Software Engineering Automation on SWE Multilingual
70.2ResolvedDeepSeek-V3.2
Evaluation Results
| Method | Links | |
|---|---|---|
| DeepSeek-V3.2thinking mode=true2025.12 | 70.2 | |
| Claude-4.5-Sonnet2025.12 | 68 | |
| Kimi-K2thinking mode=true2025.12 | 61.1 | |
| MiniMax M22025.12 | 56.5 | |
| GPT-5 High2025.12 | 55.3 |