Choose a model by scenario
A composite score hides differences. Top three per scenario, with the recorded value for that dimension; click through to each model.
Capability × scenario matrix
Leaderboard →| Scenario | Top three on this dimension | ||
|---|---|---|---|
| Composite tasks Multi-step reasoning, general assistants, consistent baselines | |||
| Science reasoning Graduate science questions, derivations, literature analysis | |||
| Coding & agents Repo-scale edits, CLI tasks, tool use | |||
| Documents Reports, design drafts, structured long text | |||
| Speed Streaming, interactive products, short batch answers | |||
| Value Large batch inference, price-sensitive background jobs | |||
| Context Whole document sets, large codebases, multi-doc comparison | |||
Note: a single-dimension ranking is not an overall win. A cheap model may lead on one metric yet be weak on speed or context; read "watch out for" on the model page before deciding.
Data sources & methodology
Full methodology & sources →Every number on this page comes from published evaluations. We run no tests of our own and accept no vendor-submitted scores. Main sources:
Evaluation data in the wider industry also comes from public datasets, leaderboard platforms and their evaluation harnesses, private in-house sets, production logs and user feedback, and synthetic data. This site's current rankings use only the parts that are public, independently checkable and clearly defined.