OpenCodePapers
natural-language-inference-on-rte-glue-dev
Natural Language Inference
Dataset Link
Results over time
Click legend items to toggle metrics. Hover points for model names.
Leaderboard
Show papers without code
Paper
Code
Accuracy
↕
ModelName
ReleaseDate
↕
DeBERTa: Decoding-enhanced BERT with Disentangled Attention
✓ Link
88.3
DeBERTa Large
2020-06-05
ELECTRA: Pre-training Text Encoders as Discriminators Rather Than Generators
✓ Link
88.0
ELECTRA-1.75M
2020-03-23
MPNet: Masked and Permuted Pre-training for Language Understanding
✓ Link
88.0
MPNet Large
2020-04-20
ReFTA: Breaking the Weight Reconstruction Bottleneck in Tensorized Parameter-Efficient Fine-Tuning
✓ Link
87.1
ReFTA (RoBERTa-Large)
2026-06-03
I-BERT: Integer-only BERT Quantization
✓ Link
87.0
I-BERT RoBERTa-Large
2021-01-05
RoBERTa: A Robustly Optimized BERT Pretraining Approach
✓ Link
86.6
RoBERTa
2019-07-26
Model soups: averaging weights of multiple fine-tuned models improves accuracy without increasing inference time
✓ Link
84.8
T5-large (Greedy soup)
2022-03-10
GLU Variants Improve Transformer
✓ Link
84.12
FFN GLU
2020-02-12
ERNIE-Gram: Pre-Training with Explicitly N-Gram Masked Language Modeling for Natural Language Understanding
✓ Link
83.8
ERNIE-Gram
2020-10-23
MVP: Multi-task Supervised Pre-training for Natural Language Generation
✓ Link
82.87
MVP
2022-06-24
LFM2.5-Encoders: Fast at Long Context, Even on CPU
✓ Link
75.23
LFM2.5-Encoder-350M
2026-07-28
Sheared Backpropagation for Fine-tuning Foundation Models
72.92
PREBR@80% (batch size 8)
2024-06-17
Resource-Efficient Transformer Pruning for Finetuning of Large Models
✓ Link
65.98
RECAP (BERT-base, 50% pruning)
2024-06-17
DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lighter
✓ Link
59.9
DistilBERT
2019-10-02
FLAVA: A Foundational Language And Vision Alignment Model
✓ Link
57.8
FLAVA
2021-12-08
×