Our new X account is live! Follow @wizwand_team for updates
Home
/
Benchmarks
Triplet (Ori-Ori) on Original (test)
Loading...
46.9
Thard
Ours best
17.988
25.494
33
40.506
Mar 7, 2024
Thard
Teasy
Updated 4d ago
Evaluation Results
Method
Method
Links
Thard
Teasy
Ours best
Backbone=instructor-ba...
2024.03
46.9
93.3
Disable LLM
Backbone=instructor-base
2024.03
24.5
80.5
Baseline
Backbone=instructor-base
2024.03
19.1
86.1
Feedback
Search any
task
Search any
task