Long-form writing on LongBench-Write (test)
86.7Overall Quality Score (S_bar)
Claude Opus 4.6
Updated 1mo ago
Evaluation Results
| Method | Links | |||
|---|---|---|---|---|
2026.06 | 86.7 | 88.1 | 98.4 | |
2025.06 | 86.3 | 84.2 | 88.4 | |
2025.06 | 84 | 82.6 | 85.4 | |
2026.06 | 83.3 | 84.7 | 98.4 | |
2026.06 | 81.2 | 88.5 | 90.2 | |
2025.06 | 80.7 | 73.7 | 87.7 | |
2025.06 | 80.5 | 78.6 | 82.3 | |
2026.06 | 80.3 | 83.2 | 96.8 | |
2025.06 | 79.8 | 77.4 | 82.2 | |
2026.06 | 79.8 | 84.8 | 94.2 | |
2026.06 | 78.4 | 82.7 | 94.9 | |
2026.06 | 77.8 | 91.5 | 85.3 | |
2026.06 | 77.6 | 81.1 | 95.8 | |
2025.06 | 77 | 65.6 | 88.3 | |
2026.06 | 73.4 | 75.5 | 97.6 | |
2025.06 | 68.3 | 51 | 85.5 | |
2025.06 | 67.3 | 47.9 | 86.6 | |
2026.06 | 67.1 | 90.3 | 75.1 | |
2025.06 | 65.6 | 50.8 | 80.3 | |
2025.06 | 60.3 | 50 | 70.6 | |
2026.06 | 58.3 | 73 | 76.8 | |
2026.06 | 57.8 | 75.9 | 71.4 | |
2026.06 | 57.5 | 67.9 | 80.5 | |
2025.06 | 56.6 | 59.6 | 53.5 | |
2026.06 | 41.5 | 53.6 | 71.9 |