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

Science Question Answering on Science QA (Task Acc. & Brier Delta)

65Task Accuracy

FINCH

27.76837.43447.156.766May 19, 2026May 27, 2026Jun 4, 2026Jun 13, 2026Jun 21, 2026Jun 29, 2026Jul 8, 2026
Updated 16d ago

Evaluation Results

MethodLinks
2026.05
65-
2026.07
63-
63-
2026.05
62.5-
2026.07
60-
2026.05
58.3-
2026.07
58-
2026.05
57.5-
2026.05
56.7-
55-
2026.05
51.7-
2026.05
49.2-
2026.05
48.3-
2026.05
46.7-
2026.05
29.2-