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

Physical Reasoning on PROST

29.6Accuracy

GPT-NeoX

21.17623.36325.5527.737Apr 14, 2022Oct 24, 2022May 5, 2023Nov 14, 2023May 25, 2024Dec 4, 2024Jun 15, 2025
Updated 20d ago

Evaluation Results

MethodLinks
2022.04
29.6
2025.06
29.57
2022.04
28.8
2025.06
28.22
2025.06
28.19
2025.06
27.62
2022.04
27.2
2022.04
27
2022.04
26.7
2022.04
26.7
2022.04
25.7
2022.04
25.7
2022.04
25.4
2022.04
25.2
2025.06
24.41
2025.06
24.26
2025.06
24.03
2025.06
23.6
2022.04
23
2022.04
21.5