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

Science Reasoning on ARC

89.6Accuracy

MENTOR

-3.58420.60844.868.992Oct 5, 2025Oct 23, 2025Nov 11, 2025Nov 30, 2025Dec 19, 2025Jan 7, 2026Jan 26, 2026
Updated 23d ago

Evaluation Results

MethodLinks
2025.10
89.6
2025.10
86.7
2025.10
86
2025.10
86
2026.01
84.9
2026.01
84.2
2026.01
83.8
2026.01
83.7
2026.01
83.4
2026.01
83.2
2026.01
82.8
2026.01
82
2026.01
81.6
2025.10
80.8
2026.01
79.7
2025.10
77.3
2025.10
74.9
2025.10
72.5
2025.10
72.5
2025.10
72.1
2025.10
70.7
2025.10
70.4
2025.10
70.3
2025.10
23.6
2025.10
0