Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
General Language Capability on BIG-bench 57 Task
Loading...
48.7
Accuracy (Weighted)
GAL 120B
39.236
41.693
44.15
46.607
Nov 16, 2022
Accuracy (Weighted)
Accuracy (Unweighted)
Updated 3mo ago
Evaluation Results
Method
Method
Links
Accuracy (Weighted)
Accuracy (Unweighted)
GAL 120B
Params (bn)=120, Shot-...
2022.11
48.7
45.3
GAL 30B
Params (bn)=30, Shot-c...
2022.11
46.6
42.7
OPT 175B
Params (bn)=175, Shot-...
2022.11
43.4
42.6
BLOOM 176B
Params (bn)=176, Shot-...
2022.11
42.6
42.2
OPT 30B
Params (bn)=30, Shot-c...
2022.11
39.6
38
Feedback
Search any
task
Search any
task