List your company

Real-world Multimodal Interaction on RealWorldQA

76.5RealWorldQA ScoreGPT-4o
59.44463.87268.372.728Dec 27, 2025

Evaluation results

MethodLinks
GPT-4oOpen Data=false, Super-Image (SI)=false2025.1276.5
MAmmoTH-VLLLM Backbone=Qwen2.5-7B, Open Data=true, Super-Image (SI)=true2025.1271.3
InternVL3LLM Backbone=Qwen2.5-7B, Open Data=false, Super-Image (SI)=false2025.1270.8
Molmo-8B-DLLM Backbone=Qwen2 7B, Open Data=true, Super-Image (SI)=false2025.1270.7
Gemini-1.5 ProOpen Data=false, Super-Image (SI)=false2025.1270.4
MAmmoTH-VLLLM Backbone=Qwen2.5-7B, Open Data=true, Super-Image (SI)=false2025.1269.9
Qwen2.5-VLLLM Backbone=Qwen2.5-7B, Open Data=false, Super-Image (SI)=false2025.1268.5
DeepSeek-VL2LLM Backbone=DeepSeek-MoE 27B, Open Data=false, Super-Image (SI)=false2025.1268.4
Dream-VLLLM Backbone=Dream 7B, Open Data=true, Super-Image (SI)=true2025.1268.4
LLaVA-OVLLM Backbone=Qwen2-7B, Open Data=true, Super-Image (SI)=false2025.1266.3
Dream-VLLLM Backbone=Dream 7B, Open Data=true, Super-Image (SI)=false2025.1266.3
LLaVA-OVLLM Backbone=Qwen2-7B, Open Data=true, Super-Image (SI)=true2025.1265.5
Cambrian-1LLM Backbone=LLaMA3-8B, Open Data=true, Super-Image (SI)=false2025.1264.2
LLaDA-VLLM Backbone=LLaDA 8B, Open Data=true, Super-Image (SI)=false2025.1263.2
Claude 3.5 SonnetOpen Data=false, Super-Image (SI)=false2025.1260.1