Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Recipe Generation on Recipe Gen (test)
Loading...
89.7
Structural Accuracy
RL-Struct
43.732
55.666
67.6
79.534
Nov 29, 2025
Structural Accuracy
JSON Validity
Updated 5mo ago
Evaluation Results
Method
Method
Links
Structural Accuracy
JSON Validity
RL-Struct
Avg. Depth=3, learning...
2025.11
89.7
92.1
SFT
Avg. Depth=3, learning...
2025.11
65.4
72.1
Zero-shot
Avg. Depth=3, learning...
2025.11
45.5
82.1
Feedback
Search any
task
Search any
task
