Model results

SWE-bench Live

Choose a shared evaluation protocol to compare model scores. Versions, sources and configurations stay separate.

Atlas snapshot captured 10/19/2026, 10:20:28 AM UTC. This is an import timestamp, not the evaluation date. Coverage may be incomplete.

Official source

← All evaluation groups

SWE-bench Live

Source: SWE-bench Live (reviewed publisher results)
Version: windows-0605
Measurement date: 2026-06-06
Metric: % · Higher is better
Evaluation scope: windows split; 16/60 resolved; system Win-agent + GPT-5.5 (Medium); submission evidence https://github.com/SWE-bench-Live/submission/tree/main/submissions/windows/win-agent/gpt-5.5-medium; publisher verified=True

Positions are withheld because at least one result lacks explicit independent provenance or a documented evaluation scope. Missing metadata is shown as unreported; matching imported metadata is not independent verification of the protocol.

GPT-5.5
openai/gpt-5.5-20260423
26.666667%
View modelEvidence aggregated