Our new X account is live! Follow @wizwand_team for updates
Home
/
Benchmarks
Boolean Question Answering on BoolQ (Calibrated Accuracy)
Loading...
86.1
Calibrated Accuracy
SC+IC (tune)
60.412
67.081
73.75
80.419
May 29, 2024
Calibrated Accuracy
Updated 4d ago
Evaluation Results
Method
Method
Links
Calibrated Accuracy
SC+IC (tune)
Backbone=MIXTRAL-8×7B,...
2024.05
86.1
SC+IC (tune)
Backbone=MIXTRAL-8×7B,...
2024.05
81.8
SC+IC (tune)
Backbone=LLAMA-2-13B,...
2024.05
81.4
SC+IC (tune)
Backbone=LLAMA-2-13B,...
2024.05
80.4
SC+IC (tune)
Backbone=MISTRAL-7B, P...
2024.05
79.5
SC+IC (tune)
Backbone=MISTRAL-7B, P...
2024.05
77.8
SC+IC (tune)
Backbone=LLAMA-2-7B, P...
2024.05
73.5
SC+IC (transfer)
Backbone=LLAMA-2-7B, P...
2024.05
73.5
SC+IC
Backbone=LLAMA-2-7B, P...
2024.05
73.4
SC
Backbone=LLAMA-2-7B, P...
2024.05
73.2
SC+A
Backbone=LLAMA-2-7B, P...
2024.05
73
SC+IC (tune)
Backbone=LLAMA-2-7B, P...
2024.05
71.5
SC+IC (transfer)
Backbone=LLAMA-2-7B, P...
2024.05
71.5
SC+IC
Backbone=LLAMA-2-7B, P...
2024.05
70.7
SC
Backbone=LLAMA-2-7B, P...
2024.05
70
SC+A
Backbone=LLAMA-2-7B, P...
2024.05
69.9
Greedy
Backbone=LLAMA-2-7B, P...
2024.05
67.1
Greedy
Backbone=LLAMA-2-7B, P...
2024.05
61.4
Feedback
Search any
task
Search any
task