List your company

Mathematical Reasoning on GSM-Plus (test)

68.8AccuracyMCTS w/ FETCH
-2.75215.82434.452.976Feb 16, 2025Mar 27, 2025May 5, 2025Jun 13, 2025Jul 22, 2025Aug 30, 2025Oct 9, 2025

Evaluation results

MethodLinks
MCTS w/ FETCHsearch_strategy=MCTS, variant=FETCH2025.0268.83.53
MCTS w/ Var Reducesearch_strategy=MCTS, variant=Var Reduce2025.0268.614.4
BFS w/ FETCHsearch_strategy=BFS, variant=FETCH2025.0268.41.09
Beam Search w/ FETCHsearch_strategy=Beam Search, variant=FETCH2025.0268.21.62
Beam Search w/ Var Reducesearch_strategy=Beam Search, variant=Var Reduce2025.02681.89
Tree Search w/ FETCHsearch_strategy=Tree Search, variant=FETCH2025.0267.70.69
BFS w/ Var Reducesearch_strategy=BFS, variant=Var Reduce2025.0267.62.89
MCTSsearch_strategy=MCTS2025.0267.614.1
Beam Search w/ State Mergesearch_strategy=Beam Search, variant=State Merge2025.0267.41.61
Tree Search w/ Var Reducesearch_strategy=Tree Search, variant=Var Reduce2025.02670.89
MCTS w/ State Mergesearch_strategy=MCTS, variant=State Merge2025.02673.43
Beam Searchsearch_strategy=Beam Search2025.0266.91.88
BFS w/ State Mergesearch_strategy=BFS, variant=State Merge2025.0266.41.12
Tree Searchsearch_strategy=Tree Search2025.02660.92
Tree Search w/ State Mergesearch_strategy=Tree Search, variant=State Merge2025.0265.70.69
BFSsearch_strategy=BFS2025.0265.52.84
Best-of-Nsearch_strategy=Best-of-N2025.0263.40.95
Weighted Votingsearch_strategy=Weighted Voting2025.02620.95
Self-Consistencysearch_strategy=Self-Consistency2025.0260.10.95
Greedy Decodingsearch_strategy=Greedy Decoding2025.02500.09
TeacherTeacher and Student Model Pair=Qwen-2.5-3b to Qwen-2.5-0.5b2025.1045.4—
TeacherTeacher and Student Model Pair=Llama-3.1-3b to Llama-3.1-1b2025.1038.6—
TeacherTeacher and Student Model Pair=Gemma-7b to Gemma-2b2025.1033.4—
AdaSwitchTeacher and Student Model Pair=Qwen-2.5-3b to Qwen-2.5-0.5b2025.1021.6—
ImitKDTeacher and Student Model Pair=Qwen-2.5-3b to Qwen-2.5-0.5b2025.1021.3—
SWITCHTeacher and Student Model Pair=Qwen-2.5-3b to Qwen-2.5-0.5b2025.1020.8—
SKDTeacher and Student Model Pair=Qwen-2.5-3b to Qwen-2.5-0.5b2025.1020.4—
On-policyTeacher and Student Model Pair=Qwen-2.5-3b to Qwen-2.5-0.5b2025.1020.2—
Off-policyTeacher and Student Model Pair=Qwen-2.5-3b to Qwen-2.5-0.5b2025.1017.9—
AdaSwitchTeacher and Student Model Pair=Llama-3.1-3b to Llama-3.1-1b2025.1017.3—
SKDTeacher and Student Model Pair=Llama-3.1-3b to Llama-3.1-1b2025.1016.9—
SWITCHTeacher and Student Model Pair=Llama-3.1-3b to Llama-3.1-1b2025.1016—
ImitKDTeacher and Student Model Pair=Llama-3.1-3b to Llama-3.1-1b2025.1015.6—
SFTTeacher and Student Model Pair=Qwen-2.5-3b to Qwen-2.5-0.5b2025.1015.5—
SeqKDTeacher and Student Model Pair=Qwen-2.5-3b to Qwen-2.5-0.5b2025.1014.4—
On-policyTeacher and Student Model Pair=Llama-3.1-3b to Llama-3.1-1b2025.1014.3—
AdaSwitchTeacher and Student Model Pair=Gemma-7b to Gemma-2b2025.1014.2—
SKDTeacher and Student Model Pair=Gemma-7b to Gemma-2b2025.1013.9—
Off-policyTeacher and Student Model Pair=Llama-3.1-3b to Llama-3.1-1b2025.1013.8—
On-policyTeacher and Student Model Pair=Gemma-7b to Gemma-2b2025.1013.8—
SWITCHTeacher and Student Model Pair=Gemma-7b to Gemma-2b2025.1013.8—
ImitKDTeacher and Student Model Pair=Gemma-7b to Gemma-2b2025.1013.5—
SFTTeacher and Student Model Pair=Llama-3.1-3b to Llama-3.1-1b2025.1012—
SeqKDTeacher and Student Model Pair=Llama-3.1-3b to Llama-3.1-1b2025.1011.8—
SFTTeacher and Student Model Pair=Gemma-7b to Gemma-2b2025.1011.7—
Off-policyTeacher and Student Model Pair=Gemma-7b to Gemma-2b2025.1010.7—
SeqKDTeacher and Student Model Pair=Gemma-7b to Gemma-2b2025.1010.5—
StudentTeacher and Student Model Pair=Llama-3.1-3b to Llama-3.1-1b2025.100—
StudentTeacher and Student Model Pair=Qwen-2.5-3b to Qwen-2.5-0.5b2025.100—
StudentTeacher and Student Model Pair=Gemma-7b to Gemma-2b2025.100—