List your company

Question Answering on SimpleQA, TriviaQA, GPQA, Math500, GSM8K, and CommonsenseQA (OOD)

42AURCRLVR
37.8438.924041.08Jul 3, 2026

Evaluation results

MethodLinks
RLVRModel=Llama-3.1-8B2026.0742
BASEModel=Llama-3.1-8B2026.0741
RLCRModel=Llama-3.1-8B2026.0740
RLSRModel=Llama-3.1-8B2026.0738