List your company
ResearchFormerly WizWand

Mathematical Reasoning on Minerva (Accuracy, #Tokens)

54.53AccuracyPass@k
22.674830.944939.21547.4851May 24, 2026
Updated 5mo ago

Evaluation results

MethodLinks
Pass@kModel=Phi-4-mini-Instruct, N=322026.0554.5317,119
Pass@kModel=Qwen2.5-7B-Instruct, N=322026.0552.3319,765
Pass@kModel=Qwen2.5-3B-Instruct, N=322026.0546.219,765
SPSModel=Qwen2.5-7B-Instruct, N=82026.0543.269,387
PB-SMCModel=Qwen2.5-7B-Instruct, N=82026.0541.7913,216
SMCModel=Qwen2.5-7B-Instruct, N=322026.0540.3221,642
Beam SearchModel=Qwen2.5-7B-Instruct, N=322026.0540.223,900
DVTSModel=Qwen2.5-7B-Instruct, N=322026.0539.2223,549
Self-ConsistencyModel=Qwen2.5-7B-Instruct, N=322026.0538.8519,765
SPSModel=Qwen2.5-3B-Instruct, N=82026.0538.7310,800
Best-of-NModel=Qwen2.5-7B-Instruct, N=322026.0538.4819,765
PB-SMCModel=Qwen2.5-3B-Instruct, N=82026.0538.2315,450
PB-SMCModel=Phi-4-mini-Instruct, N=82026.0537.8713,198
SMCModel=Qwen2.5-3B-Instruct, N=322026.0536.5225,143
MCTSModel=Qwen2.5-7B-Instruct, N=322026.0536.2725,208
Beam SearchModel=Qwen2.5-3B-Instruct, N=322026.0535.7823,131
SPSModel=Phi-4-mini-Instruct, N=82026.0535.429,832
DVTSModel=Qwen2.5-3B-Instruct, N=322026.0535.0524,971
Best-of-NModel=Phi-4-mini-Instruct, N=322026.0534.817,119
Base ModelModel=Qwen2.5-7B-Instruct, N=12026.0534.68617
SMCModel=Phi-4-mini-Instruct, N=322026.0534.4424,907
DVTSModel=Phi-4-mini-Instruct, N=322026.0533.8222,140
Best-of-NModel=Qwen2.5-3B-Instruct, N=322026.0533.719,765
Self-ConsistencyModel=Phi-4-mini-Instruct, N=322026.0533.717,119
MCTSModel=Qwen2.5-3B-Instruct, N=322026.0533.5826,121
Beam SearchModel=Phi-4-mini-Instruct, N=322026.0533.4623,768
Self-ConsistencyModel=Qwen2.5-3B-Instruct, N=322026.0533.2119,765
MCTSModel=Phi-4-mini-Instruct, N=322026.0532.7523,108
Base ModelModel=Qwen2.5-3B-Instruct, N=12026.0529.53617
Base ModelModel=Phi-4-mini-Instruct, N=12026.0523.9535