Coding Agent Capacity on SWE-Evo
27.1Score
Claude-Opus-4.5
Updated 24d ago
Evaluation Results
| Method | Links | |
|---|---|---|
2026.06 | 27.1 | |
2026.06 | 16.7 | |
2026.06 | 12.8 | |
2026.06 | 12.5 | |
2026.06 | 10.6 | |
2026.06 | 10.4 | |
2026.06 | 8.9 | |
2026.06 | 8.5 |
Claude-Opus-4.5
| Method | Links | |
|---|---|---|
2026.06 | 27.1 | |
2026.06 | 16.7 | |
2026.06 | 12.8 | |
2026.06 | 12.5 | |
2026.06 | 10.6 | |
2026.06 | 10.4 | |
2026.06 | 8.9 | |
2026.06 | 8.5 |