Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Tool Calling on BFCL Simple Python v1 (test)
Loading...
93.5
Accuracy
PrefillShare
69.58
75.79
82
88.21
Feb 12, 2026
Accuracy
Updated 1mo ago
Evaluation Results
Method
Method
Links
Accuracy
PrefillShare
Backbone=Qwen3-8B-Base...
2026.02
93.5
Full-FT
Backbone=Qwen3-8B-Base...
2026.02
93.3
PrefillShare
Backbone=LLaMA3.1-8B,...
2026.02
90.7
Full-FT
Backbone=LLaMA3.1-8B,...
2026.02
90
Qwen3-8B-Base
KV Sharing=Inherent
2026.02
81.5
LLaMA3.1-8B
KV Sharing=Inherent
2026.02
70.5
Feedback
Search any
task
Search any
task