List your company
ResearchFormerly WizWand

VRP optimization-modeling on VRP Optimization-Modeling Benchmark 3

93.24Pass@1VRPCoder-GRPO
-3.729621.445246.6271.7948Jun 3, 2026
Updated 4mo ago

Evaluation results

MethodLinks
VRPCoder-GRPOModel scale=8B, Stage=GRPO2026.0693.24
Gemini-3.1-Pro PreviewModel type=Closed-source frontier LLM2026.0691.89
VRPCoder-SFTModel scale=8B, Stage=SFT2026.0682.43
Claude-Sonnet-4.5Model type=Closed-source frontier LLM2026.0679.73
DeepSeek-V3.2Model type=Open-source general-purpose LLM2026.0651.35
MiniMax-M2.5Model type=Open-source general-purpose LLM2026.0617.57
Qwen2.5-72B-InstructModel type=Open-source general-purpose LLM2026.0612.16
ORLM-LLaMA-3-8BModel type=OR-LLM2026.0612.16
OptMATH-Qwen2.5-7BModel type=OR-LLM2026.062.7
Qwen3-8BModel type=Open-source general-purpose LLM2026.061.35
SIRL-Gurobi-32BModel type=OR-LLM2026.061.35
SIRL-Gurobi-8BModel type=OR-LLM2026.060