List your company

Reasoning on Average (MATH500, AMC23, AIME24, AIME25, GPQA-d)

87.2AccuracyDDC
66.08871.56977.0582.531May 14, 2026

Evaluation results

MethodLinks
DDCBackbone=Qwen3-32B, Voting size budget=5122026.0587.24.9
D-LBackbone=DeepSeek-R1-0528-Qwen3-8B, Voting size budget=5122026.0587.116.4
DDCBackbone=DeepSeek-R1-0528-Qwen3-8B, Voting size budget=5122026.0586.75.7
D-LBackbone=Qwen3-32B, Voting size budget=5122026.0586.119
SCBackbone=DeepSeek-R1-0528-Qwen3-8B, Voting size budget=5122026.0585.248.5
ACBackbone=DeepSeek-R1-0528-Qwen3-8B, Voting size budget=5122026.0585.217.1
D-HBackbone=DeepSeek-R1-0528-Qwen3-8B, Voting size budget=5122026.0585.228.5
D-HBackbone=Qwen3-32B, Voting size budget=5122026.058523.2
SCBackbone=Qwen3-32B, Voting size budget=5122026.0584.741.1
ACBackbone=Qwen3-32B, Voting size budget=5122026.0584.413.7
DDCBackbone=Qwen3-4B, Voting size budget=5122026.0583.44.9
DDCBackbone=Qwen3-8B, Voting size budget=5122026.0581.45.1
D-LBackbone=Qwen3-8B, Voting size budget=5122026.0581.315.8
D-HBackbone=Qwen3-8B, Voting size budget=5122026.0581.324
SCBackbone=Qwen3-8B, Voting size budget=5122026.0580.838.4
D-LBackbone=Qwen3-4B, Voting size budget=5122026.0580.519.1
ACBackbone=Qwen3-8B, Voting size budget=5122026.0579.113.1
D-HBackbone=Qwen3-4B, Voting size budget=5122026.0575.828.3
SCBackbone=Qwen3-4B, Voting size budget=5122026.0574.845
ACBackbone=Qwen3-4B, Voting size budget=5122026.0574.814.9
DDCBackbone=Qwen3-1.7B, Voting size budget=5122026.0570.18
D-LBackbone=Qwen3-1.7B, Voting size budget=5122026.0569.436.3
D-HBackbone=Qwen3-1.7B, Voting size budget=5122026.056950.4
SCBackbone=Qwen3-1.7B, Voting size budget=5122026.056769.3
ACBackbone=Qwen3-1.7B, Voting size budget=5122026.0566.928.4