Our new X account is live! Follow @wizwand_team for updates
Home
/
Benchmarks
Arithmetic Reasoning on SVAMP latest (test)
Loading...
64.8
Accuracy
8-shot
0.528
17.214
33.9
50.586
Dec 9, 2023
Accuracy
Updated 4d ago
Evaluation Results
Method
Method
Links
Accuracy
8-shot
Backbone=GPT-3.5, Prom...
2023.12
64.8
SYRELM
Backbone=Vicuna 13B
2023.12
56.65
PAL
Backbone=Vicuna 13B
2023.12
53.7
ART
Backbone=Vicuna 13B
2023.12
49.83
LMFT
Backbone=Vicuna 13B, O...
2023.12
42.5
SYRELM
Backbone=GPT-J 6B
2023.12
40.1
4-shot
Backbone=Vicuna 13B, P...
2023.12
37.5
LMFT
Backbone=GPT-J 6B, Opt...
2023.12
31.6
Toolformer
Backbone=GPT-J, Optimi...
2023.12
29.4
1-shot
Backbone=Vicuna 13B, P...
2023.12
27
PAL
Backbone=GPT-J 6B
2023.12
22.33
4-shot
Backbone=GPT-J 6B, Pro...
2023.12
9.45
ART
Backbone=GPT-J 6B
2023.12
3.1
1-shot
Backbone=GPT-J 6B, Pro...
2023.12
3
Feedback
Search any
task
Search any
task