List your company

Mathematical Reasoning on GSM8K 1319 problems (test)

96.59AccuracyMCTS + EquivPruner
83.267686.726390.18593.6437May 22, 2025

Evaluation results

MethodLinks
MCTS + EquivPrunerBase Model=Qwen2.5-Math-7B-Instruct, Search Strategy=Monte Carlo Tree Search + EquivPruner2025.0596.5918,07151.89
Vanilla MCTSBase Model=Qwen2.5-Math-7B-Instruct, Search Strategy=Monte Carlo Tree Search2025.0596.4434,826100
Vanilla MCTSBase Model=Qwen2.5-Math-1.5B-Instruct, Search Strategy=Monte Carlo Tree Search2025.0591.0539,337100
MCTS + EquivPrunerBase Model=Qwen2.5-Math-1.5B-Instruct, Search Strategy=Monte Carlo Tree Search + EquivPruner2025.0590.7523,75260.38
MCTS + EquivPrunerBase Model=Mistral-7b-sft, Search Strategy=Monte Carlo Tree Search + EquivPruner2025.0585.0612,53762.01
Vanilla MCTSBase Model=Mistral-7b-sft, Search Strategy=Monte Carlo Tree Search2025.0583.7820,217100