Benchmark · agentic
DeepSWE
DataCurve's long-horizon real-repo coding-agent suite (headline metric = pass@1 resolve rate); Artificial Analysis swapped SWE-bench Pro out of its Coding Agent Index for it. Not a SWE-bench variant.
| 日期 | 模型 | 得分 | 来源 |
|---|---|---|---|
| 2026-07-27 | GPT-5.6 Sol | 72.7% | Kimi K3在DeepSWE pass@4上超越GPT-5.6 Sol，成本降低64% |
| 2026-07-27 | Kimi K3 | 68.5% | Kimi K3在DeepSWE pass@4上超越GPT-5.6 Sol，成本降低64% |