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

Instruction Following on IFBench

82.9Pass@1 (Strict)

Nemotron-Cascade-2 30B-A3B

1.956822.970943.98564.9991Dec 15, 2025Dec 30, 2025Jan 15, 2026Jan 31, 2026Feb 15, 2026Mar 3, 2026Mar 19, 2026
Updated 29d ago

Evaluation Results

MethodLinks
82.9
72.6
71.5
70.2
2025.12
68.1
2025.12
55.1
2025.12
47.6
2026.01
47
2025.12
46.3
2026.01
44.3
2026.01
43.2
2026.01
40.5
2026.01
37.8
2025.12
37.3
2025.12
37
2026.01
36.7
2026.01
34.8
2025.12
34.4
2025.12
34
2025.12
32.3
2025.12
29.3
2025.12
29.3
2025.12
28.4
2025.12
27.4
2025.12
26.7
2025.12
23.8
2025.12
22.3
2025.12
22.1
2026.02
20.8
2026.02
20.8
2026.02
20.8
2026.02
20.4
2026.02
20.4
2026.02
20.4
2026.02
20.4
2026.02
20.4
2026.02
20
2026.02
19.6
2026.02
19.6
2026.02
18.8
2026.02
18.8
2026.02
18.8
2026.02
18.8
2026.02
18.4
2026.02
18.4
2026.02
18.4
2026.02
18
2026.02
18
2026.02
18
2026.02
18
2026.02
18
2026.02
17.6
2026.02
17.6
2026.02
17.6
2026.02
16.8
2026.02
15.2
2026.02
14
2026.02
14
2026.02
12.24
2026.02
12
2026.02
11.6
2026.02
11.6
2026.02
11.6
2026.02
11.6
2026.02
11.34
2026.02
11.2
2026.02
10.48
2026.02
10.48
2026.02
9.55
2026.02
8.36
2026.02
7.46
2026.02
5.07