List your company

Mathematical Reasoning on AIME 2025 (avg@4, pass@4)

59.17Average Score (avg@4)PIPO-SFT + OPD
33.1739.9246.6753.42May 26, 2026

Evaluation results

MethodLinks
PIPO-SFT + OPDBackbone=Qwen3.5-9B, Response Budget=32K-slot2026.0559.1783.33
RegularBackbone=Qwen3.5-9B, Response Budget=32K-slot2026.0553.3366.67
PIPO-SFTBackbone=Qwen3.5-9B, Response Budget=32K-slot2026.0551.6776.67
PIPO-SFT + OPDBackbone=Qwen3.5-4B, Response Budget=32K-slot2026.055076.67
RegularBackbone=Qwen3.5-4B, Response Budget=32K-slot2026.0549.1763.33
Eagle-2Backbone=Qwen3.5-9B, Response Budget=32K-slot2026.0549.1763.33
PIPO-SFTBackbone=Qwen3.5-4B, Response Budget=32K-slot2026.0542.560
Eagle-2Backbone=Qwen3.5-4B, Response Budget=32K-slot2026.0540.8360
MTPBackbone=Qwen3.5-9B, Response Budget=32K-slot2026.054050
MTPBackbone=Qwen3.5-4B, Response Budget=32K-slot2026.0534.1743.33