Skip to content
AI Atlas
BenchmarkActivecategory · coding

SWE-bench (full test split)

swebench.com

resolve real GitHub issues (2,294 instances)

quality57

Updated 25 min ago · first seen 11 Sept 2026

bench_01M293SPG8K6FQ2ZZD4YS1NK9R

Metric
resolved · %
Direction
Results
0
Leader

Leaderboard 0 current results

Select models with +, then open Compare.

No benchmark results recorded

Results appear when a tier 1–3 source publishes them; we never copy scores without a source.