Long-context understanding on LongBench (All Core Tasks + Averages)
55.132WikiMQA
Baseline
Updated 4d ago
Evaluation Results
| Method | Links | ||||||||||||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
2026.02 | 55.13 | 34.77 | 55.4 | 59.8 | 55.97 | 26.9 | 29.41 | 31.05 | 10 | 99 | - | 25.14 | 53.92 | 43.24 | - | 91.16 | 50.3 | - | 44.67 | - | |
2026.02 | 50.74 | 35.77 | 54.97 | 60.94 | 54.3 | 27.57 | 29.7 | 31 | 9.03 | 100 | - | 24.9 | 49.7 | 33.76 | - | 87.74 | 49 | - | 46.04 | - | |
2026.02 | 48.63 | 35.28 | 54.05 | 58.12 | 54.69 | 27.02 | 24.35 | 32.78 | 7.85 | 100 | - | 25.03 | 41.22 | 22.11 | - | 86.15 | 46.7 | - | 45.04 | - | |
2026.02 | 48.48 | 35.41 | 54.72 | 60.8 | 54.54 | 27.39 | 27.79 | 31.58 | 7.98 | 100 | - | 25.04 | 48.8 | 35.7 | - | 86.96 | 48.8 | - | 46.7 | - | |
2026.02 | 48.01 | 34.92 | 52.61 | 59.81 | 53.64 | 27.17 | 26.14 | 30.88 | 8.67 | 100 | - | 24.57 | 44.75 | 14.87 | - | 81.89 | 45.9 | - | 44.27 | - | |
2026.02 | 45.98 | 34.95 | 54.79 | 57.96 | 52.31 | 27.58 | 25.36 | 32.21 | 6.02 | 99.43 | - | 24.28 | 53.8 | 31.43 | - | 69.28 | 46.8 | - | 46.2 | - | |
2026.02 | 45.62 | 34.77 | 55.4 | 55.13 | 55.97 | 26.9 | 29.41 | 30.05 | 10 | 99 | 44.67 | 25.14 | 47.79 | 43.24 | 73 | 91.16 | 47.95 | 50.48 | - | - | |
2026.02 | 45.54 | 33.22 | 56.51 | 53.78 | 54.53 | 25.96 | 33.11 | 31.18 | 6.53 | 98 | 44.14 | 25.17 | 48.63 | 43.69 | 70 | 92.08 | 47.63 | 50.37 | - | - | |
2026.02 | 45.16 | 34.16 | 54.2 | 62.85 | 50.1 | 27.04 | 26.56 | 33.49 | 8.63 | 100 | - | 24.13 | 51.74 | 32.36 | - | 77.51 | 47.4 | - | 45.36 | - | |
2026.02 | 43.71 | 32.12 | 43.99 | 48.64 | 47.31 | 24.39 | 25.26 | 23.82 | 5.5 | 69 | 46.74 | 22.95 | 47.66 | 33.59 | 55 | 83.97 | 40.85 | 43.21 | - | - | |
2026.02 | 42.14 | 31.59 | 42.55 | 48.27 | 46.92 | 24.96 | 23.73 | 24.69 | 5.5 | 65 | 45.59 | 23.28 | 55.26 | 46.56 | 76 | 89.51 | 43.22 | 45.74 | - | - | |
2025.12 | 37.24 | 32.8 | 48.67 | 28.6 | 54.12 | 26.77 | 26.63 | 22.96 | 3.5 | 87.5 | 39.39 | 22.98 | 37.28 | 37.99 | - | 83.29 | - | - | - | -4.82 | |
2025.12 | 37.01 | 33.35 | 53.35 | 33.35 | 54.45 | 26.02 | 25.9 | 26.17 | 5 | 96.5 | 40.18 | 24.08 | 34.08 | 38.77 | - | 85.5 | - | - | - | 0 | |
2025.12 | 36.65 | 33.37 | 54.78 | 33.08 | 53.25 | 26.02 | 25.39 | 25 | 5 | 94.5 | 40.17 | 23.59 | 37.46 | 36.82 | - | 83.38 | - | - | - | -0.64 | |
2025.12 | 35.93 | 33.46 | 48.7 | 52.61 | 52.77 | 26.41 | 25.12 | 24.56 | 3 | 83 | 40.17 | 23.35 | 57.16 | 26.37 | - | 82.39 | - | - | - | - | |
2025.12 | 33.37 | 33.35 | 43.06 | 51.86 | 49.82 | 26.57 | 19.82 | 18.21 | 2.97 | 93.5 | 41.07 | 19.51 | 58.02 | 23.15 | - | 86.38 | - | - | - | - | |
2026.02 | 29.54 | 28.34 | 31.01 | 29.35 | 40.97 | 24.61 | 14.11 | 17.98 | 3 | 5.3 | 19.67 | 21.56 | 36.02 | 38.79 | 61.5 | 79.81 | 30.1 | 31.9 | - | - | |
2026.02 | 29.34 | 29.49 | 30.26 | 30.29 | 41.29 | 25.96 | 14.61 | 18.59 | 3.14 | 5 | 21.05 | 21.46 | 25.44 | 39.26 | 62 | 78.89 | 29.75 | 31.53 | - | - | |
2026.02 | 23.04 | 33.3 | 33.18 | 12.04 | 35.77 | 26.18 | 17.39 | 14.25 | 7 | 98.67 | - | 23.4 | 11.54 | 41.48 | - | 82.65 | 36.1 | - | 28 | - | |
2026.02 | 22.43 | 32.11 | 33.23 | 13.98 | 33.98 | 24.79 | 19.13 | 13.16 | 7 | 100 | - | 22.87 | 8.76 | 42.69 | - | 89.16 | 36.4 | - | 26.13 | - | |
2026.02 | 22.43 | 31.98 | 34.88 | 16.55 | 34.62 | 25.21 | 19.06 | 15.39 | 9 | 100 | - | 22.6 | 11.55 | 43.99 | - | 88.82 | 37 | - | 26.31 | - | |
2026.02 | 22.1 | 32.97 | 32.96 | 11.61 | 36.49 | 25.69 | 16.38 | 13.51 | 6 | 98.17 | - | 22.18 | 10.92 | 39.38 | - | 73.35 | 34.1 | - | 24.95 | - | |
2026.02 | 21.42 | 32.86 | 35.12 | 15.25 | 34.83 | 25.78 | 18.96 | 14.95 | 12 | 100 | - | 22.52 | 12.06 | 43.83 | - | 88.49 | 36.9 | - | 26.48 | - | |
2026.02 | 20.68 | 31.83 | 33.48 | 15.2 | 34.15 | 25.34 | 17.97 | 13.61 | 7 | 100 | - | 22.53 | 8.76 | 42.97 | - | 88.29 | 36.3 | - | 25.87 | - | |
2026.02 | 20.5 | 32.3 | 32.42 | 14.82 | 33.89 | 24.9 | 16.69 | 13.99 | 8 | 100 | - | 22.66 | 10.09 | 43.29 | - | 86.96 | 36.1 | - | 25.13 | - |