Our new X account is live! Follow @wizwand_team for updates
Home
/
Benchmarks
Real-world Multimodal Interaction on RealWorldQA
Loading...
76.5
RealWorldQA Score
GPT-4o
59.444
63.872
68.3
72.728
Dec 27, 2025
RealWorldQA Score
Updated 3d ago
Evaluation Results
Method
Method
Links
RealWorldQA Score
GPT-4o
Open Data=false, Super...
2025.12
76.5
MAmmoTH-VL
LLM Backbone=Qwen2.5-7...
2025.12
71.3
InternVL3
LLM Backbone=Qwen2.5-7...
2025.12
70.8
Molmo-8B-D
LLM Backbone=Qwen2 7B,...
2025.12
70.7
Gemini-1.5 Pro
Open Data=false, Super...
2025.12
70.4
MAmmoTH-VL
LLM Backbone=Qwen2.5-7...
2025.12
69.9
Qwen2.5-VL
LLM Backbone=Qwen2.5-7...
2025.12
68.5
DeepSeek-VL2
LLM Backbone=DeepSeek-...
2025.12
68.4
Dream-VL
LLM Backbone=Dream 7B,...
2025.12
68.4
LLaVA-OV
LLM Backbone=Qwen2-7B,...
2025.12
66.3
Dream-VL
LLM Backbone=Dream 7B,...
2025.12
66.3
LLaVA-OV
LLM Backbone=Qwen2-7B,...
2025.12
65.5
Cambrian-1
LLM Backbone=LLaMA3-8B...
2025.12
64.2
LLaDA-V
LLM Backbone=LLaDA 8B,...
2025.12
63.2
Claude 3.5 Sonnet
Open Data=false, Super...
2025.12
60.1
Feedback
Search any
task
Search any
task