# IberBench: LLM Evaluation on Iberian Languages

arXiv: https://arxiv.org/abs/2504.16921 · HTML: https://mlsanity.com/paper/2504.16921/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Builds on 38 of its 89 references that are in the map.
- First posted on arXiv 23 Apr 2025.

## Builds on (most cited first, 30 of 38)

- [Proximal Policy Optimization Algorithms](https://mlsanity.com/paper/1707.06347/) (2017)
- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena](https://mlsanity.com/paper/2306.05685/) (2023)
- [Direct Preference Optimization: Your Language Model is Secretly a Reward Model](https://mlsanity.com/paper/2305.18290/) (2023)
- [Measuring Massive Multitask Language Understanding](https://mlsanity.com/paper/2009.03300/) (2020)
- [DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning](https://mlsanity.com/paper/2501.12948/) (2025)
- [GLUE: A Multi-Task Benchmark and Analysis Platform for Natural Language Understanding](https://mlsanity.com/paper/1804.07461/) (2018)
- [Parameter-Efficient Transfer Learning for NLP](https://mlsanity.com/paper/1902.00751/) (2019)
- [Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context](https://mlsanity.com/paper/2403.05530/) (2024)
- [Training Compute-Optimal Large Language Models](https://mlsanity.com/paper/2203.15556/) (2022)
- [Gemma 2: Improving Open Language Models at a Practical Size](https://mlsanity.com/paper/2408.00118/) (2024)
- [Jailbroken: How Does LLM Safety Training Fail?](https://mlsanity.com/paper/2307.02483/) (2023)
- [Chatbot Arena: An Open Platform for Evaluating LLMs by Human Preference](https://mlsanity.com/paper/2403.04132/) (2024)
- [XNLI: Evaluating Cross-lingual Sentence Representations](https://mlsanity.com/paper/1809.05053/) (2018)
- [Datasets: A Community Library for Natural Language Processing](https://mlsanity.com/paper/2109.02846/) (2021)
- [Phi-4-Mini Technical Report: Compact yet Powerful Multimodal Language Models via Mixture-of-LoRAs](https://mlsanity.com/paper/2503.01743/) (2025)
- [From Crowdsourced Data to High-Quality Benchmarks: Arena-Hard and BenchBuilder Pipeline](https://mlsanity.com/paper/2406.11939/) (2024)
- [XL-Sum: Large-Scale Multilingual Abstractive Summarization for 44 Languages](https://mlsanity.com/paper/2106.13822/) (2021)
- [Humans or LLMs as the Judge? A Study on Judgement Biases](https://mlsanity.com/paper/2402.10669/) (2024)
- [The Belebele Benchmark: a Parallel Reading Comprehension Dataset in 122 Language Variants](https://mlsanity.com/paper/2308.16884/) (2023)
- [PAWS-X: A Cross-lingual Adversarial Dataset for Paraphrase Identification](https://mlsanity.com/paper/1908.11828/) (2019)
- [MT-Bench-101: A Fine-Grained Benchmark for Evaluating Large Language Models in Multi-Turn Dialogues](https://mlsanity.com/paper/2402.14762/) (2024)
- [LLMs instead of Human Judges? A Large Scale Empirical Study across 20 NLP Evaluation Tasks](https://mlsanity.com/paper/2406.18403/) (2024)
- [Lessons from the Trenches on Reproducible Evaluation of Language Models](https://mlsanity.com/paper/2405.14782/) (2024)
- [GPTs are GPTs: An Early Look at the Labor Market Impact Potential of Large Language Models](https://mlsanity.com/paper/2303.10130/) (2023)
- [GPT-NER: Named Entity Recognition via Large Language Models](https://mlsanity.com/paper/2304.10428/) (2023)
- [EuroLLM: Multilingual Language Models for Europe](https://mlsanity.com/paper/2409.16235/) (2024)
- [Style Over Substance: Evaluation Biases for Large Language Models](https://mlsanity.com/paper/2307.03025/) (2023)
- [IndicGenBench: A Multilingual Benchmark to Evaluate Generation Capabilities of LLMs on Indic Languages](https://mlsanity.com/paper/2404.16816/) (2024)
- [Generative Pre-trained Transformer: A Comprehensive Review on Enabling Technologies, Potential Applications, Emerging Challenges, and Future Directions](https://mlsanity.com/paper/2305.10435/) (2023)

## Built on by (most cited first, 5 of 5)

- [Charting the European LLM Benchmarking Landscape: A New Taxonomy and a Set of Best Practices](https://mlsanity.com/paper/2510.24450/) (2025)
- [P3B3: A Multi-Turn Conversational Benchmark for Measuring European and Brazilian Portuguese Variety Bias in LLMs](https://mlsanity.com/paper/2606.16753/) (2026)
- [Observatorio Lazaro: A self-populating database of anglicism usage in the Spanish press](https://mlsanity.com/paper/2608.00713/) (2026)
- [Merge and Conquer: Instructing Multilingual Models by Adding Target Language Weights](https://mlsanity.com/paper/2603.28263/) (2026)
- [pylazaro: a Python package for anglicism extraction in Spanish](https://mlsanity.com/paper/2609.29276/) (2026)

## Abstract (arXiv)

Large Language Models (LLMs) remain difficult to evaluate comprehensively, particularly for languages other than English, where high-quality data is often limited. Existing benchmarks and leaderboards are predominantly English-centric, with only a few addressing other languages. These benchmarks fall short in several key areas: they overlook the diversity of language varieties, prioritize fundamental Natural Language Processing (NLP) capabilities over tasks of industrial relevance, and are static. With these aspects in mind, we present IberBench, a comprehensive and extensible benchmark designed to assess LLM performance on both fundamental and industry-relevant NLP tasks, in languages spoken across the Iberian Peninsula and Ibero-America. IberBench integrates 101 datasets from evaluation campaigns and recent benchmarks, covering 22 task categories such as sentiment and emotion analysis, toxicity detection, and summarization. The benchmark addresses key limitations in current evaluation practices, such as the lack of linguistic diversity and static evaluation setups by enabling continual updates and community-driven model and dataset submissions moderated by a committee of experts. We evaluate 23 LLMs ranging from 100 million to 14 billion parameters and provide empirical insights into their strengths and limitations. Our findings indicate that (i) LLMs perform worse on industry-relevant tasks than in fundamental ones, (ii) performance is on average lower for Galician and Basque, (iii) some tasks show results close to random, and (iv) in other tasks LLMs perform above random but below shared task systems. IberBench offers open-source implementations for the entire evaluation pipeline, including dataset normalization and hosting, incremental evaluation of LLMs, and a publicly accessible leaderboard.