Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Agentic Reasoning on BFCL v4 (non-live and live)
Loading...
86.45
Accuracy
CopT
77.1732
79.5816
81.99
84.3984
May 19, 2026
Accuracy
Token Count
Updated 14d ago
Evaluation Results
Method
Method
Links
Accuracy
Token Count
CopT
Backbone=Qwen2.5-35B-A...
2026.05
86.45
168
CopT
Backbone=Qwen2.5-35B-A...
2026.05
86.17
130
CoT
Backbone=Qwen2.5-35B-A3B
2026.05
85.77
235
CopT
Backbone=Qwen2.5-2B, R...
2026.05
78.37
164
CopT
Backbone=Qwen2.5-2B, R...
2026.05
78.01
139
CoT
Backbone=Qwen2.5-2B
2026.05
77.53
234
Feedback
Search any
task
Search any
task