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

Question Answering on ARC-Challenge (Normalized Accuracy)

46.93Normalized Accuracy

CALDERA

-2.917210.023922.96535.9061May 29, 2024Sep 7, 2024Dec 18, 2024Mar 30, 2025Jul 10, 2025Oct 20, 2025Jan 30, 2026
Updated 1mo ago

Evaluation Results

MethodLinks
2024.05
46.93
2024.05
46.59
2024.05
44.8
2026.01
38.6
2026.01
37
2026.01
36.3
2026.01
34.4
2026.01
28.8
2026.01
26.8
2026.01
25.3
2026.01
25.1
2025.12
5.9
2025.12
5.7
2025.12
5
2025.12
3.3
2025.12
1.7
2025.12
-1