List your company

Mathematics on AIME 24 (AVG@32, Pass@32)

74.38AVG@32Projected
29.961641.493353.02564.5567Jul 3, 2026

Evaluation results

MethodLinks
ProjectedScale=14B, Category=Cross-Domain Merging2026.0774.3893.33
OR-ZeroScale=14B, Category=Math Expert2026.0774.2793.33
Best Single-Domain ExpertScale=14B2026.0774.2793.33
TIES MergingScale=14B, Category=Cross-Domain Merging2026.0773.5493.33
DARE + TIESScale=14B, Category=Cross-Domain Merging2026.0773.0690
DeepCoderScale=14B, Category=Code Expert2026.0771.0486.67
Task ArithmeticScale=14B, Category=Cross-Domain Merging2026.0771.0493.33
Distill-Qwen-14BScale=14B, Category=Single-Domain Reference2026.0767.7190
ProjectedScale=1.5B, Category=Cross-Domain Merging2026.0743.4476.67
TIES MergingScale=1.5B, Category=Cross-Domain Merging2026.0742.0873.33
DeepScaleRScale=1.5B, Category=Math Expert2026.0740.3176.67
Best Single-Domain ExpertScale=1.5B2026.0740.3176.67
DARE + TIESScale=1.5B, Category=Cross-Domain Merging2026.0740.0573.33
Archer-CodeScale=1.5B, Category=Code Expert2026.0739.4876.67
Task ArithmeticScale=1.5B, Category=Cross-Domain Merging2026.0736.2563.33
Distill-Qwen-1.5BScale=1.5B, Category=Single-Domain Reference2026.0731.6776.67