List your company
ResearchFormerly WizWand

Social Video Reasoning on VAGUE (test)

77.4AccuracyGemini-3.0-Flash
32.284843.997455.7167.4226Jul 27, 2025
Updated 6mo ago

Evaluation results

MethodLinks
Gemini-3.0-FlashStrategy=CoCoT, Model Category=Reasoning VLMs, Thinking mode=true2025.0777.4
Gemini-3.0-FlashStrategy=Direct, Model Category=Reasoning VLMs, Thinking mode=true2025.0773.05
Gemini-3.0-FlashStrategy=CoT, Model Category=Reasoning VLMs, Thinking mode=true2025.0772.27
Gemini-2.5-ProStrategy=CoCoT, Model Category=Standard VLMs2025.0767.62
GPT-4oStrategy=CoCoT, Model Category=Standard VLMs2025.0767.43
Claude-3.5-SonnetStrategy=CoCoT, Model Category=Standard VLMs2025.0767.3
Claude-3.5-SonnetStrategy=Direct, Model Category=Standard VLMs2025.0762.92
OpenAI o1-fullStrategy=CoT, Model Category=Reasoning VLMs2025.0762.57
GPT-5.2-HighStrategy=CoCoT, Model Category=Reasoning VLMs2025.0762.02
GPT-4oStrategy=Direct, Model Category=Standard VLMs2025.0761.6
OpenAI o1-fullStrategy=CoCoT, Model Category=Reasoning VLMs2025.0761.59
GPT-4oStrategy=CoT, Model Category=Standard VLMs2025.0760
Gemini-3.0-FlashStrategy=CCoT, Model Category=Reasoning VLMs, Thinking mode=true2025.0760
GPT-5.2-HighStrategy=CoT, Model Category=Reasoning VLMs2025.0759.99
OpenAI o1-fullStrategy=Direct, Model Category=Reasoning VLMs2025.0759.82
Claude-3.5-SonnetStrategy=CoT, Model Category=Standard VLMs2025.0759.52
GPT-5.2-HighStrategy=Direct, Model Category=Reasoning VLMs2025.0759.21
Gemini-2.5-ProStrategy=CoT, Model Category=Standard VLMs2025.0758.32
LLaVA-OneVision-7BStrategy=CoCoT, Model Category=Open-Source VLMs2025.0754.65
LLaVA-OneVision-7BStrategy=CoT, Model Category=Open-Source VLMs2025.0753.31
Gemini-2.5-ProStrategy=Direct, Model Category=Standard VLMs2025.0753.25
Claude-3.5-SonnetStrategy=CCoT, Model Category=Standard VLMs2025.0752.02
Idefics3-8BStrategy=Direct, Model Category=Open-Source VLMs2025.0750.98
LLaVA-v1.6-7BStrategy=CoCoT, Model Category=Open-Source VLMs2025.0750.21
GPT-4oStrategy=CCoT, Model Category=Standard VLMs2025.0750.12
Molmo-7BStrategy=CoCoT, Model Category=Open-Source VLMs2025.0750
LLaVA-OneVision-7BStrategy=Direct, Model Category=Open-Source VLMs2025.0749.73
OpenAI o1-fullStrategy=CCoT, Model Category=Reasoning VLMs2025.0748.84
Idefics3-8BStrategy=CoT, Model Category=Open-Source VLMs2025.0748.54
Idefics3-8BStrategy=CoCoT, Model Category=Open-Source VLMs2025.0748.24
Molmo-7BStrategy=Direct, Model Category=Open-Source VLMs2025.0748
LLaVA-v1.6-7BStrategy=CoT, Model Category=Open-Source VLMs2025.0747.44
GPT-5.2-HighStrategy=CCoT, Model Category=Reasoning VLMs2025.0747.31
Gemini-2.5-ProStrategy=CCoT, Model Category=Standard VLMs2025.0746.7
Molmo-7BStrategy=CoT, Model Category=Open-Source VLMs2025.0746
LLaVA-v1.6-7BStrategy=Direct, Model Category=Open-Source VLMs2025.0746
Qwen2-VL-7BStrategy=CoCoT, Model Category=Open-Source VLMs2025.0744.42
LLaVA-OneVision-7BStrategy=CCoT, Model Category=Open-Source VLMs2025.0744.3
OpenAI o3-miniStrategy=CoCoT, Model Category=Reasoning VLMs2025.0743.64
Idefics3-8BStrategy=CCoT, Model Category=Open-Source VLMs2025.0742.43
OpenAI o3-miniStrategy=CoT, Model Category=Reasoning VLMs2025.0740.21
Molmo-7BStrategy=CCoT, Model Category=Open-Source VLMs2025.0740.19
LLaVA-v1.6-7BStrategy=CCoT, Model Category=Open-Source VLMs2025.0740.1
Qwen2-VL-7BStrategy=Direct, Model Category=Open-Source VLMs2025.0738.52
Qwen2-VL-7BStrategy=CoT, Model Category=Open-Source VLMs2025.0738.49
OpenAI o3-miniStrategy=Direct, Model Category=Reasoning VLMs2025.0738.15
OpenAI o3-miniStrategy=CCoT, Model Category=Reasoning VLMs2025.0734.43
Qwen2-VL-7BStrategy=CCoT, Model Category=Open-Source VLMs2025.0734.02