# ModernBERT or DeBERTaV3? Examining Architecture and Data Influence on Transformer Encoder Models Performance

arXiv: https://arxiv.org/abs/2504.08716 · HTML: https://mlsanity.com/paper/2504.08716/

## Key facts

- Cited by 12 papers in the map (data through 14 Oct 2026).
- Builds on 27 of its 46 references that are in the map.
- First posted on arXiv 11 Apr 2025.

## Builds on (most cited first, 27 of 27)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [RoBERTa: A Robustly Optimized BERT Pretraining Approach](https://mlsanity.com/paper/1907.11692/) (2019)
- [Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks](https://mlsanity.com/paper/2005.11401/) (2020)
- [RoFormer: Enhanced Transformer with Rotary Position Embedding](https://mlsanity.com/paper/2104.09864/) (2021)
- [FlashAttention: Fast and Memory-Efficient Exact Attention with IO-Awareness](https://mlsanity.com/paper/2205.14135/) (2022)
- [FlashAttention-2: Faster Attention with Better Parallelism and Work Partitioning](https://mlsanity.com/paper/2307.08691/) (2023)
- [DeBERTa: Decoding-enhanced BERT with Disentangled Attention](https://mlsanity.com/paper/2006.03654/) (2020)
- [Gemma 2: Improving Open Language Models at a Practical Size](https://mlsanity.com/paper/2408.00118/) (2024)
- [mT5: A massively multilingual pre-trained text-to-text transformer](https://mlsanity.com/paper/2010.11934/) (2020)
- [GLU Variants Improve Transformer](https://mlsanity.com/paper/2002.05202/) (2020)
- [DeBERTaV3: Improving DeBERTa using ELECTRA-Style Pre-Training with Gradient-Disentangled Embedding Sharing](https://mlsanity.com/paper/2111.09543/) (2021)
- [The FineWeb Datasets: Decanting the Web for the Finest Text Data at Scale](https://mlsanity.com/paper/2406.17557/) (2024)
- [Towards General Text Embeddings with Multi-stage Contrastive Learning](https://mlsanity.com/paper/2308.03281/) (2023)
- [Smarter, Better, Faster, Longer: A Modern Bidirectional Encoder for Fast, Memory Efficient, and Long Context Finetuning and Inference](https://mlsanity.com/paper/2412.13663/) (2024)
- [FlashAttention-3: Fast and Accurate Attention with Asynchrony and Low-precision](https://mlsanity.com/paper/2407.08608/) (2024)
- [Nomic Embed: Training a Reproducible Long Context Text Embedder](https://mlsanity.com/paper/2402.01613/) (2024)
- [RedPajama: an Open Dataset for Training Large Language Models](https://mlsanity.com/paper/2411.12372/) (2024)
- [CulturaX: A Cleaned, Enormous, and Multilingual Dataset for Large Language Models in 167 Languages](https://mlsanity.com/paper/2309.09400/) (2023)
- [Nemotron-CC: Transforming Common Crawl into a Refined Long-Horizon Pretraining Dataset](https://mlsanity.com/paper/2412.02595/) (2024)
- [FlauBERT: Unsupervised Language Model Pre-training for French](https://mlsanity.com/paper/1912.05372/) (2019)
- [Towards a Cleaner Document-Oriented Multilingual Crawled Corpus](https://mlsanity.com/paper/2201.06642/) (2022)
- [XLM-V: Overcoming the Vocabulary Bottleneck in Multilingual Masked Language Models](https://mlsanity.com/paper/2301.10472/) (2023)
- [FQuAD: French Question Answering Dataset](https://mlsanity.com/paper/2002.06071/) (2020)
- [MosaicBERT: A Bidirectional Encoder Optimized for Fast Pretraining](https://mlsanity.com/paper/2312.17482/) (2023)
- [CamemBERT 2.0: A Smarter French Language Model Aged to Perfection](https://mlsanity.com/paper/2411.08868/) (2024)
- [Data-Efficient French Language Modeling with CamemBERTa](https://mlsanity.com/paper/2306.01497/) (2023)

## Built on by (most cited first, 12 of 12)

- [New Encoders for German Trained from Scratch: Comparing ModernGBERT with Converted LLM2Vec Models](https://mlsanity.com/paper/2505.13136/) (2025)
- [TabiBERT: A Large-Scale ModernBERT Foundation Model and A Unified Benchmark for Turkish](https://mlsanity.com/paper/2512.23065/) (2025)
- [SHIELD: A Diverse Clinical Note Dataset and Distilled Small Language Models for Enterprise-Scale De-identification](https://mlsanity.com/paper/2605.03301/) (2026)
- [A Causal Language Modeling Detour Improves Encoder Continued Pretraining](https://mlsanity.com/paper/2605.12438/) (2026)
- [TRACE: Toulmin-based Reasoning Assessment through Constructive Elements for LLM CoT Evaluation](https://mlsanity.com/paper/2605.29656/) (2026)
- [When Do Concepts Become Functionally Sufficient During Language-Model Training?](https://mlsanity.com/paper/2608.15323/) (2026)
- [The GDN-CC Dataset: Automatic Corpus Clarification for AI-enhanced Democratic Citizen Consultations](https://mlsanity.com/paper/2601.14944/) (2026)
- [Where Does the Signal Live? A Web Data Recipe for Medical Encoder Pretraining](https://mlsanity.com/paper/2606.22079/) (2026)
- [BERTomelo: Your Portuguese Encoder Best Friend](https://mlsanity.com/paper/2606.28999/) (2026)
- [OntoBook: Ontology-Grounded Synthetic Textbooks for Medical Encoder Pretraining](https://mlsanity.com/paper/2607.18927/) (2026)
- [Do Visual Features Improve Other-Initiated Repair Detection? A Dyadic Multimodal Approach](https://mlsanity.com/paper/2607.23845/) (2026)
- [UltraBERT: Beyond the Limit of BERT Pre-Training](https://mlsanity.com/paper/2610.15028/) (2026)

## Abstract (arXiv)

Pretrained transformer-encoder models like DeBERTaV3 and ModernBERT introduce architectural advancements aimed at improving efficiency and performance. Although the authors of ModernBERT report improved performance over DeBERTaV3 on several benchmarks, the lack of disclosed training data and the absence of comparisons using a shared dataset make it difficult to determine whether these gains are due to architectural improvements or differences in training data. In this work, we conduct a controlled study by pretraining ModernBERT on the same dataset as CamemBERTaV2, a DeBERTaV3 French model, isolating the effect of model design. Our results show that the previous model generation remains superior in sample efficiency and overall benchmark performance, with ModernBERT's primary advantage being its support for long context, faster training, and inference speed. However, the new proposed model still provides meaningful architectural improvements compared to earlier models such as BERT and RoBERTa. Additionally, we observe that high-quality pre-training data accelerates convergence but does not significantly improve final performance, suggesting potential benchmark saturation. These findings show the importance of disentangling pretraining data from architectural innovations when evaluating transformer models.