Our new X account is live! Follow @wizwand_team for updates
Home
/
Benchmarks
Triplet Evaluation (Ori-Imp) on Intent Semantic Toolkit (test)
Loading...
71
Teasy Score
instructor-large
0.592
18.871
37.15
55.429
Mar 7, 2024
Teasy Score
Thard Score
Updated 4d ago
Evaluation Results
Method
Method
Links
Teasy Score
Thard Score
instructor-large
2024.03
71
0.036
paraphrase
2024.03
68.9
0.039
instructor-base
2024.03
68
0.02
IAE
2024.03
67.3
0.032
Ours best
backbone=instructor-la...
2024.03
20.4
0.776
Disable LLM
backbone=instructor-la...
2024.03
8
0.508
Baseline
backbone=instructor-large
2024.03
3.3
0.706
Feedback
Search any
task
Search any
task