List your company

Mathematical Reasoning on Minerva Math (pass@8)

28.3Pass@8 RateNo Curriculum
3.8610.20516.5522.895Feb 13, 2026

Evaluation results

MethodLinks
No CurriculumBackbone=Qwen2.5-Math-7B, Reward Setting=Oracle (w. Verifier)2026.0228.3
VI-CuRLBackbone=Qwen2.5-Math-7B, Reward Setting=Oracle (w. Verifier)2026.0228.3
VCRLBackbone=Qwen2.5-Math-7B, Reward Setting=Oracle (w. Verifier)2026.0224.3
AdaRFTBackbone=Qwen2.5-Math-7B, Reward Setting=Oracle (w. Verifier)2026.0222.8
AdaRFTBackbone=Qwen2.5-Math-1.5B, Reward Setting=Oracle (w. Verifier)2026.0221.7
VCRLBackbone=Qwen2.5-Math-1.5B, Reward Setting=Oracle (w. Verifier)2026.0218.7
AdaRFTBackbone=DeepSeek-R1-Distill-Qwen-1.5B, Reward Setting=Oracle (w. Verifier)2026.0217.6
VI-CuRLBackbone=Qwen2.5-Math-1.5B, Reward Setting=Oracle (w. Verifier)2026.0217.1
VI-CuRLBackbone=DeepSeek-R1-Distill-Qwen-1.5B, Reward Setting=Oracle (w. Verifier)2026.0216.6
No CurriculumBackbone=Qwen2.5-Math-1.5B, Reward Setting=Oracle (w. Verifier)2026.0216.2
BaseBackbone=Qwen2.5-Math-1.5B, Reward Setting=No RL2026.0215.5
No CurriculumBackbone=DeepSeek-R1-Distill-Qwen-1.5B, Reward Setting=Oracle (w. Verifier)2026.0215.5
BaseBackbone=DeepSeek-R1-Distill-Qwen-1.5B, Reward Setting=No RL2026.0214
VI-CuRLBackbone=Llama3.2-3B-Instruct, Reward Setting=Oracle (w. Verifier)2026.0214
BaseBackbone=Qwen2.5-Math-7B, Reward Setting=No RL2026.0211.8
VCRLBackbone=DeepSeek-R1-Distill-Qwen-1.5B, Reward Setting=Oracle (w. Verifier)2026.0210.8
AdaRFTBackbone=Llama3.2-3B-Instruct, Reward Setting=Oracle (w. Verifier)2026.028.8
No CurriculumBackbone=Llama3.2-3B-Instruct, Reward Setting=Oracle (w. Verifier)2026.028.4
VCRLBackbone=Llama3.2-3B-Instruct, Reward Setting=Oracle (w. Verifier)2026.028.1
BaseBackbone=Llama3.2-3B-Instruct, Reward Setting=No RL2026.024.8