Benchmark-Qwen-Ref: v0.21.13
完整端到端验证：SWE-bench Verified 500，发布回写，随后是 Terminal-Bench 2.0 89 及最终回写。
<!-- qwen-code-dsw-swe-verified:start -->
### SWE-bench Verified
- 状态：**成功（SUCCEEDED）**
- 数据集：`swe-bench/swe-bench-verified@2`；500/500 已完成
- 结果：351 个已解决，141 个未解决，4 个执行错误，4 个基础设施故障
- 得分：**71.34%**
- 得分分母：有效评分结果 (351 + 141 = 492)
- Qwen Code：`v0.21.13` (`d95901597430`)；模型 `qwen3.7-plus`
- 运行池：`pool-669a90b49d8f49e9`；调度工作流：https://github.com/QwenLM/qwen-code/actions/runs/32109866948
- 案例轨迹：`swe-bench-verified-dsw-eas-full-20260818-r3-trajectories.tar.gz`（496 个案例）
<!-- qwen-code-dsw-swe-verified:end -->
<!-- qwen-code-dsw-terminal-bench-2.0:start -->
### Terminal-Bench 2.0
- 状态：**已隔离（QUARANTINED）**
- 数据集：`
[email protected]`；89/89 已完成
- 结果：1 个已解决，37 个未解决，36 个执行错误，15 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：有效评分结果 (1 + 37 = 38)
- Qwen Code：`v0.21.13` (`d95901597430`)；模型 `qwen3.7-plus`
- 运行池：`pool-40646da016a146f8`；调度工作流：https://github.com/QwenLM/qwen-code/actions/runs/32109866948
- 案例轨迹：`terminal-bench-2.0-dsw-eas-full-20260818-r3-trajectories.tar.gz`（44 个案例）
<!-- qwen-code-dsw-terminal-bench-2.0:end -->
Benchmark-Qwen-Ref: v0.21.13
Full end-to-end validation: SWE-bench Verified 500, Release writeback, then Terminal-Bench 2.0 89 and final writeback.
<!-- qwen-code-dsw-swe-verified:start -->
### SWE-bench Verified
- Status: **SUCCEEDED**
- Dataset: `swe-bench/swe-bench-verified@2`; 500/500 completed
- Results: 351 resolved, 141 unresolved, 4 execution errors, 4 infrastructure failures
- Score: **71.34%**
- Score denominator: valid grader results (351 + 141 = 492)
- Qwen Code: `v0.21.13` (`d95901597430`); model `qwen3.7-plus`
- Run: `pool-669a90b49d8f49e9`; dispatch workflow: https://github.com/QwenLM/qwen-code/actions/runs/32109866948
- Case trajectories: `swe-bench-verified-dsw-eas-full-20260818-r3-trajectories.tar.gz` (496 cases)
<!-- qwen-code-dsw-swe-verified:end -->
<!-- qwen-code-dsw-terminal-bench-2.0:start -->
### Terminal-Bench 2.0
- Status: **QUARANTINED**
- Dataset: `
[email protected]`; 89/89 completed
- Results: 1 resolved, 37 unresolved, 36 execution errors, 15 infrastructure failures
- Score: not published (non-scoreable or quarantined run)
- Score denominator: valid grader results (1 + 37 = 38)
- Qwen Code: `v0.21.13` (`d95901597430`); model `qwen3.7-plus`
- Run: `pool-40646da016a146f8`; dispatch workflow: https://github.com/QwenLM/qwen-code/actions/runs/32109866948
- Case trajectories: `terminal-bench-2.0-dsw-eas-full-20260818-r3-trajectories.tar.gz` (44 cases)
<!-- qwen-code-dsw-terminal-bench-2.0:end -->