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

Science Question Answering on ARC Challenge (test)

94.3Accuracy

large teacher

4.23627.6185174.382Sep 28, 2025Nov 4, 2025Dec 12, 2025Jan 18, 2026Feb 25, 2026Apr 3, 2026May 11, 2026
Updated 1d ago

Evaluation Results

MethodLinks
2026.05
94.3---
2026.05
92.6---
90.9098.50.55
2026.05
87.54---
2026.05
87.26---
2026.05
87.11---
2026.05
87---
2026.05
86.95---
2026.05
86.92---
2026.05
86.69---
2026.05
86.69---
2026.05
86.25---
2026.05
85.07---
850.2980.43
2026.02
70.5---
2026.02
68.5---
2026.02
68.4---
2026.02
68.3---
2026.02
68.2---
2026.02
67.9---
2026.02
64---
2026.02
63.1---
2026.02
62.3---
2026.02
61.8---
2026.02
60.6---
2026.02
58.8---
2026.02
58.3---
2026.05
48.8---
2026.05
46.9---
2026.05
46.5---
2026.05
46.3---
2026.05
45.5---
2026.05
45.4---
2026.05
37.4---
2026.05
36.2---
2026.05
35.6---
2026.05
35.5---
2026.05
34.7---
2026.05
34.5---
2026.05
29.66---
2026.05
17.1---
2026.05
7.7---