Natural Language Inference on WNLI

97.9Accuracy

SOTA

Updated 1mo ago

Evaluation Results

Method	Links
SOTA 2023.05		97.9
GPT-4 2023.05		91.6
MUPPET 2022.12		91.1
Knowledge Hunter 2019.05		90.1
ChatGPT 2023.05		81.7
BERT_WIKI_WSCR 2019.05		74.7
Training-free Weight Recycling (L^T_KD) 2023.05		72.2
BERT_WSCR 2019.05		71.9
BERT_WIKI 2019.05		71.2
BERT-base_WSCR 2019.05		70.5
OPT-IML 175B 2022.12		70
BERT 2019.05		65.8
LaMDA-PT 137B 2022.12		64.8
BERT-base 2019.05		63
OPT-IML 175B 2022.12		62.7
FLAN 137B 2022.12		61
OPT-IML 30B 2022.12		58.5
Training-free Weight Recycling (L^W_KD) 2023.05		58.3
RPJ-INCITE-7B 2024.02		57.8
OPT-IML 30B 2022.12		57.7
LaMDA-PT 137B 2022.12		56.3
OLMo-7B 2024.02		56.3
Demonstration learning 2023.05		55.6
Full dataset tuning 2023.05		55.6
FLAN 137B 2022.12		55.4
OPT 175B 2022.12		55.4
Finetune 2022.12		55.21
ColD-Fusion 2022.12		54.93
LLaMA-7B 2024.02		52.1
Multitask 2022.12		51.55
OPT 30B 2022.12		50.6
OPT 30B 2022.12		50.3
32-shot tuning 2023.05		50
RWKV-4-Raven-14B 2023.05		49.3
RWKV-4-Raven-14B 2023.05		47.9
Falcon-7B 2024.02		47.9
MPT-7B 2024.02		47.9
OPT 175B 2022.12		47.7
LLaMA2-7B 2024.02		45.1
Pythia-6.9B 2024.02		38