List your company

Puzzle on Reasoning Gym

43.98Avg@4AIPO
1.70412.679523.65534.6305May 8, 2026

Evaluation results

MethodLinks
AIPOModel=Qwen2.5-32B-Instruct2026.0543.98
GRPOModel=Qwen2.5-32B-Instruct2026.0534.24
SFTModel=Qwen2.5-32B-Instruct2026.0531.13
OriginalModel=Qwen2.5-32B-Instruct2026.0528.56
AIPOStudent LLM=DeepSeek-R1-Distill-Qwen-1.5B, Teacher LLM=Qwen3-30B-A3B-Instruct-2507, Runs (k)=42026.0516.44
GRPOStudent LLM=DeepSeek-R1-Distill-Qwen-1.5B, Teacher LLM=Qwen3-30B-A3B-Instruct-2507, Runs (k)=42026.0513.53
SFTStudent LLM=DeepSeek-R1-Distill-Qwen-1.5B, Teacher LLM=Qwen3-30B-A3B-Instruct-2507, Runs (k)=42026.0510.98
OriginalStudent LLM=DeepSeek-R1-Distill-Qwen-1.5B, Teacher LLM=Qwen3-30B-A3B-Instruct-2507, Runs (k)=42026.053.33