Multi-Hop Question Answering on Multi-Hop QA Partial Context
72.1AccuracyGPT-4o
Evaluation Results
| Method | Links | |
|---|---|---|
| GPT-4o2026.01 | 72.1 | |
| Qwen3-32BParameters=32B2026.01 | 54.38 | |
| Exaone3.5-7.8BParameters=7.8B2026.01 | 52.31 | |
| Qwen3-8BParameters=8B2026.01 | 51.34 | |
| HyperClovaX-14BParameters=14B2026.01 | 42.97 |