List your company

Mathematical Reasoning on AIME 2024 (avg@8, pass@8)

48.33Average Score (k=8)Mixed
40.103642.239344.37546.5107Jun 3, 2026

Evaluation results

MethodLinks
MixedFramework=TD-Grokking2026.0648.3380
DynamicFramework=TD-Grokking2026.0647.9180
QuestAFramework=GRPO2026.0647.576.67
AblationFramework=GRPO2026.0646.6773.33
SFTFramework=GRPO2026.0643.7573.33
Base2026.0642.0870
VanillaFramework=GRPO2026.0642.0876.67
Scaf-GRPOFramework=GRPO2026.0642.0873.33
Sub-onlyFramework=TD-Grokking2026.0640.4273.33