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.
225 models · page 4 of 5
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 →DeepSeek
DeepSeek-Math-RL
1 benchmarks · 2 observations
Explore results →DeepSeek
DeepSeek-MOE-16B-Chat
1 benchmarks · 3 observations
Explore results →DeepSeek
DeepSeek-OCR 2
1 benchmarks · 1 observations
Explore results →DeepSeek
deepseek-r1 / InternAgent
1 benchmarks · 1 observations
Explore results →DeepSeek
deepseek-r1 / ML-Master
1 benchmarks · 1 observations
Explore results →DeepSeek
DeepSeek-R1-Distill-Llama
1 benchmarks · 2 observations
Explore results →DeepSeek
DeepSeek-R1-Distill-Llama-8B
1 benchmarks · 3 observations
Explore results →DeepSeek
DeepSeek-R1-Distill-Qwen
1 benchmarks · 2 observations
Explore results →DeepSeek
DeepSeek-R1-Distill-Qwen-7B
1 benchmarks · 3 observations
Explore results →DeepSeek
DeepSeek-R1-Zero
1 benchmarks · 1 observations
Explore results →DeepSeek
deepseek-vl-7B
1 benchmarks · 1 observations
Explore results →DeepSeek
Deepseek-VL[28]
1 benchmarks · 1 observations
Explore results →DeepSeek
deepseek/deepseek-chat@reasoning=default
1 benchmarks · 4 observations
Explore results →DeepSeek
deepseek/deepseek-r1@reasoning=none
1 benchmarks · 4 observations
Explore results →DeepSeek
deepseek/deepseek-r1@reasoning=xhigh
1 benchmarks · 4 observations
Explore results →DeepSeek
deepseek/deepseek-v3.2@reasoning=high
1 benchmarks · 4 observations
Explore results →DeepSeek
deepseek/deepseek-v3.2@reasoning=none
1 benchmarks · 4 observations
Explore results →DeepSeek
deepseek/deepseek-v4-flash-0731@reasoning=none
1 benchmarks · 4 observations
Explore results →DeepSeek
deepseek/deepseek-v4-flash-0731@reasoning=xhigh
1 benchmarks · 4 observations
Explore results →DeepSeek
deepseek/deepseek-v4-flash@reasoning=none
1 benchmarks · 4 observations
Explore results →DeepSeek
deepseek/deepseek-v4-flash@reasoning=xhigh
1 benchmarks · 4 observations
Explore results →DeepSeek
deepseek/deepseek-v4-pro-0813@reasoning=low
1 benchmarks · 4 observations
Explore results →DeepSeek
deepseek/deepseek-v4-pro-0813@reasoning=max
1 benchmarks · 4 observations
Explore results →DeepSeek
deepseek/deepseek-v4-pro@reasoning=none
1 benchmarks · 4 observations
Explore results →DeepSeek
deepseek/deepseek-v4-pro@reasoning=xhigh
1 benchmarks · 4 observations
Explore results →DeepSeek
deepseek/deepseek-v4.1-flash@reasoning=low
1 benchmarks · 4 observations
Explore results →DeepSeek
deepseek/deepseek-v4.1-flash@reasoning=max
1 benchmarks · 4 observations
Explore results →DeepSeek
DTS-SQL + DeepSeek 7B University of Alberta [Pourreza et al. '24]
1 benchmarks · 1 observations
Explore results →Z.ai
GLM-3-6B-128k
1 benchmarks · 1 observations
Explore results →Z.ai
GLM-4-9B-chat-1M
1 benchmarks · 1 observations
Explore results →Z.ai
GLM-4.5-air-fp8†
1 benchmarks · 1 observations
Explore results →Z.ai
GLM-4.6 (Terminus 2)
1 benchmarks · 1 observations
Explore results →Z.ai
GLM-4.7 (Terminus 2)
1 benchmarks · 1 observations
Explore results →Z.ai
GLM-4p7
1 benchmarks · 1 observations
Explore results →Z.ai
GLM-5 (Mini-SWE)
1 benchmarks · 1 observations
Explore results →Z.ai
GLM-5 (Terminus 2)
1 benchmarks · 1 observations
Explore results →Z.ai
GLM-5.2 (Terminus 2)
1 benchmarks · 1 observations
Explore results →Z.ai
GLM-5.2-high
1 benchmarks · 1 observations
Explore results →Z.ai
GLM-5.2-max
1 benchmarks · 1 observations
Explore results →Z.ai
GLM-5.3 (Terminus 2)
1 benchmarks · 1 observations
Explore results →Z.ai
GLM-5.3 Flash (Terminus 2)
1 benchmarks · 1 observations
Explore results →Z.ai
GLM-5.3-flash-high
1 benchmarks · 1 observations
Explore results →Z.ai
GLM-5.3-high
1 benchmarks · 1 observations
Explore results →