Classification on RAFT

Metric: Avg (higher is better)

LeaderboardDataset

Loading chart...

Results

Submit a result

Sort:

#	Model↕	Avg▼	Augmentations	Paper	Date↕	Code
1	T-Few	0.758	No	Few-Shot Parameter-Efficient Fine-Tuning is Bett...	2022-05-11	Code
2	Human (crowdsourced)	0.735	No	RAFT: A Real-World Few-Shot Text Classification ...	2021-09-28	Code
3	GPT-3	0.627	No	RAFT: A Real-World Few-Shot Text Classification ...	2021-09-28	Code
4	AdaBoost	0.514	No	RAFT: A Real-World Few-Shot Text Classification ...	2021-09-28	Code
5	GPT-Neo	0.481	No	RAFT: A Real-World Few-Shot Text Classification ...	2021-09-28	Code
6	GPT-2	0.458	No	RAFT: A Real-World Few-Shot Text Classification ...	2021-09-28	Code
7	BART MNLI zero-shot	0.382	No	RAFT: A Real-World Few-Shot Text Classification ...	2021-09-28	Code
8	Plurality-class	0.331	No	RAFT: A Real-World Few-Shot Text Classification ...	2021-09-28	Code
9	GPT-3 zero-shot	0.292	No	RAFT: A Real-World Few-Shot Text Classification ...	2021-09-28	Code

#1T-FewSOTA
0.758
Avg· 2022-05-11
Few-Shot Parameter-Efficient Fine-Tuning is Better and Cheaper than In-Context Learning Code
#2Human (crowdsourced)SOTA
0.735
Avg· 2021-09-28
RAFT: A Real-World Few-Shot Text Classification Benchmark Code
#3GPT-3
0.627
Avg· 2021-09-28
RAFT: A Real-World Few-Shot Text Classification Benchmark Code
#4AdaBoost
0.514
Avg· 2021-09-28
RAFT: A Real-World Few-Shot Text Classification Benchmark Code
#5GPT-Neo
0.481
Avg· 2021-09-28
RAFT: A Real-World Few-Shot Text Classification Benchmark Code
#6GPT-2
0.458
Avg· 2021-09-28
RAFT: A Real-World Few-Shot Text Classification Benchmark Code
#7BART MNLI zero-shot
0.382
Avg· 2021-09-28
RAFT: A Real-World Few-Shot Text Classification Benchmark Code
#8Plurality-class
0.331
Avg· 2021-09-28
RAFT: A Real-World Few-Shot Text Classification Benchmark Code
#9GPT-3 zero-shot
0.292
Avg· 2021-09-28
RAFT: A Real-World Few-Shot Text Classification Benchmark Code