List your company

Scientific Verification on FMT

70.5Exact Match (EM)PRISM-MCTS
62.408864.509466.6168.7106Apr 7, 2026

Evaluation results

MethodLinks
PRISM-MCTSModel=GPT-4.1-mini2026.0470.570.07
MCTS-RAGModel=Qwen3-30B-A3B-Instruct-25072026.0470.569.99
MCTS-RAGModel=GPT-4.1-mini2026.0469.568.98
ReST-MCTS*Model=GPT-4.1-mini2026.046968.91
Zero-shotModel=GPT-4.1-mini2026.0468.3468.75
Search-O1Model=Qwen3-30B-A3B-Instruct-25072026.046867.76
PRISM-MCTSModel=Qwen3-30B-A3B-Instruct-25072026.046867.41
Search-O1Model=GPT-4.1-mini2026.046665.03
ReActModel=Qwen3-30B-A3B-Instruct-25072026.0465.565.43
ReActModel=GPT-4.1-mini2026.046567.61
ReST-MCTS*Model=Qwen3-30B-A3B-Instruct-25072026.046463.43
Zero-shotModel=Qwen3-30B-A3B-Instruct-25072026.0462.7262.85