List your company

Multimodal Anomaly Detection on MMAD 1-shot

95.24Anomaly DiscriminationHuman (expert)
48.190460.405272.6284.8348May 19, 2026

Evaluation results

MethodLinks
Human (expert)Scale=-2026.0595.247592.3183.3394.286.1180.3786.65
Gemini-2.5-flashScale=-2026.0593.3869.8863.376.4181.5794.048280.08
Human (ordinary)Scale=-2026.0586.966.2585.5871.2581.5289.5869.7278.69
Gemini-2.5-proScale=-2026.0583.0773.8667.279.9786.2794.8883.0881.19
Kimi-VL-A3BScale=16B2026.0572.9353.4959.6672.3981.7491.9185.8974
Qwen2.5-VLScale=7B2026.0571.3954.3561.1765.8179.3291.4484.4372.56
Gemini-1.5-proScale=-2026.0568.6360.1258.5670.3882.4689.282.2573.09
GPT-4oScale=-2026.0568.6365.855.6273.2183.4194.9882.874.92
InternVL3.5Scale=8B2026.0567.549.3757.958.0777.6672.0181.1166.3
JUDOScale=7B2026.0565.0474.7473.0184.5689.4194.0487.5881.2
GPT-5-miniScale=-2026.0564.167.3569.0779.0286.7293.9683.3777.65
AnomalyR1Scale=7B2026.0560.9364.8170.7279.0685.5293.1286.9177.29
Claude-3.5-sonnetScale=-2026.0560.1460.1448.8167.1379.1185.1979.8368.36
MiMo-VLScale=8B2026.0554.4559.5660.7771.578.4890.5681.670.99
LLaVA-OneVisionScale=7B2026.0551.7746.1341.8562.1969.7390.3180.9363.27
Random ChanceScale=-2026.055025252525252528.57