Every model, in the open
Sortable by any column, filterable by lab — sourced or blank, never guessed.
All models
Coding score is 0–100 — SWE-bench Verified where published, otherwise a sourced estimate (marked est). Click a row for its benchmarks, sources, and sourced quotes about it. "—" means the figure wasn't publicly sourced. We don't guess.
| Model | Codingscore /100 | Context | Pricein / out · 1M |
|---|