List your company
ResearchFormerly WizWand

Common Sense Reasoning on WorldSense

64.6AccuracyGemini-2.5-Pro
-2.1170415.2037332.524549.84527Jul 31, 2024Nov 17, 2024Mar 7, 2025Jun 25, 2025Oct 13, 2025Jan 31, 2026May 21, 2026
Updated 5mo ago

Evaluation results

MethodLinks
Gemini-2.5-ProModel Accessibility=Proprietary2026.0564.6
Gemini-2.0-FlashModel Accessibility=Proprietary2026.0556.2
LatentOmniModel Accessibility=Open-source, Training/Reasoning Strategy=Latent reasoning2026.0548.9
OmniVinciModel Accessibility=Open-source2026.0548.2
Qwen2.5-Omni-7B + Vanilla SFTModel Accessibility=Open-source, Training/Reasoning Strategy=Vanilla SFT2026.0547.5
HumanOmniV2-7BModel Accessibility=Open-source2026.0547.1
Qwen2.5-Omni-7B + Explicit Text CoTModel Accessibility=Open-source, Training/Reasoning Strategy=Explicit Text CoT2026.0546.6
Qwen2.5-Omni-7BModel Accessibility=Open-source, Training/Reasoning Strategy=Base2026.0545.4
Baichuan-Omni-1.5Model Accessibility=Open-source2026.0543.3
GPT-4oModel Accessibility=Proprietary2026.0542.6
VITA-1.5-7BModel Accessibility=Open-source2026.0536.9
MiniCPM-o-7BModel Accessibility=Open-source2026.0529.7
VideoLLaMA2-7BModel Accessibility=Open-source2026.0525.4
Llama 3 405B2024.070.637
Llama 3 70B2024.070.611
Mixtral 8x22B2024.070.515
Gemma 7B2024.070.46
Llama 3 8B2024.070.455
Mistral 7B2024.070.449