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.
3,335 models · page 9 of 70
Gemma 3 12B
8 benchmarks · 8 observations
Explore results →Gemma 3 4B
6 benchmarks · 6 observations
Explore results →Gemma 3 1B
2 benchmarks · 2 observations
Explore results →Reported model
computer-use-preview-2025-03-11
1 benchmarks · 3 observations
Explore results →Reka AI
Reka Flash 3
1 benchmarks · 1 observations
Explore results →Qwen
QwQ-32B
8 benchmarks · 9 observations
Explore results →OpenAI
GPT-4.5 Preview (Feb 2025)
15 benchmarks · 15 observations
Explore results →OpenAI
GPT-4.5
2 benchmarks · 5 observations
Explore results →Microsoft
Phi-4 Mini
2 benchmarks · 2 observations
Explore results →Anthropic
Claude 3.7 Sonnet
45 benchmarks · 130 observations
Explore results →xAI
Grok 3 mini Reasoning
10 benchmarks · 21 observations
Explore results →Gemini 2.0 Flash (Feb 2025)
14 benchmarks · 14 observations
Explore results →Gemini 2.0 Pro Exp (Feb 2025)
6 benchmarks · 6 observations
Explore results →Gemini 2.0 Flash-Lite
3 benchmarks · 4 observations
Explore results →Gemini 2.0 Pro
2 benchmarks · 2 observations
Explore results →OpenAI
o3-mini
46 benchmarks · 76 observations
Explore results →Mistral
Mistral Small 3
4 benchmarks · 6 observations
Explore results →OpenAI
GPT-4o (Jan 2025)
2 benchmarks · 2 observations
Explore results →Qwen
Qwen2.5 Max
10 benchmarks · 10 observations
Explore results →Qwen
Qwen Plus (Jan 2025)
3 benchmarks · 3 observations
Explore results →Gemini 2.0 Flash Thinking Exp
11 benchmarks · 11 observations
Explore results →Gemini 2.0 Flash Thinking (Jan 2025)
1 benchmarks · 1 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 →Qwen
LLaVA-Video-7B-Qwen2-TPO
1 benchmarks · 1 observations
Explore results →Mistral
Codestral
2 benchmarks · 4 observations
Explore results →Reported model
MiniCPM-o-2 6
1 benchmarks · 1 observations
Explore results →Qwen
VideoChat-Flash-Qwen2-7B res448
1 benchmarks · 1 observations
Explore results →Tsinghua University,University of Illinois Urbana-Champaign (UIUC),Shanghai AI Lab,Peking University,Shanghai Jiao Tong University,CUHK Shenzhen Research Institute
Eurus-2-7B-PRIME
1 benchmarks · 1 observations
Explore results →AI2
OLMo 2 Furious 13B
1 benchmarks · 1 observations
Explore results →DeepSeek
DeepSeek V3
45 benchmarks · 84 observations
Explore results →Reported model
VITA-1.5
1 benchmarks · 1 observations
Explore results →OpenAI
o1
44 benchmarks · 71 observations
Explore results →xAI
Grok 2 (Dec 2024)
10 benchmarks · 10 observations
Explore results →Microsoft
Phi-4
9 benchmarks · 11 observations
Explore results →Gemini 2.0 Flash (Dec 2024)
6 benchmarks · 9 observations
Explore results →NVIDIA
NVILA 8B
2 benchmarks · 2 observations
Explore results →Meta
Llama 3.3 70B
16 benchmarks · 17 observations
Explore results →Shanghai AI Lab,SenseTime,Tsinghua University,Nanjing University,Fudan University,Chinese University of Hong Kong (CUHK),Shanghai Jiao Tong University
InternVL2 5-78B
2 benchmarks · 2 observations
Explore results →Amazon
Amazon Nova Pro
5 benchmarks · 5 observations
Explore results →Amazon
Amazon Nova Lite
3 benchmarks · 3 observations
Explore results →Amazon
Amazon Nova Micro
2 benchmarks · 2 observations
Explore results →Prime Intellect,Hugging Face,Arcee AI
INTELLECT-1
7 benchmarks · 7 observations
Explore results →Qwen
QwQ-32B-Preview
5 benchmarks · 7 observations
Explore results →Reported model
mPLUG-Owl3-7B-241101
2 benchmarks · 2 observations
Explore results →