Software Engineering
SWE-bench-Live
Released coding-agent attempts on real repository issues across Python, multilingual and Windows tracks.
1,517items
61subjects
MIT for the official task datasets and evaluation harness; no explicit license is present in the captured community submission repository.license
software_engineeringdomain
tool_usedomain
textmodality
item-level responses released
Saturation status: Yes
Response matrix
Loading response matrix…
Correct (1)Incorrect (0)Unobserved
Scale: 1 = correct · 0 = incorrect