SWE-Bench Pro is Scale AI’s long-horizon software-engineering benchmark, built from harder tasks than SWE-bench and published with a public leaderboard (Scale). It is where the corpus reads coding-agent state of the art once SWE-bench Verified neared saturation: GPT-5.2 Thinking took 55.6% in December, and in February OpenAI’s GPT-5.3-Codex, described as instrumental in creating itself, set a new state of the art.
Benchmark
SWE-Bench Pro
Scale AI's harder successor to SWE-bench, the leaderboard on which GPT-5.2 Thinking and then the self-built GPT-5.3-Codex set state of the art.
Sources
Attribution and reporting linked by this record; links do not imply independent verification.
- Welcome to December 12, 2025 (theinnermostloop.substack.com)
Development timeline
Newest reporting dates first. Reporting dates may differ from event dates.
Cite or correct this record
Suggest a correction — opens a GitHub draft for you to review and submit.