List your company
ResearchFormerly WizWand

VRP optimization-modeling on VRP Optimization-Modeling Benchmark 4

96.4Pass@1Gemini-3.1-Pro Preview
-2.60823.09648.874.504Jun 3, 2026
Updated 4mo ago

Evaluation results

MethodLinks
Gemini-3.1-Pro PreviewModel type=Closed-source frontier LLM2026.0696.4
VRPCoder-GRPOModel scale=8B, Stage=GRPO2026.0688
VRPCoder-SFTModel scale=8B, Stage=SFT2026.0685.2
Claude-Sonnet-4.5Model type=Closed-source frontier LLM2026.0658.8
DeepSeek-V3.2Model type=Open-source general-purpose LLM2026.0645.6
MiniMax-M2.5Model type=Open-source general-purpose LLM2026.0632.8
SIRL-Gurobi-32BModel type=OR-LLM2026.0630
Qwen2.5-72B-InstructModel type=Open-source general-purpose LLM2026.0627.2
SIRL-Gurobi-8BModel type=OR-LLM2026.0613.2
OptMATH-Qwen2.5-7BModel type=OR-LLM2026.068.4
ORLM-LLaMA-3-8BModel type=OR-LLM2026.067.6
Qwen3-8BModel type=Open-source general-purpose LLM2026.061.2