Theorem Question Answering on TheoremQA (test)
87.4AccuracyDS-R1-Distill-Qwen-14B + Meta-Reasoner
Evaluation Results
| Method | Links | |
|---|---|---|
| DS-R1-Distill-Qwen-14B + Meta-ReasonerBackbone=DS-R1-Distill-Qwen-14B, Reasoning Strategy=Meta-Reasoner2025.02 | 87.4 | |
| Gemini-Exp-1206 + Meta-ReasonerBackbone=Gemini-Exp-1206, Reasoning Strategy=Meta-Reasoner2025.02 | 86.32 | |
| GPT-4o-mini + Meta-ReasonerBackbone=GPT-4o-mini, Reasoning Strategy=Meta-Reasoner2025.02 | 84.13 | |
| Qwen3-8B + Meta-ReasonerBackbone=Qwen3-8B, Reasoning Strategy=Meta-Reasoner2025.02 | 82.93 | |
| GPT-4 Turbo + MACMBackbone=GPT-4 Turbo, Reasoning Strategy=MACM2025.02 | 79.41 | |
| GPT-4o-mini + ReflexionBackbone=GPT-4o-mini, Reasoning Strategy=Reflexion2025.02 | 74.32 | |
| Gemini-Exp-1206 + CoTBackbone=Gemini-Exp-1206, Reasoning Strategy=CoT2025.02 | 43.12 | |
| GPT-4o-mini + CoTBackbone=GPT-4o-mini, Reasoning Strategy=CoT2025.02 | 39.46 |