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

Vision-Language Medical Reasoning on PathVQA

85.37Accuracy (%)

DS-RL + GTP

53.213261.561669.9178.2584Apr 13, 2026Apr 26, 2026May 9, 2026May 22, 2026Jun 4, 2026Jun 17, 2026Jun 30, 2026
Updated 24d ago

Evaluation Results

MethodLinks
2026.06
85.37--
2026.06
85.34--
2026.06
85.19--
2026.06
77.28--
2026.06
77.19--
2026.06
77.16--
2026.06
74.93--
2026.04
72.324.522.5
2026.06
71.98--
2026.04
71.45416
2026.04
70.083.815.2
2026.04
69.924.222.68
2026.04
68.921.26
2026.04
68.17936
2026.04
67.430.35
2026.04
67.31.14.4
2026.04
67.068.534
2026.04
66.6214
2026.06
65.76--
2026.04
65.641.26.48
2026.04
65.121248
2026.06
64.99--
2026.04
64.152.50.15
2026.06
63.8--
2026.04
62.330.90.1
2026.04
62.171560
2026.06
62.05--
2026.04
60.080.81.5
2026.04
58.310.80.05
2026.04
54.450.70.05
2025.08
-3,648-
2025.08
-3,648-
2025.08
-7,901-
2025.08
-17,927-
2025.08
-23,226-
2025.08
-3,253-
2025.08
-3,648-
2025.08
-4,301-
2025.08
-17,927-
2025.08
-23,226-
2025.08
-7,325-