Long-context Question Answering on LoCoMo (LLJ Metrics)
97.1Single-Hop LLJ Score
Mnemis
Updated 4d ago
Evaluation Results
| Method | Links | |||||||
|---|---|---|---|---|---|---|---|---|
2026.02 | 97.1 | 90.7 | 79.2 | 92.9 | 93.9 | - | - | |
2026.02 | 96.1 | 89.7 | 70.8 | 91.1 | 92.3 | - | - | |
2026.02 | 94.9 | 92.5 | 77.1 | 88.3 | 92.1 | - | - | |
2026.02 | 90.5 | 80.8 | 71.7 | 79.6 | 85.3 | - | - | |
2026.02 | 86.9 | 74.2 | 56.6 | 77.2 | 80.6 | - | - | |
2026.02 | 85.1 | 88.4 | 65.6 | 83.7 | 85.4 | - | - | |
2026.02 | 84.9 | 77.6 | 51 | 75.1 | 79.5 | - | - | |
2026.02 | 84.5 | 50.8 | 59 | 71 | 73.4 | - | - | |
2026.01 | 81.5 | 72.1 | 76.8 | 84.2 | 80.7 | - | - | |
2026.01 | 79.9 | 70.8 | 72.9 | 79.8 | 77.6 | - | - | |
2026.01 | 78.3 | 72.7 | 54.6 | 63.7 | 67.7 | - | - | |
2026.02 | 76.5 | 76.6 | 67.7 | 64.9 | 73.8 | - | - | |
2026.02 | 71.4 | 56.9 | 47.9 | 68.2 | 66.3 | - | - | |
2026.01 | 67.1 | 58.1 | 75.7 | 51.2 | 57.1 | - | - | |
2026.02 | 66.9 | 60.2 | 43.8 | 53.7 | 61.6 | - | - | |
2026.02 | 66.2 | 74.8 | 46.9 | 61 | 65.8 | - | - | |
2026.01 | 62.2 | 23.4 | 71.1 | 47.9 | 46.9 | - | - | |
2026.01 | 61.7 | 49.3 | 76.6 | 41.4 | 49 | - | - | |
2026.01 | 45.5 | 51.5 | 60.1 | 28.2 | 38.2 | - | - | |
2026.01 | 41.2 | 50.4 | 55.8 | 19.5 | 32.2 | - | - | |
2026.01 | 39.8 | 49.9 | 54.1 | 18.9 | 31.4 | - | - | |
2026.01 | 38.5 | 48.2 | 53 | 17.8 | 30.1 | - | - | |
2026.01 | 37.1 | 41.5 | 50.2 | 16.5 | 27.6 | - | - | |
2026.01 | 30.5 | 35.8 | 45.3 | 14.2 | 23.6 | - | - | |
2026.01 | - | - | - | - | - | 25.78 | 25.15 | |
2026.01 | - | - | - | - | - | 30.37 | 36.85 | |
2026.01 | - | - | - | - | - | 42.52 | 44.14 | |
2026.01 | - | - | - | - | - | 45.36 | 43.74 | |
2026.01 | - | - | - | - | - | 45.02 | 47.41 | |
2026.01 | - | - | - | - | - | 54.4 | 54.68 |