DeepSeek
DeepSeek-Coder-V2 236B
3 benchmarks · 4 observations
Explore results →DeepSeek
DeepSeek-Coder-V2-Lite-Base
5 benchmarks · 5 observations
Explore results →DeepSeek
DeepSeek-Coder-V2-Lite-Instruct
2 benchmarks · 2 observations
Explore results →Mistral
Mistral 7B v0.3
6 benchmarks · 8 observations
Explore results →DeepSeek
DeepSeek V2 (MoE-236B, May 2024)
8 benchmarks · 9 observations
Explore results →Mistral
Mixtral 8x22B
12 benchmarks · 14 observations
Explore results →Mistral
Mistral Large
12 benchmarks · 16 observations
Explore results →NVIDIA
Nemotron 4 15B
8 benchmarks · 8 observations
Explore results →Mistral
mistral-small-2402
2 benchmarks · 2 observations
Explore results →NVIDIA
StarCoder 2 3B
5 benchmarks · 5 observations
Explore results →NVIDIA
StarCoder 2 15B
5 benchmarks · 5 observations
Explore results →NVIDIA
StarCoder 2 7B
5 benchmarks · 5 observations
Explore results →Mistral
llava-v1.6-mistral-7b
1 benchmarks · 1 observations
Explore results →Mistral
Mixtral 8x7B
20 benchmarks · 33 observations
Explore results →Mistral
Mistral
3 benchmarks · 30 observations
Explore results →Mistral
Mistral 7B v0.2
3 benchmarks · 3 observations
Explore results →DeepSeek
DeepSeek LLM 67B
3 benchmarks · 3 observations
Explore results →Mistral
video chat2 mistral
1 benchmarks · 1 observations
Explore results →DeepSeek
DeepSeek Coder 1.3B
5 benchmarks · 5 observations
Explore results →DeepSeek
DeepSeek Coder 33B
5 benchmarks · 5 observations
Explore results →DeepSeek
DeepSeek Coder 6.7B
5 benchmarks · 5 observations
Explore results →Mistral
Mistral 7B v0.1
11 benchmarks · 29 observations
Explore results →NVIDIA
Megatron-Turing NLG 530B
5 benchmarks · 19 observations
Explore results →DeepSeek
DeepSeek V4
22 benchmarks · 23 observations
Explore results →Mistral
Mistral (7B)
20 benchmarks · 36 observations
Explore results →NVIDIA
Nemotron 3.5 Lightning
13 benchmarks · 13 observations
Explore results →