完整端到端验证流程:Release -> Action -> SWE-bench Verified 500 -> SWE Publisher -> Terminal-Bench 2.0 89 -> 同一 Release。
基准测试 Qwen 引用版本:v0.21.2
<!-- qwen-code-dsw-swe-bench-verified:start -->
### SWE-bench 验证集
- 状态:**隔离(QUARANTINED)**
- 数据集:`swe-bench/swe-bench-verified@2`;500/500 已完成
- 结果:8 个已解决,10 个未解决,0 个执行错误,2 个基础设施故障
- 得分:未公布(不可评分或隔离运行)
- 得分分母:有效评分器结果(8 + 10 = 18)
- Qwen Code:`v0.21.2`(`456fc9b02d7e`);模型 `qwen3.7-plus`
- 运行:`pool-8d07476b7e754f28`;调度工作流:https://github.com/QwenLM/qwen-code/actions/runs/31777259958
- 案例轨迹:`swe-bench-verified-dsw-eas-tb-e2e-20260814-r5-trajectories.tar.gz`(21 个案例)
<!-- qwen-code-dsw-swe-bench-verified:end -->
Full end-to-end validation: Release -> Action -> SWE-bench Verified 500 -> SWE Publisher -> Terminal-Bench 2.0 89 -> same Release.\n\nBenchmark-Qwen-Ref: v0.21.2
<!-- qwen-code-dsw-swe-bench-verified:start -->
### SWE-bench Verified
- Status: **QUARANTINED**
- Dataset: `swe-bench/swe-bench-verified@2`; 500/500 completed
- Results: 8 resolved, 10 unresolved, 0 execution errors, 2 infrastructure failures
- Score: not published (non-scoreable or quarantined run)
- Score denominator: valid grader results (8 + 10 = 18)
- Qwen Code: `v0.21.2` (`456fc9b02d7e`); model `qwen3.7-plus`
- Run: `pool-8d07476b7e754f28`; dispatch workflow: https://github.com/QwenLM/qwen-code/actions/runs/31777259958
- Case trajectories: `swe-bench-verified-dsw-eas-tb-e2e-20260814-r5-trajectories.tar.gz` (21 cases)
<!-- qwen-code-dsw-swe-bench-verified:end -->