Non-production benchmark prerelease.
Benchmark-Qwen-Ref: v0.20.0-nightly.20260722.b98306b7e
SWE-bench Verified
- Status: QUARANTINED
- Dataset:
swe-bench/swe-bench-verified@2; 500/500 completed - Results: 376 resolved, 116 unresolved, 1 execution errors, 7 infrastructure failures
- Score: not published (run quarantined)
- Qwen Code:
v0.20.0-nightly.20260722.b98306b7e(77115af615fc); modelqwen3.7-max - Run:
pool-9aa9919d5cd841ef; dispatch workflow: https://github.com/QwenLM/qwen-code/actions/runs/30253679705