Evaluation & BenchmarksCarlos E. Jimenez, John Yang et al. (Princeton and others)Princeton University
SWE-bench released
AIMade by AIWritten by AI (Claude) from the source below. Check anything important against the source.How it's made
SWE-bench released — 2,294 real GitHub issues. At release, the best model resolved 1.96%
Why it matters
Later became the de facto objective function for coding-agent development
Source — Primary sources first; secondary reports are labelled “Press”
Paperarxiv.orghttps://arxiv.org/abs/2310.06770Added in Week 35, 2026 · See that week
On the map — ⑯ Evaluation line
- Previous stopMMLU
- This record · stopSWE-bench
- Next stopGSM1k