Our new X account is live! Follow @wizwand_team for updates
Home
/
Benchmarks
Multimodal Multi-choice on RWQA
Loading...
70.5
Accuracy
SkiLa-V
41.588
49.094
56.6
64.106
Dec 18, 2025
Accuracy
Updated 3d ago
Evaluation Results
Method
Method
Links
Accuracy
SkiLa-V
2025.12
70.5
SkiLa
2025.12
69.3
GPT-4o
2025.12
68.6
Direct SFT
2025.12
68.1
LVR 7B*
Model Size=7B, Tested...
2025.12
67.7
Qwen2.5-VL 7B
Model Size=7B
2025.12
67.4
GPT-4o-mini
2025.12
67.1
Vision-R1 7B*
Model Size=7B, Tested...
2025.12
67.1
GPT-4v
2025.12
63
Gemma3 27B
Model Size=27B
2025.12
62.5
ROSS 7B
Model Size=7B
2025.12
58.7
Cambrian 13B
Model Size=13B
2025.12
58.6
Claude3.7-Sonnet
2025.12
55.4
Janus-Pro 7B
Model Size=7B
2025.12
42.7
Feedback
Search any
task
Search any
task