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.
240 models · page 3 of 5
DeepSeek
DeepSeek-Coder-33B-base
2 benchmarks · 2 observations
Explore results →DeepSeek
DeepSeek-Math-7B-Instruct
2 benchmarks · 6 observations
Explore results →DeepSeek
DeepSeek-Math-7B-RL
2 benchmarks · 4 observations
Explore results →DeepSeek
Deepseek-R1-671B
2 benchmarks · 5 observations
Explore results →Microsoft
Phi-3-medium-128k-instruct
2 benchmarks · 55 observations
Explore results →Microsoft
Phi-3-mini-128k-instruct
2 benchmarks · 55 observations
Explore results →Microsoft
Phi3.5-Vision-4B
2 benchmarks · 3 observations
Explore results →DeepSeek
RLHFlow-PRM-Deepseek-8B
2 benchmarks · 2 observations
Explore results →Microsoft
wizardlm-13b / v1.2
2 benchmarks · 3 observations
Explore results →DeepSeek
; $0.476 per task; 398 median tokens per secondTogether AIDeepSeek V4.1 Flash / Baseten
1 benchmarks · 1 observations
Explore results →DeepSeek
; $0.551 per task; 286 median tokens per secondDeepSeek APIMiniMax M3 / Fireworks
1 benchmarks · 1 observations
Explore results →DeepSeek
; $0.587 per task; 316 median tokens per secondBasetenDeepSeek V4.1 Flash / DeepSeek
1 benchmarks · 1 observations
Explore results →DeepSeek
; $1.007 per task; 116 median tokens per secondTogether AIDeepSeek V4.1 Flash / Fireworks
1 benchmarks · 1 observations
Explore results →DeepSeek
AI-DIVE + DeepSeek-V4-Flash S-Core
1 benchmarks · 1 observations
Explore results →DeepSeek
AutoLink + DeepSeek-R1 HUST VLR Lab [Wang et al. '25]
1 benchmarks · 2 observations
Explore results →DeepSeek
DeepSeek
1 benchmarks · 12 observations
Explore results →DeepSeek
DeepSeek (Deep Think)
1 benchmarks · 1 observations
Explore results →DeepSeek
DeepSeek (Standard)
1 benchmarks · 1 observations
Explore results →DeepSeek
DeepSeek Baseline
1 benchmarks · 1 observations
Explore results →DeepSeek
DeepSeek Chat V2 0628
1 benchmarks · 1 observations
Explore results →DeepSeek
DeepSeek Chat V2.5
1 benchmarks · 1 observations
Explore results →DeepSeek
DeepSeek Chat V3 (prev)
1 benchmarks · 1 observations
Explore results →DeepSeek
DeepSeek Coder V2 0724
1 benchmarks · 1 observations
Explore results →DeepSeek
DeepSeek LLM Chat (67B)
1 benchmarks · 1 observations
Explore results →DeepSeek
Deepseek R1 (Jan 2025)
1 benchmarks · 1 observations
Explore results →DeepSeek
DeepSeek V2
1 benchmarks · 2 observations
Explore results →DeepSeek
DeepSeek V2 0628†
1 benchmarks · 1 observations
Explore results →DeepSeek
DeepSeek V2 Lite Instruct
1 benchmarks · 1 observations
Explore results →DeepSeek
DeepSeek V2.5 (DeepSeek-AI, 2024)
1 benchmarks · 1 observations
Explore results →DeepSeek
DeepSeek V2.5 1210
1 benchmarks · 1 observations
Explore results →DeepSeek
DeepSeek V3 (March 2025)
1 benchmarks · 1 observations
Explore results →DeepSeek
DeepSeek V3.1 (Terminus 2)
1 benchmarks · 1 observations
Explore results →DeepSeek
DeepSeek V3.2 (Nonthinking) (Terminus 2)
1 benchmarks · 1 observations
Explore results →DeepSeek
DeepSeek V3.2 (Thinking) (Terminus 2)
1 benchmarks · 1 observations
Explore results →DeepSeek
DeepSeek V3.2 Exp (Chat)
1 benchmarks · 1 observations
Explore results →DeepSeek
DeepSeek V3.2 Exp (Reasoner)
1 benchmarks · 1 observations
Explore results →DeepSeek
DeepSeek V3.2 Speciale / ML-Master 2.0
1 benchmarks · 1 observations
Explore results →DeepSeek
DeepSeek V4 Flash 0731 (Terminus 2)
1 benchmarks · 1 observations
Explore results →DeepSeek
DeepSeek V4 Pro 0813 (Terminus 2)
1 benchmarks · 1 observations
Explore results →DeepSeek
DeepSeek V4.1 Flash (Terminus 2)
1 benchmarks · 1 observations
Explore results →DeepSeek
DeepSeek V4.1 Flash / Together AI
1 benchmarks · 1 observations
Explore results →DeepSeek
DeepSeek-Chat / V2
1 benchmarks · 2 observations
Explore results →DeepSeek
DeepSeek-Coder-base / 1.3B
1 benchmarks · 1 observations
Explore results →DeepSeek
DeepSeek-Coder-base / 33B
1 benchmarks · 1 observations
Explore results →DeepSeek
DeepSeek-Coder-base / 6.7B
1 benchmarks · 1 observations
Explore results →DeepSeek
DeepSeek-Coder-V2
1 benchmarks · 1 observations
Explore results →DeepSeek
DeepSeek-Distilled-Qwen-32B
1 benchmarks · 2 observations
Explore results →DeepSeek
DeepSeek-Math-7B-Base
1 benchmarks · 3 observations
Explore results →