Our new X account is live! Follow @wizwand_team for updates
Home
/
Benchmarks
Relevance Labeling on BEIR RobustQA
Loading...
94.1
Class-wise Recall (Irrelevance)
LARA
48.444
60.297
72.15
84.003
Feb 6, 2026
Class-wise Recall (Irrelevance)
Class-wise Recall (Relevance)
bAcc
Updated 4d ago
Evaluation Results
Method
Method
Links
Class-wise Recall (Irrelevance)
Class-wise Recall (Relevance)
bAcc
LARA
Escalation Ratio=50.0%
2026.02
94.1
98.4
96.3
DREAM
Escalation Ratio=3.5%
2026.02
91.9
98.4
95.2
Human-Only
Escalation Ratio=100.0%
2026.02
89.9
97.8
93.8
LARA
Escalation Ratio=25.0%
2026.02
80.2
95.3
87.8
LARA
Escalation Ratio=12.5%
2026.02
76.1
91.6
83.9
LARA
Escalation Ratio=3.5%
2026.02
74.5
89.6
82.1
LLMJudge
Escalation Ratio=0.0%
2026.02
50.2
97.5
73.9
Feedback
Search any
task
Search any
task