List your company

Question Answering on Out-of-domain QA (ARC-C, GPQA, MMLU-Pro) (test)

84.7ARC-C ScoreExGRPO
80.33281.46682.683.734May 1, 2026

Evaluation results

MethodLinks
ExGRPOSource domain=mathematical reasoning, re-tuning=none, transfer_mode=direct2026.0584.737.452.958.3
DoTS (ExGRPO + ReLIFT)Source domain=mathematical reasoning, re-tuning=none, transfer_mode=direct2026.0584.642.953.960.5
ReLIFTSource domain=mathematical reasoning, re-tuning=none, transfer_mode=direct2026.0582.836.953.957.9
LUFFYSource domain=mathematical reasoning, re-tuning=none, transfer_mode=direct2026.0580.539.95357.8