Long-context Memory Evaluation on LongMemEval
100Single-Turn Preference
BMAM
Updated 4d ago
Evaluation Results
| Method | Links | |||||||
|---|---|---|---|---|---|---|---|---|
2026.01 | 100 | 76.8 | 59.4 | 52.6 | 70.5 | 87.1 | 67.6 | |
2026.01 | 96.7 | 67.9 | 77.4 | 70.7 | 74.3 | 95.7 | 77.8 | |
2026.01 | 94.16 | 38.14 | 69.6 | 69.24 | 79.18 | 90.7 | 71.9 | |
2026.01 | 91.67 | 32.56 | 64.22 | 62.86 | 75.76 | 90.57 | 67.5 | |
2026.01 | 90 | 26.8 | 72.2 | 63.2 | 66.7 | 82.9 | 66.4 | |
2026.01 | 89.9 | 58.9 | 44.4 | 52.6 | 55.1 | 85.7 | 58.4 | |
2026.02 | 86.7 | 92.9 | 72.2 | 55.6 | 79.5 | 90 | 74.6 | |
2026.02 | 83.3 | 78.6 | 89.5 | 78.2 | 97.4 | 98.6 | 87.4 | |
2026.01 | 80.1 | 23.2 | 75.9 | 66.9 | 89.7 | 92.9 | 72.4 | |
2026.02 | 76.7 | 76.8 | 84.2 | 73.7 | 96.2 | 97.1 | 83.8 | |
2026.01 | 76.7 | 19.6 | 17.3 | 42.1 | 41 | 67.1 | 38.4 | |
2026.01 | 75 | 88.37 | 49.54 | 46.67 | 66.67 | 86.79 | 62.25 | |
2026.01 | 70.24 | 22.36 | 52.52 | 75.31 | 76.92 | 90.36 | 66.17 | |
2026.01 | 66.12 | 25.64 | 66.28 | 75.5 | 77.76 | 90.28 | 69.08 | |
2026.01 | 62.5 | 88.37 | 27.52 | 34.29 | 66.67 | 81.13 | 51.5 | |
2026.01 | 62.5 | 81.4 | 36.45 | 38.46 | 72.31 | 81.13 | 55.3 | |
2026.01 | 62.5 | 83.72 | 26.61 | 15.24 | 71.21 | 86.79 | 47.25 | |
2026.01 | 58.33 | 90.7 | 47.71 | 48.57 | 62.12 | 84.91 | 60.5 | |
2026.01 | 53.3 | 63.6 | 25.6 | 30.1 | 52.6 | 72.9 | 43.5 | |
2026.01 | 53.3 | 75 | 54.1 | 47.4 | 74.4 | 92.9 | 63.8 | |
2026.01 | 50 | 87.5 | 33.08 | 36.09 | 76.92 | 82.86 | 54.8 | |
2026.01 | 50 | 83.72 | 55.05 | 51.43 | 62.12 | 90.57 | 62.75 | |
2026.01 | 41.67 | 86.05 | 51.38 | 52.38 | 72.73 | 85.85 | 62.88 | |
2026.01 | 38.33 | 89.29 | 35.88 | 34.15 | 77.18 | 81.43 | 54.62 | |
2026.01 | 33.33 | 72.09 | 22.02 | 21.9 | 57.58 | 58.49 | 38.75 | |
2026.01 | 32.5 | 88.64 | 57.45 | 56.72 | 73.56 | 84.29 | 62.88 | |
2026.01 | 29.17 | 79.07 | 28.44 | 37.14 | 59.09 | 69.81 | 46.75 | |
2026.02 | 16.7 | 98.2 | 60.2 | 51.1 | 76.9 | 85.7 | 65.6 |