List your company

Task Planning on MomaGraph-Bench 1.0 (Tier 1)

83.7AccuracyClaude-4.5-Sonnet
41.47652.43863.474.362Dec 18, 2025

Evaluation results

MethodLinks
Claude-4.5-SonnetModel Type=Closed Source, Reasoning Protocol=w/ Graph2025.1283.7
GPT-5Model Type=Closed Source, Reasoning Protocol=w/ Graph2025.1279.8
Gemini-2.5-ProModel Type=Closed Source, Reasoning Protocol=w/ Graph2025.1279
Claude-4.5-SonnetModel Type=Closed Source, Reasoning Protocol=w/o Graph2025.1277.3
GPT-5Model Type=Closed Source, Reasoning Protocol=w/o Graph2025.1277.3
Gemini-2.5-ProModel Type=Closed Source, Reasoning Protocol=w/o Graph2025.1276.6
MomaGraph-R1Params=7B, Model Type=Open Source, Reasoning Protocol=w/ Graph2025.1276.4
MomaGraph-R1Params=7B, Model Type=Open Source, Reasoning Protocol=w/o Graph2025.1270.2
Qwen2.5-VL-7B-InstructParams=7B, Model Type=Open Source, Reasoning Protocol=w/ Graph2025.1266.3
LLaVA-OnevisionParams=7B, Model Type=Open Source, Reasoning Protocol=w/ Graph2025.1263.8
Qwen2.5-VL-7B-InstructParams=7B, Model Type=Open Source, Reasoning Protocol=w/o Graph2025.1262.1
LLaVA-OnevisionParams=7B, Model Type=Open Source, Reasoning Protocol=w/o Graph2025.1260
DeepSeek-VL2Params=4.5B, Model Type=Open Source, Reasoning Protocol=w/ Graph2025.1256.9
DeepSeek-VL2Params=4.5B, Model Type=Open Source, Reasoning Protocol=w/o Graph2025.1254.2
InternVL2.5Params=8B, Model Type=Open Source, Reasoning Protocol=w/o Graph2025.1253.6
LLaVA-V1.5Params=7B, Model Type=Open Source, Reasoning Protocol=w/ Graph2025.1253.4
LLaVA-V1.5Params=7B, Model Type=Open Source, Reasoning Protocol=w/o Graph2025.1251
InternVL2.5Params=8B, Model Type=Open Source, Reasoning Protocol=w/ Graph2025.1251
InstructBLIPParams=7B, Model Type=Open Source, Reasoning Protocol=w/ Graph2025.1244.1
InstructBLIPParams=7B, Model Type=Open Source, Reasoning Protocol=w/o Graph2025.1243.1