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 11 of 14
OpenAI
o1-preview / AIDE
1 benchmarks · 1 observations
Explore results →OpenAI
o1-preview / R&D-Agent
1 benchmarks · 1 observations
Explore results →OpenAI
O1-preview-0912
1 benchmarks · 8 observations
Explore results →OpenAI
O1-preview-2024-09-12 (OpenAI, 2024b)
1 benchmarks · 1 observations
Explore results →OpenAI
o3 (high) + gpt-4.1
1 benchmarks · 1 observations
Explore results →OpenAI
o3 / AIRA-dojo
1 benchmarks · 1 observations
Explore results →OpenAI
o3 + GPT-4.1 / R&D-Agent
1 benchmarks · 1 observations
Explore results →OpenAI
o3-2025-04-16-high
1 benchmarks · 1 observations
Explore results →OpenAI
o3-2025-04-16-reasoning-high
1 benchmarks · 1 observations
Explore results →OpenAI
o3-mini-2025-01-31-high
1 benchmarks · 1 observations
Explore results →OpenAI
o3-mini-2025-01-31-medium
1 benchmarks · 1 observations
Explore results →OpenAI
o3-preview (Low)*
1 benchmarks · 1 observations
Explore results →OpenAI
o3-pro-2025-06-10
1 benchmarks · 1 observations
Explore results →OpenAI
o3-pro-2025-06-10-reasoning-high
1 benchmarks · 1 observations
Explore results →OpenAI
o4-mini-2025-04-16-medium
1 benchmarks · 1 observations
Explore results →OpenAI
o4-mini-2025-04-16-reasoning-high
1 benchmarks · 1 observations
Explore results →OpenAI
Open-Flamingo (GPT Eval)
1 benchmarks · 3 observations
Explore results →OpenAI
OpenAI ADA
1 benchmarks · 1 observations
Explore results →OpenAI
OpenAI Codex (N/A)
1 benchmarks · 2 observations
Explore results →OpenAI
OpenAI Curie
1 benchmarks · 1 observations
Explore results →OpenAI
OpenAI DeepResearch
1 benchmarks · 1 observations
Explore results →OpenAI
OpenAI gpt-3.5-0613
1 benchmarks · 1 observations
Explore results →OpenAI
OpenAI gpt-3.5-turbo-0301
1 benchmarks · 1 observations
Explore results →OpenAI
OpenAI gpt-4-0314
1 benchmarks · 1 observations
Explore results →OpenAI
OpenAI gpt-4-0613
1 benchmarks · 1 observations
Explore results →OpenAI
OpenAI internal research model / undisclosed
1 benchmarks · 1 observations
Explore results →OpenAI
OpenAI o3-mini
1 benchmarks · 1 observations
Explore results →OpenAI
OpenAI Operator
1 benchmarks · 1 observations
Explore results →OpenAI
OpenAI text-davinci-001
1 benchmarks · 1 observations
Explore results →OpenAI
OpenAI text-davinci-002
1 benchmarks · 1 observations
Explore results →OpenAI
OpenAI text-davinci-003
1 benchmarks · 1 observations
Explore results →OpenAI
OpenAI-O1-mini-128k
1 benchmarks · 1 observations
Explore results →OpenAI
OpenAI-o3-mini-high
1 benchmarks · 24 observations
Explore results →OpenAI
OpenAI-o3-mini-medium†
1 benchmarks · 4 observations
Explore results →OpenAI
openai/chatgpt-4o-latest
1 benchmarks · 1 observations
Explore results →OpenAI
openai/gpt-4.1@reasoning=default
1 benchmarks · 4 observations
Explore results →OpenAI
openai/gpt-4o-2024-08-06@reasoning=default
1 benchmarks · 4 observations
Explore results →OpenAI
openai/gpt-4o-mini-2024-07-18@reasoning=default
1 benchmarks · 4 observations
Explore results →OpenAI
openai/gpt-4o-mini@reasoning=default
1 benchmarks · 2 observations
Explore results →OpenAI
openai/gpt-4o@reasoning=default
1 benchmarks · 2 observations
Explore results →OpenAI
openai/gpt-5-chat@reasoning=default
1 benchmarks · 4 observations
Explore results →OpenAI
openai/gpt-5-codex@reasoning=default
1 benchmarks · 4 observations
Explore results →OpenAI
openai/gpt-5.1-chat@reasoning=default
1 benchmarks · 4 observations
Explore results →OpenAI
openai/gpt-5.1-codex@reasoning=default
1 benchmarks · 4 observations
Explore results →OpenAI
openai/gpt-5.1@reasoning=default
1 benchmarks · 4 observations
Explore results →OpenAI
openai/gpt-5.2-chat@reasoning=default
1 benchmarks · 4 observations
Explore results →OpenAI
openai/gpt-5.2-codex@reasoning=high
1 benchmarks · 4 observations
Explore results →OpenAI
openai/gpt-5.2-codex@reasoning=low
1 benchmarks · 4 observations
Explore results →