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.
1,221 models · page 1 of 26
InclusionAI
Ling 3.1 Flash 1019
12 benchmarks · 12 observations
Explore results →Reflection
Beam 1.0
35 benchmarks · 41 observations
Explore results →NVIDIA
Nemotron 3.5 Super VL
19 benchmarks · 23 observations
Explore results →Mistral
Mistral Large 4
36 benchmarks · 40 observations
Explore results →Mistral
Mistral Large 4 Preview
22 benchmarks · 26 observations
Explore results →Mistral
Mistral Large 4 (unknown)
6 benchmarks · 6 observations
Explore results →InclusionAI
Ling-3.0-flash-Fin
13 benchmarks · 13 observations
Explore results →Cognition
SWE-2
1 benchmarks · 1 observations
Explore results →Inception Labs
Mercury 2.5 (unknown)
3 benchmarks · 3 observations
Explore results →Apodex
Apodex 1.1
1 benchmarks · 1 observations
Explore results →Tencent
Tencent Hy4 preview (unknown)
1 benchmarks · 1 observations
Explore results →Thinking Machines
Inkling Small
3 benchmarks · 3 observations
Explore results →Thinking Machines
Inkling
29 benchmarks · 86 observations
Explore results →Reported model
SWE-1.7
1 benchmarks · 2 observations
Explore results →NVIDIA
Nemotron 3 Ultra
27 benchmarks · 28 observations
Explore results →NVIDIA
Nemotron 3 Ultra 550B A55B (Reasoning)
3 benchmarks · 3 observations
Explore results →Cursor
Composer 2.5
2 benchmarks · 3 observations
Explore results →Ant Group
Ring-2.6-1T
2 benchmarks · 2 observations
Explore results →China Mobile
JT-35B-Flash
1 benchmarks · 1 observations
Explore results →IBM
Granite 4.1 30B
2 benchmarks · 2 observations
Explore results →Mistral
Mistral Medium 3.5
28 benchmarks · 30 observations
Explore results →Poolside
Laguna M.1
18 benchmarks · 18 observations
Explore results →Poolside
Laguna XS.2
17 benchmarks · 17 observations
Explore results →Reported model
SWE-1.6
1 benchmarks · 2 observations
Explore results →KwaiKAT
KAT Coder Pro V2
1 benchmarks · 1 observations
Explore results →NVIDIA
Nemotron Cascade 2 30B A3B
1 benchmarks · 1 observations
Explore results →Mistral
Mistral Small 4
4 benchmarks · 4 observations
Explore results →NVIDIA
Nemotron 3 Super
4 benchmarks · 4 observations
Explore results →Inception Labs
Mercury 2
5 benchmarks · 5 observations
Explore results →Upstage
Solar Pro 3
2 benchmarks · 2 observations
Explore results →LG AI Research
K-EXAONE (Reasoning)
1 benchmarks · 1 observations
Explore results →NVIDIA
Nemotron 3 Nano 30B A3B (Reasoning)
1 benchmarks · 1 observations
Explore results →Mistral
Devstral Small 2
3 benchmarks · 3 observations
Explore results →Mistral
Mistral Large 3
20 benchmarks · 21 observations
Explore results →ServiceNow
Apriel-v1.6-15B-Thinker
1 benchmarks · 1 observations
Explore results →Deep Cogito
Cogito v2.1 (671B)
2 benchmarks · 2 observations
Explore results →Deep Cogito
Cogito v2.1 (Reasoning)
1 benchmarks · 1 observations
Explore results →Baidu
ERNIE 5.0 Thinking Preview
2 benchmarks · 2 observations
Explore results →KwaiKAT
KAT-Coder-Pro V1
1 benchmarks · 1 observations
Explore results →Reported model
granite-4.0-1b
2 benchmarks · 2 observations
Explore results →Reported model
granite-4.0-350m
2 benchmarks · 2 observations
Explore results →Reported model
granite-4.0-micro
2 benchmarks · 2 observations
Explore results →Mistral
Magistral Small 1.2
5 benchmarks · 5 observations
Explore results →Mistral
Magistral Medium 1.2
2 benchmarks · 2 observations
Explore results →NVIDIA
nemotron-nano-9b-v2
1 benchmarks · 1 observations
Explore results →Mistral
Mistral Medium 3.1
6 benchmarks · 6 observations
Explore results →NVIDIA
Llama Nemotron Super 49B v1.5 (Reasoning)
1 benchmarks · 1 observations
Explore results →LG AI Research
EXAONE 4.0 32B (Reasoning)
1 benchmarks · 1 observations
Explore results →