Share your thoughts, 1 month free Claude Pro on usSee more
WorkDL logo mark

Safety and Helpfulness Evaluation on SPA-VL

85.8Safety Score

SAFER-STEER

38.94851.111563.27575.4385Mar 18, 2026
Updated 1mo ago

Evaluation Results

MethodLinks
2026.03
85.879.17
2026.03
85.6678.3
2026.03
85.6678.3
2026.03
83.477.03
2026.03
83.476.42
2026.03
81.773.02
2026.03
76.0578.54
2026.03
76.0469.62
2026.03
72.4561.32
2026.03
71.1379.81
2026.03
69.4373.2
2026.03
68.8773.21
2026.03
65.0963.02
2026.03
59.8168.24
2026.03
48.6853.2
2026.03
46.2340.94
2026.03
43.2133.58
2026.03
40.7543.4