List your company
ResearchFormerly WizWand

Visual Question Answering on SAT Real

84.1AccuracySandboxVLM
56.95664.00371.0578.097Nov 14, 2025
Updated 6mo ago

Evaluation results

MethodLinks
SandboxVLMMethod Category=Test-time Scaling VLMs2025.1184.1
RoboBrain2.0-32BMethod Category=Training-Based Models, Model Scale=32B2025.1180.3
Robix-32B-BaseMethod Category=Training-Based Models, Model Scale=32B2025.1179.6
Gemini-2.5-ProMethod Category=Generalist VLMs2025.1179.3
MindJourneyMethod Category=Test-time Scaling VLMs2025.1178.7
GPT-5-miniMethod Category=Generalist VLMs2025.1175.4
Claude-Sonnet-4Method Category=Generalist VLMs2025.1175.3
Qwen2.5-VL-32BMethod Category=Generalist VLMs, Model Scale=32B2025.1174.9
Magma-8BMethod Category=Training-Based Models, Model Scale=8B2025.1171.3
Cosmos-Reason1Method Category=Training-Based Models2025.1160.7
Qwen2.5-VL-72BMethod Category=Generalist VLMs, Model Scale=72B2025.1158.7
GPT-4oMethod Category=Generalist VLMs2025.1158.3
VeBrain-8BMethod Category=Training-Based Models, Model Scale=8B2025.1158