Question Answering On Boolq

评估指标

Accuracy

评测结果

各个模型在此基准测试上的表现结果

		Paper Title	Repository
Mistral-Nemo 12B (HPT)	99.87	Hierarchical Prompting Taxonomy: A Universal Evaluation Framework for Large Language Models
Gemma-7B	99.419	Hierarchical Prompting Taxonomy: A Universal Evaluation Framework for Large Language Models
ST-MoE-32B 269B (fine-tuned)	92.4	ST-MoE: Designing Stable and Transferable Sparse Expert Models
PaLM 540B (fine-tuned)	92.2	PaLM: Scaling Language Modeling with Pathways
Turing NLR v5 XXL 5.4B (fine-tuned)	92	Toward Efficient Language Model Pretraining and Downstream Adaptation via Self-Evolution: A Case Study on SuperGLUE	-
T5-XXL 11B (fine-tuned)	91.2	Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer
PaLM 2-L (1-shot)	90.9	PaLM 2 Technical Report
UL2 20B (fine-tuned)	90.8	UL2: Unifying Language Learning Paradigms
Vega v2 6B (fine-tuned)	90.5	Toward Efficient Language Model Pretraining and Downstream Adaptation via Self-Evolution: A Case Study on SuperGLUE	-
DeBERTa-1.5B	90.4	DeBERTa: Decoding-enhanced BERT with Disentangled Attention
ST-MoE-L 4.1B (fine-tuned)	88.6	ST-MoE: Designing Stable and Transferable Sparse Expert Models
PaLM 2-M (1-shot)	88.6	PaLM 2 Technical Report
PaLM 2-S (1-shot)	88.1	PaLM 2 Technical Report
MUPPET Roberta Large	87.5	Muppet: Massive Multi-task Representations with Pre-Finetuning
FLAN 137B (prompt-tuned)	86.3	Finetuned Language Models Are Zero-Shot Learners
RoBERTa-large 355M + Entailment as Few-shot Learner	86.0	Entailment as Few-Shot Learner
T5-Large 770M (fine-tuned)	85.4	Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer
LLaMA 65B (0-shot)	85.3	LLaMA: Open and Efficient Foundation Language Models
LLaMA 2 70B (0-shot)	85	Llama 2: Open Foundation and Fine-Tuned Chat Models
FLAN 137B (4-shot)	84.6	Finetuned Language Models Are Zero-Shot Learners

0 of 66 row(s) selected.