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

Multiple Choice Question Answering on PIQA

80.5Accuracy

Original

50.44458.24766.0573.853Nov 8, 2025Dec 16, 2025Jan 23, 2026Mar 3, 2026Apr 10, 2026May 18, 2026Jun 26, 2026
Updated 26d ago

Evaluation Results

MethodLinks
2026.05
80.5
2026.05
80.4
2026.05
80.4
2026.05
80.4
2026.05
79.8
2026.05
79.7
2026.05
79.7
2026.05
79.6
2026.05
79.6
2026.05
79.4
2026.05
79.1
2026.05
79
2026.05
78.5
2026.05
78.2
2026.05
78.1
2026.05
78.1
2026.05
78
2026.05
78
2026.05
77.9
2026.05
77.8
2026.05
77.5
2026.05
77.3
2026.05
77.2
2026.05
76.9
2026.05
76.2
2026.05
75.8
2026.05
75.1
2025.11
74.92
2026.05
74.6
2026.05
74.4
2025.11
74.32
2025.11
73.61
2025.11
73.45
2025.11
73.34
2025.11
73.3
2025.11
73.1
2025.11
73.07
2025.11
72.8
2025.11
72.4
2026.05
71
2026.05
70.4
2026.05
70.4
2025.11
69.6
2025.11
69.5
2025.11
69.1
2025.11
69.1
2025.11
68.7
2025.11
68.6
2025.11
68.4
2026.05
68.3
2025.11
67.8
2026.06
67.2
2026.05
67.1
2025.11
67
2026.06
64.6
2026.06
63.8
2026.05
63
2026.05
62.7
2026.05
62.2
2026.05
62
2026.06
61.5
2026.05
60.3
2026.05
58.27
2026.05
57.2
2026.05
55.6
2026.05
55.33
2026.05
51.6