List your company

Task Planning on MomaGraph-Bench Tier 2 1.0

71.9AccuracyMomaGraph-R1
40.1848.41556.6564.885Dec 18, 2025

Evaluation results

MethodLinks
MomaGraph-R1Params=7B, Reasoning Protocol=w/ Graph2025.1271.9
Claude-4.5-SonnetReasoning Protocol=w/ Graph2025.1270.3
Gemini-2.5-ProReasoning Protocol=w/ Graph2025.1269.5
GPT-5Reasoning Protocol=w/ Graph2025.1268.2
Claude-4.5-SonnetReasoning Protocol=w/o Graph2025.1267
Gemini-2.5-ProReasoning Protocol=w/o Graph2025.1265.8
MomaGraph-R1Params=7B, Reasoning Protocol=w/o Graph2025.1265.8
GPT-5Reasoning Protocol=w/o Graph2025.1263.4
Qwen2.5-VL-7B-InstructParams=7B, Reasoning Protocol=w/o Graph2025.1258.5
Qwen2.5-VL-7B-InstructParams=7B, Reasoning Protocol=w/ Graph2025.1258.5
LLaVA-OnevisionParams=7B, Reasoning Protocol=w/ Graph2025.1256
DeepSeek-VL2Params=4.5B, Reasoning Protocol=w/ Graph2025.1253.6
InternVL2.5Params=8B, Reasoning Protocol=w/ Graph2025.1253
LLaVA-OnevisionParams=7B, Reasoning Protocol=w/o Graph2025.1252.4
DeepSeek-VL2Params=4.5B, Reasoning Protocol=w/o Graph2025.1251.2
InternVL2.5Params=8B, Reasoning Protocol=w/o Graph2025.1251.2
LLaVA-V1.5Params=7B, Reasoning Protocol=w/ Graph2025.1248.7
LLaVA-V1.5Params=7B, Reasoning Protocol=w/o Graph2025.1246.3
InstructBLIPParams=7B, Reasoning Protocol=w/o Graph2025.1242.6
InstructBLIPParams=7B, Reasoning Protocol=w/ Graph2025.1241.4