Our new X account is live! Follow @wizwand_team for updates
Home
/
Benchmarks
Visual Understanding on MMStar
Loading...
56.86
Accuracy (Clean)
Robust-R1 (SFT and RL)
29.404
36.532
43.66
50.788
Dec 19, 2025
Accuracy (Clean)
Accuracy (Intensity 25%)
Accuracy (Intensity 50%)
Accuracy (Intensity 100%)
Updated 4d ago
Evaluation Results
Method
Method
Links
Accuracy (Clean)
Accuracy (Intensity 25%)
Accuracy (Intensity 50%)
Accuracy (Intensity 100%)
Robust-R1 (SFT and RL)
Category=Ours, Trainin...
2025.12
56.86
54.4
53.6
49.53
Robust-R1 (SFT)
Category=Ours, Trainin...
2025.12
55.2
53
51.86
49.53
Qwen2.5-VL-3B
Category=General MLLM
2025.12
54.73
52.9
51.86
48.66
InternVL-4B
Category=General MLLM
2025.12
51.53
50.26
49.6
46.93
Gemma3-4B
Category=General MLLM
2025.12
43.93
43.2
42.6
41.33
Robust CLIP
Category=Robust MLLM
2025.12
33
32.26
31.8
29.46
TeCoA
Category=Robust MLLM
2025.12
30.46
30.6
30.73
28.06
Feedback
Search any
task
Search any
task