List your company

Reasoning on DeepSearchQA 2026 (test)

24.1ScoreDOLORES
11.93215.09118.2521.409May 12, 2026

Evaluation results

MethodLinks
DOLORESBase Model=Qwen3 32B Thinking2026.0524.1
Deep ResearchBase Model=Qwen3 32B Thinking2026.0523
CodeActBase Model=Qwen3 32B Thinking2026.0521.3
RLMBase Model=Qwen3 32B Thinking2026.0519
DOLORESBase Model=Llama-3.3 70B Instruct2026.0518.7
CodeActBase Model=Llama-3.3 70B Instruct2026.0518.4
ReActBase Model=Qwen3 32B Thinking2026.0517.7
RLMBase Model=Llama-3.3 70B Instruct2026.0517.5
DOLORESBase Model=Qwen3 8B Thinking2026.0516.1
ReActBase Model=Llama-3.3 70B Instruct2026.0515.5
CodeActBase Model=Qwen3 8B Thinking2026.0514.9
Deep ResearchBase Model=Qwen3 8B Thinking2026.0514.2
RLMBase Model=Qwen3 8B Thinking2026.0513.9
Deep ResearchBase Model=Llama-3.3 70B Instruct2026.0512.7
ReActBase Model=Qwen3 8B Thinking2026.0512.4