Multi-hop Question Answering on HotpotQA (Acc, BF Cost)
74.27AccuracyMinistral 3 8B + Claude Opus 4.6
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| Ministral 3 8B + Claude Opus 4.6Tuple=2, Combos=812026.04 | 74.27 | 51.9 |
Loading the SOTA2 catalog…
| Method | Links | ||
|---|---|---|---|
| Ministral 3 8B + Claude Opus 4.6Tuple=2, Combos=812026.04 | 74.27 | 51.9 |