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

Success Prediction on Eval-Actions 1.0 (test)

91Accuracy

QwenVL3-4B

54.80864.20473.682.996Jan 26, 2026
Updated 1mo ago

Evaluation Results

MethodLinks
2026.01
9192.988.8
2026.01
919390.1
2026.01
90.692.589.6
2026.01
90.692.888.5
2026.01
90.292.488.2
2026.01
9092.188.1
2026.01
8386.481.2
2026.01
81.784.281
2026.01
818480.3
2026.01
78.483.276
2026.01
76.181.273.8
2026.01
69.373.968.2
2026.01
69.174.367.6
2026.01
66.471.365.5
2026.01
62.376.850
2026.01
62.167.561
2026.01
56.266.951.2