List your company

Mathematical Reasoning on MATH-500 (Pass@1 and Avg. Pass@1)

80.2Pass@1DS
67.09670.49873.977.302Feb 13, 2026

Evaluation results

MethodLinks
DSModel=Qwen2.5-Math-7B, Avg. Rollouts=2.5x2026.0280.239.4
MoPPSModel=Qwen2.5-Math-7B, Avg. Rollouts=1.0x2026.0280.238.6
PACED-RLModel=Qwen2.5-Math-7B, Avg. Rollouts=1.0x2026.028040.1
LILOModel=Qwen2.5-Math-7B, Avg. Rollouts=4.0x2026.0278.440.1
GRPOModel=Qwen2.5-Math-7B, Avg. Rollouts=1.0x2026.0277.637.2
FlowRLModel=Qwen2.5-Math-7B, Avg. Rollouts=1.0x2026.0276.436.5
LILOModel=Qwen2.5-Math-1.5B, Avg. Rollouts=4.0x2026.0273.231.2
PACED-RLModel=Qwen2.5-Math-1.5B, Avg. Rollouts=1.0x2026.0273.232.1
DSModel=Qwen2.5-Math-1.5B, Avg. Rollouts=2.0x2026.0272.831.2
MoPPSModel=Qwen2.5-Math-1.5B, Avg. Rollouts=1.0x2026.0271.630.4
GRPOModel=Qwen2.5-Math-1.5B, Avg. Rollouts=1.0x2026.0270.629.1
FlowRLModel=Qwen2.5-Math-1.5B, Avg. Rollouts=1.0x2026.0267.627.1