Agentic Coding on SWE-bench Multilingual (pass@1)
73.3pass@1
DeepSeek-V4 Flash
Updated 6d ago
Evaluation Results
| Method | Links | |
|---|---|---|
2026.05 | 73.3 | |
2026.05 | 69.3 | |
2026.05 | 66.7 | |
2026.05 | 63.1 | |
2026.05 | 61.3 |
DeepSeek-V4 Flash
| Method | Links | |
|---|---|---|
2026.05 | 73.3 | |
2026.05 | 69.3 | |
2026.05 | 66.7 | |
2026.05 | 63.1 | |
2026.05 | 61.3 |