BIG-Bench
Benchmarks
Task NameDataset NameSOTA ResultTrendResults
Big Bench Audio
77.2Audio Accuracy
7
BIG-Bench Hard (BBH)
86.51Accuracy
7
BIG-bench Hard
39.3Orig Score
7
Big-Bench Hard Word Sorting and Multi-step Arithmetic (test)
80WS Accuracy
7
Big Bench Extra Hard
74.4Micro Avg Score
6
BIG-bench Hard
13.99BBH QA Score
6
Big-Bench Hard & others
88Abstract Algebra Score
6
Big Bench Audio
99.4Score
6
Big-Bench Hard
69.5Accuracy
6
Big Bench Audio (test)
72.9S2T Accuracy
6
Big-Bench Hard (BBH) (test)
78.6BBH Overall Accuracy
6
BIG-Bench Hard (BBH)
55.96BBH MCQ Accuracy
5
BIG-Bench Hard (BBH)
42.1Accuracy
5
BIG-bench Hard (BBH)
83.2Boolean Expressions
5
BIG-bench
49.1Anachronisms
5
BIG-bench 57 Task
48.7Accuracy (Weighted)
5
BIG-bench Hard Movie Recommendation (test)
79Test Accuracy
4
BIG-bench Hard Hyperbaton (test)
74Test Accuracy
4
Big-Bench Hard
100BBH: Boolean Expressions (Mean)
3
BIG-Bench
83.6Performance
3
BIG-Bench Hard Multi-Step Arithmetic Two (OOD)
12.4Accuracy
3
BIG-Bench Hard Object Counting (OOD)
48.4Accuracy
3
BIG-Bench Hard Web of Lies (OOD)
44.8Accuracy
3
BIG-Bench Hard Boolean Expression (OOD)
72.4Accuracy
3
BIG-bench (test)
1.144Boolean Expressions
3