Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Tool Use on Berkeley Function Calling Leaderboard (BFCL) v3
Loading...
78.9
Accuracy
Claude-Opus-4.5
30.332
42.941
55.55
68.159
Jun 16, 2026
Accuracy
Updated 1mo ago
Evaluation Results
Method
Method
Links
Accuracy
Claude-Opus-4.5
2026.06
78.9
Gemini-3-Pro
2026.06
78.2
Qwen3-235B-A22B-Instruct-2507
2026.06
71.2
Kimi-K2-Instruct-0905
2026.06
70.3
DeepSeek-V3.2
2026.06
68.8
Qwen3-Coder-480B-A35B-Instruct
2026.06
68.7
GLM-4.7
2026.06
64.8
GPT-5.1
2026.06
64.4
Qwen2.5-Coder-32B-Instruct
2026.06
62.3
Qwen2.5-Coder-14B-Instruct
2026.06
59.9
Kimi-Dev-72B
2026.06
55.5
Qwen2.5-Coder-7B-Instruct
2026.06
54.2
LoopCoder-v2
R (number of refinemen...
2026.06
40.1
LoopCoder-v2
R (number of refinemen...
2026.06
39.5
LoopCoder-v2
R (number of refinemen...
2026.06
36.3
LoopCoder-v2
R (number of refinemen...
2026.06
32.2
Feedback
Search any
task
Search any
task