Our new X account is live! Follow @wizwand_team for updates
Home
/
Benchmarks
Budgeted subset selection on Alpaca 5% retention
Loading...
157.162
SUM
TSS++ (E)
131.78184
138.37092
144.96
151.54908
Feb 3, 2026
SUM
Delta
ARC-C
MMLU
HellaSwag
TruthfulQA
Updated 4d ago
Evaluation Results
Method
Method
Links
SUM
Delta
ARC-C
MMLU
HellaSwag
TruthfulQA
TSS++ (E)
Model=Qwen, Retention...
2026.02
157.162
0.747
-
-
-
-
Random
Model=Qwen, Retention...
2026.02
156.415
-
-
-
-
-
TSS++ (E)
Model=Llama, Retention...
2026.02
142.704
0.783
-
-
-
-
Random
Model=Llama, Retention...
2026.02
141.921
-
-
-
-
-
TSS
Model=Gemma, Retention...
2026.02
132.902
0.144
-
-
-
-
Random
Model=Gemma, Retention...
2026.02
132.758
-
-
-
-
-
Feedback
Search any
task
Search any
task