Our new X account is live! Follow @wizwand_team for updates
Home
/
Benchmarks
Full-mode K2C on FK2C XF dataset 26-key (test)
Loading...
84.6
P@1
Spark + RLHF-IME binary
9.408
28.929
48.45
67.971
Nov 2, 2023
P@1
Updated 4d ago
Evaluation Results
Method
Method
Links
P@1
Spark + RLHF-IME binary
Base Model=Spark, Trai...
2023.11
84.6
Spark + RLHF-IME rank
Base Model=Spark, Trai...
2023.11
82.8
Spark + SFT
Base Model=Spark, Trai...
2023.11
81
GPT-4
Model Family=public
2023.11
18.1
ChatGPT
Model Family=public
2023.11
12.3
Feedback
Search any
task
Search any
task