List your company

Mathematical Reasoning on AIME 1983-2025 (combined)

13.28AccuracySD-E²
5.39687.44349.4911.5366Jan 25, 2026

Evaluation results

MethodLinks
SD-E²2026.0113.2816.72.6710
GRPO-CFEE (count)reward_type=count2026.019.8710.952.7713
GRPO-CFLstrategy_type=single-trace2026.018.34——610
Multi-strategy promptstrategy_type=multi-trace2026.016.749.333.16819
Single-strategy promptstrategy_type=single-trace2026.015.7——502