List your company

Room Navigation on Room Navigation Complex Instruction - CI

66Success RateSceneDiver
21.59233.12144.6556.179Jun 2, 2026

Evaluation results

MethodLinks
SceneDiverBackbone=gemini-2.5-flash, Model Category=Closed-Source2026.0666
ThinkingBackbone=gemini-2.5-flash, Model Category=Closed-Source2026.0663.3
Multi-ResBackbone=gemini-2.5-flash, Model Category=Closed-Source2026.0661.3
SoMBackbone=gemini-2.5-flash, Model Category=Closed-Source2026.0660.7
Base ModelBackbone=gemini-2.5-flash, Model Category=Closed-Source2026.0660
SceneDiverBackbone=Qwen2.5-VL-32B-Instruct-AWQ, Model Category=Open-Source2026.0653.3
Multi-ResBackbone=Qwen2.5-VL-32B-Instruct-AWQ, Model Category=Open-Source2026.0649.3
SceneDiverBackbone=gpt-4o-mini, Model Category=Closed-Source2026.0649.3
SceneDiverBackbone=doubao-seed-1.6-flash, Model Category=Closed-Source2026.0648.7
SoMBackbone=Qwen2.5-VL-32B-Instruct-AWQ, Model Category=Open-Source2026.0648
Base ModelBackbone=Qwen2.5-VL-32B-Instruct-AWQ, Model Category=Open-Source2026.0646.7
VCDBackbone=Qwen2.5-VL-32B-Instruct-AWQ, Model Category=Open-Source2026.0645.3
ThinkingBackbone=doubao-seed-1.6-flash, Model Category=Closed-Source2026.0643.3
Multi-ResBackbone=doubao-seed-1.6-flash, Model Category=Closed-Source2026.0642
Multi-ResBackbone=gpt-4o-mini, Model Category=Closed-Source2026.0641.3
SoMBackbone=doubao-seed-1.6-flash, Model Category=Closed-Source2026.0640.7
Base ModelBackbone=gpt-4o-mini, Model Category=Closed-Source2026.0638.7
Base ModelBackbone=doubao-seed-1.6-flash, Model Category=Closed-Source2026.0638
SceneDiverBackbone=Qwen2.5-VL-7B-Instruct-AWQ, Model Category=Open-Source2026.0637.3
SoMBackbone=gpt-4o-mini, Model Category=Closed-Source2026.0636
Multi-ResBackbone=Qwen2.5-VL-7B-Instruct-AWQ, Model Category=Open-Source2026.0634
SceneDiverBackbone=InternVL2.5-8B, Model Category=Open-Source2026.0633.3
VCDBackbone=Qwen2.5-VL-7B-Instruct-AWQ, Model Category=Open-Source2026.0632.7
Base ModelBackbone=Qwen2.5-VL-7B-Instruct-AWQ, Model Category=Open-Source2026.0632
SoMBackbone=Qwen2.5-VL-7B-Instruct-AWQ, Model Category=Open-Source2026.0631.3
Multi-ResBackbone=InternVL2.5-8B, Model Category=Open-Source2026.0630.7
VCDBackbone=InternVL2.5-8B, Model Category=Open-Source2026.0628
Base ModelBackbone=InternVL2.5-8B, Model Category=Open-Source2026.0624
SoMBackbone=InternVL2.5-8B, Model Category=Open-Source2026.0623.3