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

Commonsense Reasoning on HellaSwag (Accuracy, Average Accuracy)

86.63Accuracy

SpikingBrain-76B

24.614840.714956.81572.9151Sep 5, 2025Oct 25, 2025Dec 15, 2025Feb 4, 2026Mar 27, 2026May 17, 2026Jul 7, 2026
Updated 17d ago

Evaluation Results

MethodLinks
2025.09
86.63-
2025.09
85.39-
2026.05
79.38-
2026.07
79.01-
2026.07
78.93-
2026.07
78.59-
2026.05
76.95-
2025.09
76.8-
2026.07
76.08-
2026.07
76.08-
2026.07
76.08-
2026.07
76.08-
2026.05
76-
2025.09
75.63-
2026.07
73.73-
2026.07
71.05-
2025.09
68.95-
2026.05
64.75-
2026.05
64.67-
2026.05
64.62-
2026.05
64.55-
2026.05
62.79-
2026.05
62.1-
2026.05
62.1-
2026.05
61.9-
2026.05
61.8-
2026.05
61.3-
2026.05
60.9-
2026.05
60.6-
2026.05
60.38-
2026.05
60-
2026.05
58.4-
2026.05
58.3-
2026.05
58.2-
2026.05
58.1-
2026.05
58-
2026.05
57.9-
2026.05
57.2-
2026.05
57-
2026.05
55.14-
2026.05
52.15-
2026.05
51.8-
2026.05
51.5-
2026.05
51.4-
2026.05
51.3-
2026.05
51.2-
2026.05
51-
2026.05
51-
2026.05
50.81-
2026.05
50.7-
2026.05
47.3-
2026.05
45.9-
2026.05
42.99-
2026.05
41.8-
2026.05
41.2-
2026.05
41.08-
2026.05
40.5-
2026.05
40.4-
2026.04
40.3244.12
2026.05
40.3-
2026.05
40-
2026.05
39.9-
2026.05
39.8-
2026.05
39.3-
2026.05
39.2-
2026.04
38.1843.44
2026.05
37.9-
2026.05
37.13-
2026.05
36.2-
2026.05
36.18-
2026.04
35.1441.61
2026.04
34.4240.74
2026.05
34.3-
2026.05
33.8-
2026.04
33.7540.6
2026.05
33.75-
2026.05
33.1-
2026.05
32.7-
2026.05
32.5-
2026.05
32.3-
2026.05
32.1-
2026.05
31.9-
2026.05
31.1-
2026.05
31-
2026.04
30.939.64
2026.04
30.2638.81
2026.05
30.2-
2026.04
30.1938.25
2026.04
29.5937.25
2026.05
29.53-
2026.04
29.0438.29
2026.04
28.7336.88
2026.04
28.6936.52
2026.05
28.5-
2026.05
28.44-
2026.05
28.28-
2026.04
27.6637.58
2026.05
27.5-
2026.04
27.438.99
2026.05
27-
Showing 100 of 106 rows