Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Function Calling on ToolUse (test)
Loading...
91.2
Structural Accuracy
RL-Struct
22.872
40.611
58.35
76.089
Nov 29, 2025
Structural Accuracy
JSON Validity
Updated 5mo ago
Evaluation Results
Method
Method
Links
Structural Accuracy
JSON Validity
RL-Struct
Avg. Depth=4, learning...
2025.11
91.2
94.5
SFT
Avg. Depth=4, learning...
2025.11
70.1
78.5
Zero-shot
Avg. Depth=4, learning...
2025.11
25.5
45
Feedback
Search any
task
Search any
task
