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

Physical Interaction Question Answering on PIQA

94.9Accuracy

Human Performance

76.781.42586.1590.875May 2, 2020Apr 26, 2021Apr 21, 2022Apr 16, 2023Apr 10, 2024Apr 5, 2025Mar 31, 2026
Updated 3d ago

Evaluation Results

MethodLinks
94.9-
2026.01
90.3-
2026.01
89.7-
2026.01
89.6-
2026.01
89.6-
2020.05
89.5-
2026.01
89.3-
2026.01
89.1-
2020.05
88.9-
2024.01
88.5-
2024.04
87.8-
2024.04
87.6-
2026.01
87.6-
2026.01
87-
2024.04
86.9-
2024.04
86.8-
2024.04
86.7-
2026.01
86.7-
2023.11
86.1-
2026.01
86.1-
2026.01
85.9-
2026.01
85.9-
2026.01
85.7-
2026.01
85.4-
2023.11
85-
2026.01
84.6-
2026.01
84.6-
2024.01
84.5-
2026.01
84.4-
2026.01
84.3-
2023.11
83.9-
2026.01
83.9-
2026.01
83.7-
2026.01
83.5-
2024.04
83.4-
2026.01
83.3-
2023.11
83.2-
2024.04
83.2-
2023.10
83-
2024.01
83-
2024.04
82.7-
2026.01
82.7-
2026.01
82.6-
2024.04
82.3-
2023.11
82.2-
2024.04
82.2-
2026.01
82.2-
2024.04
82.1-
2024.04
81.8-
2024.04
81.8-
2024.01
81.7-
2024.04
81.6-
2024.04
81.6-
2024.04
81.1-
2024.04
81.1-
2024.04
81.1-
2024.04
80.9-
2024.04
80.9-
2026.01
80.9-
2023.10
80.8-
2024.04
80.7-
2026.01
80.5-
2024.01
80.3-
2026.01
80.3-
2024.01
80.2-
2026.02
80.1-
2026.02
79.93.2925
2026.02
79.84.3504
2026.02
79.7-
2026.02
79.6-
2020.05
79.4-
2024.01
79.2-
2024.01
79.2-
2024.03
79.18-
2024.03
79.18-
2024.04
79.1-
2026.02
79.13.0585
2024.01
79-
2024.03
78.92-
2024.01
78.8-
2026.02
78.8-
2026.02
78.84.078
2024.03
78.76-
2026.01
78.73-
2024.04
78.7-
2024.03
78.64-
2024.01
78.6-
2024.01
78.6-
2026.01
78.4-
2026.01
78.35-
2025.05
78.1-
2024.01
78-
2026.02
78-
2026.03
77.93-
2020.05
77.9-
2023.10
77.9-
2026.02
77.9-
2026.02
77.9-
2024.01
77.6-
2020.05
77.4-
Showing 100 of 333 rows