List your company

Mathematical Reasoning on Math500 Level 5 (Accuracy)

71.1AccuracyBG-MCTS
10.05225.90141.7557.599Feb 10, 2026

Evaluation results

MethodLinks
BG-MCTSBackbone LLM=Qwen-2.5-7B-Instruct, Token Budget (B)=30K2026.0271.1
RepeatedFullBackbone LLM=Qwen-2.5-7B-Instruct, Token Budget (B)=30K2026.0270.2
BG-MCTSBackbone LLM=Qwen-2.5-7B-Instruct, Token Budget (B)=20K2026.0269.9
RepeatedFullBackbone LLM=Qwen-2.5-7B-Instruct, Token Budget (B)=20K2026.0266.4
BG-MCTSBackbone LLM=Qwen-2.5-7B-Instruct, Token Budget (B)=10K2026.0266.2
AB-MCTS-MFullBackbone LLM=Qwen-2.5-7B-Instruct, Token Budget (B)=30K2026.0265.9
MCTSBackbone LLM=Qwen-2.5-7B-Instruct, Token Budget (B)=30K2026.0265.9
AB-MCTS-MFullBackbone LLM=Qwen-2.5-7B-Instruct, Token Budget (B)=20K2026.0265.7
MCTSBackbone LLM=Qwen-2.5-7B-Instruct, Token Budget (B)=20K2026.0265.7
RepeatedFullBackbone LLM=Qwen-2.5-7B-Instruct, Token Budget (B)=10K2026.0263.2
AB-MCTS-MFullBackbone LLM=Qwen-2.5-7B-Instruct, Token Budget (B)=10K2026.0262.9
MCTSBackbone LLM=Qwen-2.5-7B-Instruct, Token Budget (B)=10K2026.0261.9
AB-MCTS-MBackbone LLM=Qwen-2.5-7B-Instruct, Token Budget (B)=30K2026.0260
LiteSearch-Batch.Backbone LLM=Qwen-2.5-7B-Instruct, Token Budget (B)=30K2026.0255.7
LiteSearch-Batch.Backbone LLM=Qwen-2.5-7B-Instruct, Token Budget (B)=20K2026.0255
AB-MCTS-MBackbone LLM=Qwen-2.5-7B-Instruct, Token Budget (B)=20K2026.0254.2
LiteSearch-Batch.Backbone LLM=Qwen-2.5-7B-Instruct, Token Budget (B)=10K2026.0252.7
LiteSearch-Incre.Backbone LLM=Qwen-2.5-7B-Instruct, Token Budget (B)=30K2026.0251
LiteSearch-Incre.Backbone LLM=Qwen-2.5-7B-Instruct, Token Budget (B)=20K2026.0250.5
RefinementFullBackbone LLM=Qwen-2.5-7B-Instruct, Token Budget (B)=10K2026.0249.8
GreedyBackbone LLM=Qwen-2.5-7B-Instruct, Token Budget (B)=10K2026.0249.3
GreedyBackbone LLM=Qwen-2.5-7B-Instruct, Token Budget (B)=20K2026.0249.3
GreedyBackbone LLM=Qwen-2.5-7B-Instruct, Token Budget (B)=30K2026.0249.3
RefinementFullBackbone LLM=Qwen-2.5-7B-Instruct, Token Budget (B)=20K2026.0249.3
RefinementFullBackbone LLM=Qwen-2.5-7B-Instruct, Token Budget (B)=30K2026.0249
LiteSearch-Incre.Backbone LLM=Qwen-2.5-7B-Instruct, Token Budget (B)=10K2026.0248.8
BG-MCTSBackbone LLM=Llama-3.1-8B-Instruct, Token Budget (B)=20K2026.0246.5
RepeatedFullBackbone LLM=Llama-3.1-8B-Instruct, Token Budget (B)=30K2026.0245
BG-MCTSBackbone LLM=Llama-3.1-8B-Instruct, Token Budget (B)=30K2026.0244.3
RepeatedFullBackbone LLM=Llama-3.1-8B-Instruct, Token Budget (B)=20K2026.0243.8
AB-MCTS-MBackbone LLM=Qwen-2.5-7B-Instruct, Token Budget (B)=10K2026.0243.3
MCTSBackbone LLM=Llama-3.1-8B-Instruct, Token Budget (B)=30K2026.0243
MCTSBackbone LLM=Llama-3.1-8B-Instruct, Token Budget (B)=20K2026.0240.6
RepeatedFullBackbone LLM=Llama-3.1-8B-Instruct, Token Budget (B)=10K2026.0239.3
BG-MCTSBackbone LLM=Llama-3.1-8B-Instruct, Token Budget (B)=10K2026.0239.3
AB-MCTS-MFullBackbone LLM=Llama-3.1-8B-Instruct, Token Budget (B)=30K2026.0234.3
MCTSBackbone LLM=Llama-3.1-8B-Instruct, Token Budget (B)=10K2026.0233.3
AB-MCTS-MFullBackbone LLM=Llama-3.1-8B-Instruct, Token Budget (B)=20K2026.0232.3
AB-MCTS-MFullBackbone LLM=Llama-3.1-8B-Instruct, Token Budget (B)=10K2026.0231.1
LiteSearch-Incre.Backbone LLM=Llama-3.1-8B-Instruct, Token Budget (B)=30K2026.0230.4
LiteSearch-Incre.Backbone LLM=Llama-3.1-8B-Instruct, Token Budget (B)=20K2026.0229.1
LiteSearch-Batch.Backbone LLM=Llama-3.1-8B-Instruct, Token Budget (B)=30K2026.0228.1
LiteSearch-Batch.Backbone LLM=Llama-3.1-8B-Instruct, Token Budget (B)=20K2026.0227.1
RefinementFullBackbone LLM=Llama-3.1-8B-Instruct, Token Budget (B)=10K2026.0224.9
LiteSearch-Incre.Backbone LLM=Llama-3.1-8B-Instruct, Token Budget (B)=10K2026.0224.9
RefinementFullBackbone LLM=Llama-3.1-8B-Instruct, Token Budget (B)=20K2026.0224.6
RefinementFullBackbone LLM=Llama-3.1-8B-Instruct, Token Budget (B)=30K2026.0224.1
LiteSearch-Batch.Backbone LLM=Llama-3.1-8B-Instruct, Token Budget (B)=10K2026.0223.6
GreedyBackbone LLM=Llama-3.1-8B-Instruct, Token Budget (B)=10K2026.0222.4
GreedyBackbone LLM=Llama-3.1-8B-Instruct, Token Budget (B)=20K2026.0222.4
GreedyBackbone LLM=Llama-3.1-8B-Instruct, Token Budget (B)=30K2026.0222.4
AB-MCTS-MBackbone LLM=Llama-3.1-8B-Instruct, Token Budget (B)=30K2026.0220.9
AB-MCTS-MBackbone LLM=Llama-3.1-8B-Instruct, Token Budget (B)=20K2026.0217.9
AB-MCTS-MBackbone LLM=Llama-3.1-8B-Instruct, Token Budget (B)=10K2026.0212.4