List your company

Reasoning on PhantomWiki 2025 (test)

51.2ScoreDOLORES
2.42415.08727.7540.413May 12, 2026

Evaluation results

MethodLinks
DOLORESBase Model=Llama-3.3 70B Instruct2026.0551.2
CodeActBase Model=Llama-3.3 70B Instruct2026.0538.1
DOLORESBase Model=Qwen3 32B Thinking2026.0536.9
RLMBase Model=Llama-3.3 70B Instruct2026.0527
CodeActBase Model=Qwen3 32B Thinking2026.0525.2
ReActBase Model=Llama-3.3 70B Instruct2026.0524.4
Deep ResearchBase Model=Qwen3 32B Thinking2026.0521.2
DOLORESBase Model=Qwen3 8B Thinking2026.0517.2
ReActBase Model=Qwen3 32B Thinking2026.0516.7
RLMBase Model=Qwen3 32B Thinking2026.0516
Deep ResearchBase Model=Llama-3.3 70B Instruct2026.0516
CodeActBase Model=Qwen3 8B Thinking2026.0515.3
ReActBase Model=Qwen3 8B Thinking2026.0514.4
Deep ResearchBase Model=Qwen3 8B Thinking2026.0512
RLMBase Model=Qwen3 8B Thinking2026.054.3