List your company

Mathematical Reasoning on In-Distribution Reasoning Suite (AIME 24, AIME 25, AMC, MATH-500, Minerva)

36AIME 24 Pass@32DYPO
10.5217.13523.7530.365Apr 10, 2026

Evaluation results

MethodLinks
DYPOTraining Category=SFT and RL, Backbone=Qwen2.5-Math-7B, Inference Temperature=0.6, Option Shuffling=true2026.043628.76789.242.452.5
Oat-ZeroTraining Category=Reinforcement Learning, Backbone=Qwen2.5-Math-7B, Inference Temperature=0.6, Option Shuffling=true2026.0433.411.961.27834.643.8
CHORDTraining Category=SFT and RL, Backbone=Qwen2.5-Math-7B, Inference Temperature=0.6, Option Shuffling=true2026.0431.224.466.889.439.350.2
SRFTTraining Category=SFT and RL, Backbone=Qwen2.5-Math-7B, Inference Temperature=0.6, Option Shuffling=true2026.0430.72669.888.439.750.9
LUFFYTraining Category=SFT and RL, Backbone=Qwen2.5-Math-7B, Inference Temperature=0.6, Option Shuffling=true2026.0429.423.165.687.637.548.6
ReLIFTTraining Category=SFT and RL, Backbone=Qwen2.5-Math-7B, Inference Temperature=0.6, Option Shuffling=true2026.0428.322.965.187.437.148.2
SuperRLTraining Category=SFT and RL, Backbone=Qwen2.5-Math-7B, Inference Temperature=0.6, Option Shuffling=true2026.0428.121.663.986.436.447.3
SimpleRL-ZeroTraining Category=Reinforcement Learning, Backbone=Qwen2.5-Math-7B, Inference Temperature=0.6, Option Shuffling=true2026.04276.854.9762537.9
SFT → RLTraining Category=SFT and RL, Backbone=Qwen2.5-Math-7B, Inference Temperature=0.6, Option Shuffling=true2026.0425.823.162.787.239.747.7
RLTraining Category=Reinforcement Learning, Backbone=Qwen2.5-Math-7B, Inference Temperature=0.6, Option Shuffling=true2026.0425.115.36284.439.345.2
SFTTraining Category=Supervised Fine-Tuning, Backbone=Qwen2.5-Math-7B, Inference Temperature=0.6, Option Shuffling=true2026.0422.222.352.882.640.844.1
PRIME-ZeroTraining Category=Reinforcement Learning, Backbone=Qwen2.5-Math-7B, Inference Temperature=0.6, Option Shuffling=true2026.041712.85481.43940.8
OpenReasoner-ZeroTraining Category=Reinforcement Learning, Backbone=Qwen2.5-Math-7B, Inference Temperature=0.6, Option Shuffling=true2026.0416.51552.182.433.139.8
Qwen2.5-Math-7BTraining Category=Base Model, Backbone=Qwen2.5-Math-7B, Inference Temperature=0.6, Option Shuffling=true2026.0411.54.931.343.67.419.7