List your company

Task Planning on MomaGraph-Bench Tier 4 1.0

69.5AccuracyClaude-4.5-Sonnet
30.29240.47150.6560.829Dec 18, 2025

Evaluation results

MethodLinks
Claude-4.5-SonnetReasoning Protocol=w/ Graph2025.1269.5
MomaGraph-R1Params=7B, Reasoning Protocol=w/ Graph2025.1268.1
Claude-4.5-SonnetReasoning Protocol=w/o Graph2025.1265.2
Gemini-2.5-ProReasoning Protocol=w/ Graph2025.1265.2
GPT-5Reasoning Protocol=w/ Graph2025.1263.6
Gemini-2.5-ProReasoning Protocol=w/o Graph2025.1260.8
MomaGraph-R1Params=7B, Reasoning Protocol=w/o Graph2025.1260.8
Qwen2.5-VL-7B-InstructParams=7B, Reasoning Protocol=w/ Graph2025.1259
Qwen2.5-VL-7B-InstructParams=7B, Reasoning Protocol=w/o Graph2025.1256.5
GPT-5Reasoning Protocol=w/o Graph2025.1254.5
DeepSeek-VL2Params=4.5B, Reasoning Protocol=w/ Graph2025.1245.4
LLaVA-OnevisionParams=7B, Reasoning Protocol=w/o Graph2025.1243.4
LLaVA-OnevisionParams=7B, Reasoning Protocol=w/ Graph2025.1243.4
LLaVA-V1.5Params=7B, Reasoning Protocol=w/ Graph2025.1240.9
DeepSeek-VL2Params=4.5B, Reasoning Protocol=w/o Graph2025.1240.9
InternVL2.5Params=8B, Reasoning Protocol=w/ Graph2025.1240.9
LLaVA-V1.5Params=7B, Reasoning Protocol=w/o Graph2025.1238.9
InstructBLIPParams=7B, Reasoning Protocol=w/ Graph2025.1236.3
InternVL2.5Params=8B, Reasoning Protocol=w/o Graph2025.1233.3
InstructBLIPParams=7B, Reasoning Protocol=w/o Graph2025.1231.8