Question Answering on MuSiQue (In-Distribution)
44AccuracyClaude Sonnet 4
Evaluation Results
| Method | Links | |||
|---|---|---|---|---|
| Claude Sonnet 4Model Category=Closed-source Models2025.07 | 44 | 57 | 42 | |
| GPT-4.1Model Category=Closed-source Models2025.07 | 43 | 45 | 55 | |
| Deliberative Searcher-72BModel Category=70B Models, Backbone=Qwen2.5-VL-72B2025.07 | 37 | 71 | 14 | |
| Deliberative Searcher-DeepSeek-70BModel Category=70B Models, Backbone=DeepSeek-R1-Distill-70B2025.07 | 34 | 72 | 11 | |
| GPT-4oModel Category=Closed-source Models2025.07 | 33 | 52 | 47 | |
| Deliberative Searcher-7BModel Category=7B Models, Backbone=Qwen2.5-VL-7B2025.07 | 29 | 74 | 2 | |
| Deliberative Searcher-7BModel Category=7B Models, Backbone=Qwen2.5-VL-7B, Reward Function=ECE-based2025.07 | 27 | 71 | 2 | |
| R1-Searcher-7BModel Category=7B Models, Backbone=R1-7B2025.07 | 26 | 35 | 65 | |
| Qwen2.5-VL-72BModel Category=70B Models, Backbone=Qwen2.5-VL-72B2025.07 | 25 | 50 | 49 | |
| InternVL3-78BModel Category=70B Models, Backbone=InternVL3-78B2025.07 | 24 | 41 | 58 | |
| DeepSeek-R1-Distill-70BModel Category=70B Models, Backbone=DeepSeek-R1-Distill-70B2025.07 | 23 | 32 | 68 | |
| ReSearch-7BModel Category=7B Models2025.07 | 18 | 22 | 78 | |
| Search-R1-7BModel Category=7B Models, Backbone=R1-7B2025.07 | 16 | 45 | 53 | |
| Qwen2.5-VL-7BModel Category=7B Models, Backbone=Qwen2.5-VL-7B2025.07 | 12 | 48 | 52 |