List your company

Code on MBPP (Average Performance)

67.19Average PerformanceAIPO
17.852430.661243.4756.2788May 8, 2026May 11, 2026May 14, 2026May 17, 2026May 20, 2026May 23, 2026May 26, 2026

Evaluation results

MethodLinks
AIPOStudent LLM=DeepSeek-R1-Distill-Qwen-1.5B, Teacher LLM=Qwen3-30B-A3B-Instruct-2507, Runs (k)=42026.0567.19
GRPOStudent LLM=DeepSeek-R1-Distill-Qwen-1.5B, Teacher LLM=Qwen3-30B-A3B-Instruct-2507, Runs (k)=42026.0565.05
OriginalStudent LLM=DeepSeek-R1-Distill-Qwen-1.5B, Teacher LLM=Qwen3-30B-A3B-Instruct-2507, Runs (k)=42026.0560.12
SFTStudent LLM=DeepSeek-R1-Distill-Qwen-1.5B, Teacher LLM=Qwen3-30B-A3B-Instruct-2507, Runs (k)=42026.0555.51
DARTBase Model=Qwen3-0.6B2026.0534.91
STaRBase Model=Qwen3-0.6B2026.0534.6
GRPOBase Model=Qwen3-0.6B2026.0534.52
BaseBase Model=Qwen3-0.6B2026.0534.01
DARTBase Model=Qwen2.5-0.5B-Instruct2026.0534.01
TESSYBase Model=Qwen3-0.6B2026.0531.11
Original-SFTBase Model=Qwen3-0.6B2026.0530.52
GRPOBase Model=Qwen2.5-0.5B-Instruct2026.0529.98
STaRBase Model=Qwen2.5-0.5B-Instruct2026.0529.88
BaseBase Model=Qwen2.5-0.5B-Instruct2026.0529.72
TESSYBase Model=Qwen2.5-0.5B-Instruct2026.0528.88
Original-SFTBase Model=Qwen2.5-0.5B-Instruct2026.0519.75