Coding
SWE-bench Pro
A harder, contamination-resistant successor to SWE-bench Verified, drawn from commercial and copyleft repositories that were never public training data.
SWE-bench Pro is scored as a percentage of questions answered correctly. 1 of the 159 models in this index report a score for it. The highest published figure here is 81.2%, from Claude Fable 5.1.
Reported scores
Top 1 on SWE-bench Pro
Ordered by the figure each maker published. Models that have not reported this benchmark are not listed — an absent score is not a low score.
| # | Model | Published score |
|---|---|---|
| 1 | Claude Fable 5.1Anthropic |
Where these numbers come from
Every score on this page is a published figure, taken from the model's own card, system card, technical report or release post, or from a public leaderboard. CorX Labs did not run these evaluations. Most are self-reported by the lab that built the model, which means they were produced under that lab's own choice of prompt, scaffold and number of attempts — so treat them as a starting point for a shortlist, not as a settled ranking.
A score someone other than the model's maker measured is marked Independent and names its measurer. Those are the stronger numbers on this page — an outside harness has no reason to flatter anyone — and there are not many of them.
Where a figure has not been published, the cell reads Not reported rather than an estimate. Nothing here is inferred, interpolated or guessed. Each model records the month its row was last checked. Full method and caveats.
How to read this score
SWE-bench Pro is the benchmark to read when a model has no SWE-bench Verified figure. Its tasks come from commercial and copyleft repositories that were never in public training data, so a score cannot come from having seen the fix.
Where it is weak
Far fewer models report it, so the field is thin and a high score has less company to be measured against. It is also still an agent benchmark, which means the harness around the model moves the number as much as the model does.