List your company

Code generation on LiveBench (Pass@K, GSS@K)

20.39Pass@10Qwen2.5-VL-72B-Ins
8.253211.404114.55517.7059Sep 29, 2025

Evaluation results

MethodLinks
Qwen2.5-VL-72B-Ins2025.0920.39—22.37—
GRPOTN=16, AN=1, S/S=186.912025.0911.926.314.1225
GRPO-MATN=4, AN=4, S/S=93.452025.0911.696.7314.710
GRPOTN=4, AN=1, S/S=76.212025.0911.566.5913.76
GRPOTN=8, AN=1, S/S=104.832025.0911.446.5313.3924
Qwen2.5-VL-7B-Ins2025.0910.72—11.31—
Qwen2.5-VL-3B-Ins2025.099.8—11.67—
SFT2025.098.72—10.59—