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

Reasoning on BBH (Accuracy)

74.99BBH Accuracy

NTele-R1-32B

24.019637.252350.48563.7177Jul 6, 2025Sep 4, 2025Nov 3, 2025Jan 3, 2026Mar 4, 2026May 3, 2026Jul 3, 2026
Updated 19d ago

Evaluation Results

MethodLinks
74.99
2025.08
72.74
2025.10
71.02
2025.10
70.95
2025.10
66.32
2026.07
65
2026.07
63.8
2026.07
63.6
2026.07
63.4
2026.07
63.1
2026.07
62.8
2026.07
62.7
2026.07
62.3
2026.07
62
2025.07
58.2
2025.07
57.9
2025.07
57.8
2025.07
56.3
2026.07
56.3
2025.10
55.37
2026.07
55.1
2026.07
54.9
2026.07
54.7
2026.07
54.4
2026.07
54.2
2026.07
54
2025.10
53.51
2026.07
53.5
2026.07
53.2
2025.07
52.8
2025.07
52.7
2025.07
52.6
2025.07
51.7
2025.07
50.8
2025.07
50.4
2025.07
47.5
2025.07
46.7
2025.10
43.66
2025.07
40.9
2026.06
39.53
2025.10
39.45
2026.06
39.35
2026.06
39.3
2026.06
39.2
2026.06
38.58
2026.06
36.2
2026.06
31.82
2025.10
30.72
2025.10
30.26
2026.06
30.22
2026.06
25.98