Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Anomaly Type Classification on M3-AD Average across scenes
Loading...
52.7
Type Score
QWEN-3-VL-INSTRUCT
-0.86
13.045
26.95
40.855
Feb 10, 2026
Type Score
Updated 1mo ago
Evaluation Results
Method
Method
Links
Type Score
QWEN-3-VL-INSTRUCT
Category=RA-MONITOR, P...
2026.02
52.7
QWEN-3-VL-INSTRUCT
Category=RA-MONITOR, P...
2026.02
51.2
GPT-5.1-MINI
Category=COMMERCIAL, P...
2026.02
49.8
GEMINI-2.5-FLASH-LITE
Category=COMMERCIAL, P...
2026.02
44.4
GPT-5.1-NANO
Category=COMMERCIAL, P...
2026.02
37.4
QWEN-3-VL-INSTRUCT
Category=OPEN-SOURCE,...
2026.02
36.8
INTERN-VL-3.5
Category=OPEN-SOURCE,...
2026.02
36.2
QWEN-3-VL-THINKING
Category=THINKING, Par...
2026.02
34.9
QWEN-3-VL-THINKING
Category=THINKING, Par...
2026.02
34.2
INTERN-VL-3.5
Category=OPEN-SOURCE,...
2026.02
32.7
QWEN-3-VL-INSTRUCT
Category=OPEN-SOURCE,...
2026.02
32.6
QWEN-3-VL-INSTRUCT
Category=OPEN-SOURCE,...
2026.02
27.1
QWEN-2.5-VL-INSTRUCT
Category=OPEN-SOURCE,...
2026.02
25.5
LLAVA-ONEVISION-SI
Category=OPEN-SOURCE,...
2026.02
24.2
QWEN-2.5-VL-INSTRUCT
Category=OPEN-SOURCE,...
2026.02
22.5
ANOMALY-R1
Category=OPEN-SOURCE,...
2026.02
20.6
QWEN-2.5-VL-INSTRUCT
Category=OPEN-SOURCE,...
2026.02
20.3
QWEN-2-VL-INSTRUCT
Category=OPEN-SOURCE,...
2026.02
16.9
QWEN-2-VL-INSTRUCT
Category=OPEN-SOURCE,...
2026.02
1.2
Feedback
Search any
task
Search any
task