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.
636 models · page 12 of 14
OpenAI
openai/gpt-5.2-codex@reasoning=xhigh
1 benchmarks · 4 observations
Explore results →OpenAI
openai/gpt-5.2@reasoning=high
1 benchmarks · 4 observations
Explore results →OpenAI
openai/gpt-5.2@reasoning=none
1 benchmarks · 4 observations
Explore results →OpenAI
openai/gpt-5.3-chat@reasoning=default
1 benchmarks · 4 observations
Explore results →OpenAI
openai/gpt-5.3-codex@reasoning=high
1 benchmarks · 4 observations
Explore results →OpenAI
openai/gpt-5.3-codex@reasoning=low
1 benchmarks · 4 observations
Explore results →OpenAI
openai/gpt-5.3-codex@reasoning=xhigh
1 benchmarks · 4 observations
Explore results →OpenAI
openai/gpt-5.4-mini@reasoning=high
1 benchmarks · 4 observations
Explore results →OpenAI
openai/gpt-5.4-mini@reasoning=none
1 benchmarks · 4 observations
Explore results →OpenAI
openai/gpt-5.4-mini@reasoning=xhigh
1 benchmarks · 4 observations
Explore results →OpenAI
openai/gpt-5.4-nano@reasoning=high
1 benchmarks · 4 observations
Explore results →OpenAI
openai/gpt-5.4-nano@reasoning=none
1 benchmarks · 4 observations
Explore results →OpenAI
openai/gpt-5.4-nano@reasoning=xhigh
1 benchmarks · 4 observations
Explore results →OpenAI
openai/gpt-5.4@reasoning=none
1 benchmarks · 4 observations
Explore results →OpenAI
openai/gpt-5.4@reasoning=xhigh
1 benchmarks · 4 observations
Explore results →OpenAI
openai/gpt-5.5-chat@reasoning=default
1 benchmarks · 4 observations
Explore results →OpenAI
openai/gpt-5.5-pro@reasoning=medium
1 benchmarks · 2 observations
Explore results →OpenAI
openai/gpt-5.5-pro@reasoning=xhigh
1 benchmarks · 2 observations
Explore results →OpenAI
openai/gpt-5.5@reasoning=low
1 benchmarks · 2 observations
Explore results →OpenAI
openai/gpt-5.5@reasoning=none
1 benchmarks · 4 observations
Explore results →OpenAI
openai/gpt-5.5@reasoning=xhigh
1 benchmarks · 2 observations
Explore results →OpenAI
openai/gpt-5.6-luna@reasoning=low
1 benchmarks · 4 observations
Explore results →OpenAI
openai/gpt-5.6-luna@reasoning=max
1 benchmarks · 4 observations
Explore results →OpenAI
openai/gpt-5.6-sol@reasoning=low
1 benchmarks · 4 observations
Explore results →OpenAI
openai/gpt-5.6-sol@reasoning=max
1 benchmarks · 4 observations
Explore results →OpenAI
openai/gpt-5.6-terra@reasoning=low
1 benchmarks · 4 observations
Explore results →OpenAI
openai/gpt-5.6-terra@reasoning=max
1 benchmarks · 4 observations
Explore results →OpenAI
openai/gpt-5@reasoning=default
1 benchmarks · 4 observations
Explore results →OpenAI
openai/gpt-6-astra@reasoning=low
1 benchmarks · 4 observations
Explore results →OpenAI
openai/gpt-6-astra@reasoning=max
1 benchmarks · 4 observations
Explore results →OpenAI
openai/gpt-6-luna-pro@reasoning=max
1 benchmarks · 4 observations
Explore results →OpenAI
openai/gpt-6-luna-pro@reasoning=none
1 benchmarks · 4 observations
Explore results →OpenAI
openai/gpt-6-luna@reasoning=max
1 benchmarks · 4 observations
Explore results →OpenAI
openai/gpt-6-luna@reasoning=none
1 benchmarks · 4 observations
Explore results →OpenAI
openai/gpt-6-sol-pro@reasoning=max
1 benchmarks · 4 observations
Explore results →OpenAI
openai/gpt-6-sol-pro@reasoning=none
1 benchmarks · 4 observations
Explore results →OpenAI
openai/gpt-6-sol@reasoning=max
1 benchmarks · 4 observations
Explore results →OpenAI
openai/gpt-6-sol@reasoning=none
1 benchmarks · 4 observations
Explore results →OpenAI
openai/gpt-6.1-sol@reasoning=low
1 benchmarks · 2 observations
Explore results →OpenAI
openai/gpt-6.1-sol@reasoning=max
1 benchmarks · 2 observations
Explore results →OpenAI
openai/gpt-oss-120b@reasoning=high
1 benchmarks · 4 observations
Explore results →OpenAI
openai/gpt-oss-120b@reasoning=low
1 benchmarks · 4 observations
Explore results →OpenAI
openai/o1-preview-2024-09-12
1 benchmarks · 1 observations
Explore results →OpenAI
openai/o3@reasoning=default
1 benchmarks · 2 observations
Explore results →OpenAI
openai/o3@reasoning=low
1 benchmarks · 2 observations
Explore results →OpenAI
openai/o4-mini@reasoning=high
1 benchmarks · 4 observations
Explore results →OpenAI
openai/o4-mini@reasoning=low
1 benchmarks · 4 observations
Explore results →OpenAI
OpenSearch-SQL, v2 + GPT-4o Alibaba Cloud [Xiangjin Xie et al. '25]
1 benchmarks · 1 observations
Explore results →