Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
VRP optimization-modeling on VRP Full 700 problem set
Loading...
95
Pass@1
Gemini-3.1-Pro Preview
-3.2072
22.2889
47.785
73.2811
Jun 3, 2026
Pass@1
Updated 1mo ago
Evaluation Results
Method
Method
Links
Pass@1
Gemini-3.1-Pro Preview
Model type=Closed-sour...
2026.06
95
VRPCoder-GRPO
Model scale=8B, Stage=...
2026.06
93
VRPCoder-SFT
Model scale=8B, Stage=SFT
2026.06
88.43
Claude-Sonnet-4.5
Model type=Closed-sour...
2026.06
64.71
DeepSeek-V3.2
Model type=Open-source...
2026.06
36.29
MiniMax-M2.5
Model type=Open-source...
2026.06
24
Qwen2.5-72B-Instruct
Model type=Open-source...
2026.06
18.57
SIRL-Gurobi-32B
Model type=OR-LLM
2026.06
15
ORLM-LLaMA-3-8B
Model type=OR-LLM
2026.06
5.71
SIRL-Gurobi-8B
Model type=OR-LLM
2026.06
5.57
OptMATH-Qwen2.5-7B
Model type=OR-LLM
2026.06
3.71
Qwen3-8B
Model type=Open-source...
2026.06
0.57
Feedback
Search any
task
Search any
task