QwenLM/qwen-code dsw-eas-full-20260818-r2

on GitHub

Benchmark-Qwen-Ref: v0.21.13

Full end-to-end validation: SWE-bench Verified 500 cases, then Terminal-Bench 2.0 89 cases, with both result sets written back to this Release.

SWE-bench Verified

• Status: QUARANTINED
• Dataset: swe-bench/swe-bench-verified@2; 500/500 completed
• Results: 0 resolved, 0 unresolved, 284 execution errors, 10 infrastructure failures
• Score: not published (non-scoreable or quarantined run)
• Score denominator: valid grader results (0 + 0 = 0)
• Qwen Code: v0.21.13 (d95901597430); model qwen3.7-plus
• Run: pool-ecbfe8aebe6048a1; dispatch workflow: https://github.com/QwenLM/qwen-code/actions/runs/32097894486
• Case trajectories: swe-bench-verified-dsw-eas-full-20260818-r2-trajectories.tar.gz (305 cases)