Multi-hop Question Answering on HotpotQA (Acc, LLM)
53Accuracy
AutoAgent
Updated 1mo ago
Evaluation Results
| Method | Links | ||
|---|---|---|---|
2026.03 | 53 | 63 | |
2026.03 | 43.4 | 30.8 | |
2026.03 | 39.2 | 46.2 | |
2026.03 | 37.4 | 45.6 | |
2026.03 | 36.6 | 44.2 | |
2026.03 | 36 | 45.4 | |
2026.03 | 35.8 | 45 | |
2026.03 | 35 | 42.8 | |
2026.03 | 34.2 | 45 | |
2026.03 | 33.2 | 39.8 | |
2026.03 | 32.4 | 40.4 | |
2026.03 | 27 | 38 |