Long-context language understanding suite on ZeroSCROLLS
33.5GovReport Score
Qwen3-4B
Updated 4d ago
Evaluation Results
| Method | Links | ||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|
2025.12 | 33.5 | 9.9 | 8.6 | 18.7 | 34 | 38 | - | 32.5 | 30.5 | 87 | |
2025.12 | 29.8 | 7.9 | 8.6 | 18.3 | 26.1 | 42.8 | - | 34.6 | 48.9 | 94.5 | |
2025.12 | 26.7 | - | 11.9 | - | 24.1 | 27.7 | - | - | 28.9 | - | |
2025.12 | 26 | - | 10.8 | - | 42.4 | 49.6 | - | - | 59.2 | - | |
2025.12 | 26 | 7.4 | 9.5 | 18 | 31.1 | 11.7 | - | 25.8 | 26.2 | 76.2 | |
2025.12 | 24.9 | 9.9 | 10.9 | 9.9 | 23.2 | 11 | - | 18.4 | 17.1 | 40.5 | |
2025.12 | 24.8 | - | 9.9 | - | 35 | 42.4 | - | - | 54.9 | - | |
2025.12 | 22.5 | 8.2 | 6.2 | 9.2 | 25.7 | 15 | - | 18.3 | 11.6 | 47.6 | |
2025.12 | 22 | 10.4 | 9.8 | 18.1 | 19.6 | 18.9 | - | 24.1 | 22.5 | 71.4 | |
2025.12 | 21.8 | 7.2 | 7.5 | 14.6 | 21.4 | 8.9 | - | 20.7 | 22.6 | 61.9 | |
2024.03 | 21.4 | 14.3 | 16.2 | 20.2 | 37.8 | 21 | 43.3 | 24.9 | - | - | |
2024.03 | 20.2 | 14.5 | 15.4 | 19.8 | 34.7 | 16.2 | 10.5 | 18.8 | - | - | |
2024.03 | 20.2 | 13.9 | 16.2 | 20.1 | 32.3 | 18.8 | 29.9 | 21.6 | - | - | |
2025.12 | 20.2 | 8.3 | 7.7 | 16.8 | 24.7 | 30 | - | 23.9 | 7.5 | 76.2 | |
2025.12 | 17.8 | 7.9 | 8.6 | 15.3 | 21.1 | 35.1 | - | 30 | 43.9 | 90.5 | |
2024.03 | 17.7 | 14.2 | 15.8 | 19.9 | 25.1 | 17.7 | 5.8 | 16.6 | - | - | |
2024.03 | 16.8 | 14.1 | 15.2 | 19.5 | 21.9 | 14.4 | 3.1 | 15 | - | - | |
2024.03 | 16.6 | 14.2 | 15.2 | 18.7 | 36.9 | 18 | 14.2 | 19.1 | - | - | |
2024.03 | 16.5 | 13.1 | 15.5 | 19.2 | 20.8 | 17 | 5.9 | 15.4 | - | - | |
2024.03 | 16.2 | 12.7 | 15.1 | 18.9 | 24.3 | 13.7 | 3.3 | 15 | - | - | |
2024.03 | 15.4 | 12.3 | 15.1 | 18.9 | 19 | 15 | 5.7 | 14.5 | - | - | |
2024.03 | 14.9 | 13.8 | 14.7 | 17.9 | 28.1 | 16.8 | 9.2 | 16.5 | - | - | |
2024.03 | 7.4 | 7.4 | 12.8 | 13.2 | 20.8 | 13.4 | 5.6 | 11.5 | - | - | |
2024.03 | 5.7 | 7.1 | 12.9 | 13.3 | 19.2 | 13.4 | 4.8 | 10.9 | - | - |