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

Reasoning on HellaSwag

91.84HellaSwag Accuracy

Mistral-Small

60.078468.324276.5784.8158Mar 6, 2024Jul 14, 2024Nov 22, 2024Apr 2, 2025Aug 11, 2025Dec 20, 2025Apr 30, 2026
Updated 7d ago

Evaluation Results

MethodLinks
2025.05
91.84---
2026.04
89.8---
2026.04
88.51---
2025.05
88.28---
2025.05
87.91---
2025.05
87.81---
2025.05
87.75---
2025.05
87.62---
2025.05
87.42---
2025.05
87.36---
2025.05
87.36---
2025.05
87.31---
2025.05
87.3---
2025.05
87.29---
2026.04
86.7---
86.31-1-
2024.03
85.9---
2024.03
85.8---
2026.02
85.6-2.31-
2026.02
85.31-1.51-
84.97-1.26-
2024.03
83.5---
2025.05
83.34---
2024.03
83---
2026.04
82.69---
2024.03
81.9---
2024.03
81.6---
81.59-1-
2026.04
81.33---
2026.04
80.9---
2024.03
80.3---
2024.03
80.3---
2025.05
79.83---
2026.02
79.56---
2024.03
79.3---
2024.03
79.2---
2026.04
79.13---
2025.08
79.1---
79.01-1.5-
2024.03
78.9---
2026.04
78.67---
2026.04
78.57---
2024.03
78.1---
2025.08
78---
2024.03
77.5---
2025.08
77.5---
2026.04
77.43---
2024.03
76.5---
2024.03
76.3---
2026.02
76.19-1.49-
2026.02
75.71-2.39-
2024.03
75---
2024.03
74.78---
2025.05
74.02---
2024.03
74---
2024.03
73.7---
2026.01
73.65---
2025.08
73.6---
2025.05
73.59---
2025.05
73.45---
2025.05
73.36---
2024.03
73.1---
2026.04
73---
2026.04
72.96---
2025.05
72.79---
2025.05
72.53---
2025.05
72.16---
2025.05
71.89---
2026.01
71.77---
2025.08
71.3---
2024.03
71.26---
2026.01
71.1---
2025.08
70.5---
2024.03
70.2---
2024.03
70.2---
2026.01
70.06---
2026.01
69.35---
69.02---
2025.06
68.7---
2026.01
68.4---
2026.01
68.25---
2024.03
67.76---
2024.03
67.56---
2025.06
66.7---
2024.03
66.64---
2025.06
66.5---
2026.01
66.42---
2024.03
64.39---
2024.03
64.1---
2025.06
64---
2025.06
63.9---
2025.08
63.7---
2026.01
63.49---
2026.01
63.33---
2025.06
63---
2026.01
62.68---
2024.03
61.9---
2026.01
61.79---
2026.01
61.39---
2025.06
61.3---
Showing 100 of 209 rows