Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Function Calling on BFCL Multi-turn V4
Loading...
60
Base Success Rate
AgenticQwen-30B-A3B
34.52
41.135
47.75
54.365
Apr 23, 2026
Base Success Rate
Miss Function Rate
Miss Parameter Rate
Long Context Success Rate
Updated 1mo ago
Evaluation Results
Method
Method
Links
Base Success Rate
Miss Function Rate
Miss Parameter Rate
Long Context Success Rate
AgenticQwen-30B-A3B
Reasoning Method=non-t...
2026.04
60
52
29
55.5
Qwen3-235B-A22B-Instruct
Reasoning Method=non-t...
2026.04
58.5
47.5
35
54
AgenticQwen-8B
Reasoning Method=non-t...
2026.04
56
47.5
33.5
40.5
Qwen3-32B
Reasoning Method=non-t...
2026.04
50.5
43
30.5
33
Qwen3-30B-A3B-Instruct
Reasoning Method=non-t...
2026.04
47
14
28
45.5
Qwen3-8B
Reasoning Method=non-t...
2026.04
35.5
35
20.5
21.5
Feedback
Search any
task
Search any
task