Multimodal Report Generation on DeepConsult
13.73Instruction Adherence ScorePTAH
Evaluation Results
| Method | Links | |||||
|---|---|---|---|---|---|---|
| PTAHGeneration Type=Multimodal Generation, Planner=Qwen3-32B, Writer=Qwen3-VL-32B-Instruct2026.05 | 13.73 | 18.63 | 17.64 | 14.71 | 16.18 | |
| WebThinkerGeneration Type=Text-Only Generation, Base Model=Qwen3-32B2026.05 | 2.94 | 17.64 | 2.94 | 5.88 | 7.35 | |
| Qwen3-32BGeneration Type=Direct Generation, Base Model=Qwen3-32B2026.05 | 0.98 | 0.98 | 0.98 | 0.98 | 0.98 | |
| QwQ-32BGeneration Type=Direct Generation, Base Model=QwQ-32B2026.05 | 0.98 | 0.98 | 0.98 | 1.96 | 1.23 | |
| ReActGeneration Type=Text-Only Generation, Base Model=Qwen3-32B2026.05 | 0.98 | 0.98 | 0.98 | 6.86 | 2.45 | |
| Search-o1Generation Type=Text-Only Generation, Base Model=Qwen3-32B2026.05 | 0.98 | 0.98 | 0.98 | 7.84 | 2.69 | |
| LLM-IGeneration Type=Multimodal Generation, Base Model=Qwen3-32B2026.05 | 0.98 | 0.98 | 0.98 | 1.96 | 1.23 |