Our new X account is live! Follow @wizwand_team for updates
Home
/
Benchmarks
Reasoning on BBH (pass@1)
Loading...
69.92
BBH Pass@1
SCF-RKL
22.6624
34.9312
47.2
59.4688
Feb 12, 2026
BBH Pass@1
Updated 4d ago
Evaluation Results
Method
Method
Links
BBH Pass@1
SCF-RKL
Models=Fuse
2026.02
69.92
w/o Merging
Models=Code
2026.02
69.29
Dare Task Arithmetic
Models=Fuse
2026.02
66.17
Task Arithmetic
Models=Fuse
2026.02
66.15
w/o Merging
Model=Meta-Llama-3-8B-...
2026.02
65.78
Dare Ties Merging
Models=Fuse
2026.02
64.75
Dare Ties Merging
Model=Fused
2026.02
63.82
Task Arithmetic
Model=Fused
2026.02
63.63
Ties Merging
Models=Fuse
2026.02
60.7
SCE
Models=Fuse
2026.02
60.53
Ties Merging
Model=Fused
2026.02
57.89
w/o Merging
Model=MAmmoTH2-8B-Plus...
2026.02
53.92
SCF-RKL
Model=Fused
2026.02
51.64
w/o Merging
Models=Math
2026.02
48.15
Dare Task Arithmetic
Model=Fused
2026.02
26.98
SCE
Model=Fused
2026.02
24.48
Feedback
Search any
task
Search any
task