Our new X account is live! Follow @wizwand_team for updates
Home
/
Benchmarks
Multi-task Routing on DISTR-ROUGE2 (test)
Loading...
26.9
ROUGE2
SMOOTHIE-LOCAL
16.396
19.123
21.85
24.577
Dec 6, 2024
ROUGE2
Updated 4d ago
Evaluation Results
Method
Method
Links
ROUGE2
SMOOTHIE-LOCAL
Ensemble Scale=7B, Nei...
2024.12
26.9
BEST-MODEL
Ensemble Scale=7B
2024.12
26.4
LABELED-KNN
Ensemble Scale=7B, Nei...
2024.12
26.2
SMOOTHIE-GLOBAL
Ensemble Scale=7B
2024.12
26.1
PAIRRM
Ensemble Scale=7B
2024.12
25.5
RANDOM
Ensemble Scale=7B
2024.12
25
SMOOTHIE-LOCAL
Ensemble Scale=3B, Nei...
2024.12
20.2
PAIRRM
Ensemble Scale=3B
2024.12
19
BEST-MODEL
Ensemble Scale=3B
2024.12
18.1
SMOOTHIE-GLOBAL
Ensemble Scale=3B
2024.12
18.1
RANDOM
Ensemble Scale=3B
2024.12
17
LABELED-KNN
Ensemble Scale=3B, Nei...
2024.12
16.8
Feedback
Search any
task
Search any
task