Share your thoughts, 1 month free Claude Pro on usSee more

VRP optimization-modeling on VRP Optimization-Modeling Benchmark 3

93.24Pass@1

VRPCoder-GRPO

Updated 1mo ago

Evaluation Results

Method	Links
VRPCoder-GRPO 2026.06		93.24
Gemini-3.1-Pro Preview 2026.06		91.89
VRPCoder-SFT 2026.06		82.43
Claude-Sonnet-4.5 2026.06		79.73
DeepSeek-V3.2 2026.06		51.35
MiniMax-M2.5 2026.06		17.57
Qwen2.5-72B-Instruct 2026.06		12.16
ORLM-LLaMA-3-8B 2026.06		12.16
OptMATH-Qwen2.5-7B 2026.06		2.7
Qwen3-8B 2026.06		1.35
SIRL-Gurobi-32B 2026.06		1.35
SIRL-Gurobi-8B 2026.06		0