Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Tool Use on BFCL V3
Loading...
62.1
Accuracy
Qwen2.5-Instruct-14B with TOUCAN-SFT + COVERT-RL
30.276
38.538
46.8
55.062
Dec 31, 2025
Jan 16, 2026
Feb 2, 2026
Feb 19, 2026
Mar 7, 2026
Mar 24, 2026
Apr 10, 2026
Accuracy
Updated 4d ago
Evaluation Results
Method
Method
Links
Accuracy
Qwen2.5-Instruct-14B with TOUCAN-SFT + COVERT-RL
Model Scale=14B, Train...
2026.04
62.1
Qwen3 4B
Thinking Mode=true, FC...
2025.12
61.7
Qwen2.5-Instruct-14B with COVERT-RL
Model Scale=14B, Train...
2026.04
59.9
Qwen2.5-Instruct-14B with TOUCAN-SFT
Model Scale=14B, Train...
2026.04
59.5
Qwen2.5-Instruct-7B with TOUCAN-SFT + COVERT-RL
Model Scale=7B, Traini...
2026.04
59.1
Youtu-LLM 2B
Thinking Mode=true, FC...
2025.12
58
Qwen2.5-Instruct-7B with COVERT-RL
Model Scale=7B, Traini...
2026.04
57.2
Qwen2.5-Instruct-7B with TOUCAN-SFT
Model Scale=7B, Traini...
2026.04
57
Qwen2.5-Instruct-14B
Model Scale=14B, Train...
2026.04
56.5
Qwen3 1.7B
Thinking Mode=true, FC...
2025.12
55.5
Qwen2.5-Instruct-7B
Model Scale=7B, Traini...
2026.04
54.1
SmolLM3 3B
Thinking Mode=true, FC...
2025.12
31.5
Feedback
Search any
task
Search any
task