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

Causal Reasoning on XCOPA

94.4Accuracy

PaLM 2

46.76859.13471.583.866May 17, 2023Nov 17, 2023May 19, 2024Nov 20, 2024May 23, 2025Nov 23, 2025May 27, 2026
Updated 5d ago

Evaluation Results

MethodLinks
2023.05
94.4
2023.05
89.9
2026.01
71.2
2026.01
70
2026.05
65.69
2025.02
65
2026.05
63.82
2026.04
62
2026.05
61.82
2026.04
61.6
2026.01
61.2
2026.01
60.8
2026.04
60.8
2026.04
60.2
2026.05
59.76
2026.04
59.4
2026.04
59.2
2026.04
58.6
2026.05
58.35
2026.05
58.02
2026.01
57.2
2025.02
56.9
2025.02
56.4
2025.06
56
2026.05
55.8
2026.05
55.76
2025.06
55.7
2025.06
55.6
2025.06
55.5
2026.05
55.49
2025.06
55.3
2025.06
55.2
2025.06
55.1
2025.06
55
2026.05
54.96
2026.05
54.8
2025.06
54.7
2025.06
54.4
2025.06
54.1
2025.06
53.9
2025.06
53.9
2025.06
53.8
2025.06
53.6
2026.05
53.51
2025.06
53.4
2026.01
53.2
2026.05
53.2
2026.05
53
2026.01
52.2
2026.01
52
2026.05
52
2026.01
51.8
2026.01
51.2
2026.01
51
2026.01
48.6