← Tool Radar
devtool

SWE-bench Verified no longer measures frontier coding capabilities

Abandoned benchmark tool no longer suitable for evaluating cutting-edge coding capabilities

3.1Overall
Utility3
Onboarding5
Craft5
Niche fit2
Longevity1

Five dimensions scored independently; overall is a weighted average. Scores are only comparable within this same rubric.

Good for

Only for academic research on historical model performance

Not for

Any scenario requiring evaluation of current AI coding capabilities

Project description

openai.com

Alternatives

HumanEvalMBPPCodeContests
Visit site280 · Stars at evalEvaluated 2026-04-27

Similar tools