Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Safety Evaluation on SorryBench
Loading...
8.22
ASR
Db as Alpaca
5.1204
26.0427
46.965
67.8873
Mar 12, 2026
ASR
Updated 1mo ago
Evaluation Results
Method
Method
Links
ASR
Db as Alpaca
Setting / Model=RLVR,...
2026.03
8.22
Db as Alpaca
Setting / Model=P-SFT,...
2026.03
18.22
Db as Our Data
Setting / Model=P-SFT,...
2026.03
25.11
Db as Our Data
Setting / Model=RLVR,...
2026.03
25.33
Baseline
Setting / Model=P-SFT,...
2026.03
47.56
Baseline
Setting / Model=RLVR,...
2026.03
85.71
Feedback
Search any
task
Search any
task