Reasoning on DeepSearchQA
24.1ScoreDOLORES
Evaluation results
| Method | Links | |
|---|---|---|
| DOLORESModel=Qwen3 32B Thinking2026.05 | 24.1 | |
| Deep ResearchModel=Qwen3 32B Thinking2026.05 | 23 | |
| CodeActModel=Qwen3 32B Thinking2026.05 | 21.3 | |
| RLMModel=Qwen3 32B Thinking2026.05 | 19 | |
| DOLORESModel=Llama-3.3 70B Instruct2026.05 | 18.7 | |
| CodeActModel=Llama-3.3 70B Instruct2026.05 | 18.4 | |
| ReActModel=Qwen3 32B Thinking2026.05 | 17.7 | |
| RLMModel=Llama-3.3 70B Instruct2026.05 | 17.5 | |
| DOLORESModel=Qwen3 8B Thinking2026.05 | 16.1 | |
| ReActModel=Llama-3.3 70B Instruct2026.05 | 15.5 | |
| CodeActModel=Qwen3 8B Thinking2026.05 | 14.9 | |
| Deep ResearchModel=Qwen3 8B Thinking2026.05 | 14.2 | |
| RLMModel=Qwen3 8B Thinking2026.05 | 13.9 | |
| Deep ResearchModel=Llama-3.3 70B Instruct2026.05 | 12.7 | |
| ReActModel=Qwen3 8B Thinking2026.05 | 12.4 |