Our new X account is live! Follow @wizwand_team for updates
Home
/
Benchmarks
Function Calling on BFCL Multi-Turn Base v3 (val)
Loading...
43
Avg@8
CuES
5.4976
15.2338
24.97
34.7062
Dec 1, 2025
Avg@8
Greedy Success Rate
Updated 4d ago
Evaluation Results
Method
Method
Links
Avg@8
Greedy Success Rate
CuES
Params=14B
2025.12
43
44.15
Qwen3
Params=32B
2025.12
39.58
41
Qwen3
Params=14B
2025.12
35.94
30.7
Qwen2.5
Params=32B
2025.12
30.17
30.5
Qwen3
Params=8B
2025.12
30.13
27.5
Qwen2.5
Params=14B
2025.12
25.69
31.5
Qwen2.5
Params=7B
2025.12
17.75
20
Qwen3
Params=4B
2025.12
9.94
10
Qwen2.5
Params=3B
2025.12
6.94
7
Feedback
Search any
task
Search any
task