List your company

Mathematical Reasoning on AIME 24 (MV/WMV Acc, Tokens)

89.2Accuracy (MV)DeepConf
76.51279.80683.186.394Jun 30, 2026

Evaluation results

MethodLinks
DeepConfBackbone=DeepSeek-8B, branching factor n=322026.0689.29016.3
ASCBackbone=DeepSeek-8B, branching factor n=322026.0686—10.1
Flex-Fork-thinkBackbone=DeepSeek-8B, branching factor n=32, seed path length l0=2,0482026.068686.69.8
DeepConfBackbone=Qwen3-8B, branching factor n=322026.0681.881.211.1
Flex-Fork-thinkBackbone=Qwen3-8B, branching factor n=32, seed path length l0=2,0482026.0681.881.87
ASCBackbone=Qwen3-8B, branching factor n=322026.0680.1—10.4
DeepConfBackbone=Phi-4-RP-14B, branching factor n=322026.0680808.9
ASCBackbone=Phi-4-RP-14B, branching factor n=322026.0677.8—6.4
Flex-Fork-thinkBackbone=Phi-4-RP-14B, branching factor n=32, seed path length l0=2,0482026.067776.66.7