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

Science QA on ARC easy

77.9Accuracy

Vanilla

31.51643.55855.667.642May 28, 2026Jun 1, 2026Jun 6, 2026Jun 11, 2026Jun 15, 2026Jun 20, 2026Jun 25, 2026
Updated 26d ago

Evaluation Results

MethodLinks
2026.05
77.9
2026.05
77.8
2026.05
77.8
2026.05
77.4
2026.05
77.2
2026.05
74.6
2026.05
74.5
2026.05
74.4
2026.05
74
2026.05
73.7
2026.06
45.8
2026.06
45.5
2026.06
43.1
2026.06
42.1
2026.06
37.7
2026.06
37.6
2026.06
36.4
2026.06
35.8
2026.06
35.4
2026.06
35
2026.06
34.9
2026.06
34.7
2026.06
33.3