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.
204 models · page 5 of 5
DeepSeek
ReFoRCE + DeepSeek-V3
1 benchmarks · 1 observations
Explore results →DeepSeek
RM-R1-DeepSeek-Distilled-Qwen-14B
1 benchmarks · 1 observations
Explore results →DeepSeek
RM-R1-DeepSeek-Distilled-Qwen-32B
1 benchmarks · 1 observations
Explore results →DeepSeek
RM-R1-DeepSeek-Distilled-Qwen-7B
1 benchmarks · 1 observations
Explore results →DeepSeek
RSL-SQL + DeepSeek-R1 HUST VLR Lab [Cao et al. '24]
1 benchmarks · 1 observations
Explore results →DeepSeek
RSL-SQL + DeepSeek-v2 Anonymous [Cao et al.'24]
1 benchmarks · 1 observations
Explore results →DeepSeek
RSL-SQL + DeepSeek-V3 HUST VLR Lab [Cao et al. '24]
1 benchmarks · 1 observations
Explore results →DeepSeek
Spider-Agent + DeepSeek-R1
1 benchmarks · 2 observations
Explore results →DeepSeek
Spider-Agent + DeepSeek-V3
1 benchmarks · 1 observations
Explore results →StepFun
step-3.7-flash-medium
1 benchmarks · 1 observations
Explore results →StepFun
stepfun/step-3.5-flash@reasoning=minimal
1 benchmarks · 4 observations
Explore results →StepFun
stepfun/step-3.5-flash@reasoning=xhigh
1 benchmarks · 4 observations
Explore results →