Multi-hop Question Answering on HotpotQA (LLM-as-a-Judge, Average)
55.49LLM Judge Score
AgeMem
Updated 4d ago
Evaluation Results
| Method | Links | ||
|---|---|---|---|
2026.01 | 55.49 | 54.31 | |
2026.01 | 54.49 | 45.59 | |
2026.01 | 54.44 | 41.96 | |
2026.01 | 48.48 | 45.74 | |
2026.01 | 47.48 | 43.97 | |
2026.01 | 46.66 | 37.14 | |
2026.01 | 45.36 | 33.43 | |
2026.01 | 43.95 | 36.78 | |
2026.01 | 42.7 | 43.25 | |
2026.01 | 42.06 | 36.31 | |
2026.01 | 39.16 | 44.7 | |
2026.01 | 38.36 | 28.05 | |
2026.01 | 38.12 | 41.95 | |
2026.01 | 37.43 | 34.23 |