Our new X account is live! Follow @wizwand_team for updates
Home
/
Benchmarks
Vision-text safety classification on MSSBench Embodied
Loading...
61.97
AUPRC (Prompt)
SEA-Guard-4B
49.5212
52.7531
55.985
59.2169
Feb 2, 2026
AUPRC (Prompt)
AUPRC (Response)
Updated 4d ago
Evaluation Results
Method
Method
Links
AUPRC (Prompt)
AUPRC (Response)
SEA-Guard-4B
Zero-shot=true
2026.02
61.97
59.71
SEA-Guard-8B
Zero-shot=true
2026.02
57.43
60.97
SEA-Guard-12B
Zero-shot=true
2026.02
53.1
59.61
Gemma3-12B-IT
Zero-shot=true
2026.02
51
53.94
Gemma3-4B-IT
Zero-shot=true
2026.02
50.79
54.13
Qwen3-VL-4B-IT
Zero-shot=true
2026.02
50.66
58.58
SEA-LION-v4-Qwen-VL
Zero-shot=true
2026.02
50.33
57.24
SEA-LION-v4-Qwen-VL
Zero-shot=true, varian...
2026.02
50.17
55.62
Qwen3-VL-8B-IT
Zero-shot=true
2026.02
50
59.41
Feedback
Search any
task
Search any
task