Question Answering on 2Wiki (In-Distribution)
77AccuracyGPT-4.1
Evaluation results
| Method | Links | |||
|---|---|---|---|---|
| GPT-4.1Model Category=Closed-source Models2025.07 | 77 | 81 | 18 | |
| Deliberative Searcher-DeepSeek-70BModel Category=70B Models, Backbone=DeepSeek-R1-Distill-70B2025.07 | 65 | 69 | 5 | |
| Deliberative Searcher-72BModel Category=70B Models, Backbone=Qwen2.5-VL-72B2025.07 | 64 | 73 | 4 | |
| Claude Sonnet 4Model Category=Closed-source Models2025.07 | 61 | 89 | 8 | |
| Deliberative Searcher-7BModel Category=7B Models, Backbone=Qwen2.5-VL-7B2025.07 | 55 | 59 | 3 | |
| Deliberative Searcher-7BModel Category=7B Models, Backbone=Qwen2.5-VL-7B, Reward Function=ECE-based2025.07 | 52 | 54 | 6 | |
| GPT-4oModel Category=Closed-source Models2025.07 | 51 | 86 | 10 | |
| R1-Searcher-7BModel Category=7B Models, Backbone=R1-7B2025.07 | 48 | 59 | 40 | |
| DeepSeek-R1-Distill-70BModel Category=70B Models, Backbone=DeepSeek-R1-Distill-70B2025.07 | 46 | 55 | 44 | |
| InternVL3-78BModel Category=70B Models, Backbone=InternVL3-78B2025.07 | 43 | 62 | 36 | |
| Qwen2.5-VL-72BModel Category=70B Models, Backbone=Qwen2.5-VL-72B2025.07 | 41 | 73 | 23 | |
| Search-R1-7BModel Category=7B Models, Backbone=R1-7B2025.07 | 36 | 51 | 43 | |
| Qwen2.5-VL-7BModel Category=7B Models, Backbone=Qwen2.5-VL-7B2025.07 | 33 | 51 | 48 | |
| ReSearch-7BModel Category=7B Models2025.07 | 33 | 35 | 65 |