Our new X account is live! Follow @wizwand_team for updates
Home
/
Benchmarks
Question Answering on OBQA (test)
Loading...
60.2
Accuracy
LLAMA 1
45.224
49.112
53
56.888
May 4, 2023
May 16, 2023
May 29, 2023
Jun 10, 2023
Jun 23, 2023
Jul 5, 2023
Jul 18, 2023
Accuracy
Updated 4d ago
Evaluation Results
Method
Method
Links
Accuracy
LLAMA 1
Size=65B
2023.07
60.2
LLAMA 2
Size=70B
2023.07
60.2
LLAMA 1
Size=33B
2023.07
58.6
LLAMA 2
Size=7B
2023.07
58.6
LLAMA 2
Size=34B
2023.07
58.2
LLAMA 1
Size=7B
2023.07
57.2
LLAMA 2
Size=13B
2023.07
57
Falcon
Size=40B
2023.07
56.6
LLAMA 1
Size=13B
2023.07
56.4
MPT
Size=30B
2023.07
52
Falcon
Size=7B
2023.07
51.6
MPT
Size=7B
2023.07
51.4
Entailer
Backbone=T5-large, Fin...
2023.05
45.8
Feedback
Search any
task
Search any
task