# How to Evaluate When You Don't Know How to Evaluate? Choosing Reliable Setups for Base Language Model Benchmarking

arXiv: https://arxiv.org/abs/2610.19185 · HTML: https://mlsanity.com/paper/2610.19185/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 19 of its 28 references that are in the map.
- First posted on arXiv 13 Oct 2026.

## Builds on (most cited first, 19 of 19)

- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [Scaling Laws for Neural Language Models](https://mlsanity.com/paper/2001.08361/) (2020)
- [Efficient Memory Management for Large Language Model Serving with PagedAttention](https://mlsanity.com/paper/2309.06180/) (2023)
- [The FineWeb Datasets: Decanting the Web for the Finest Text Data at Scale](https://mlsanity.com/paper/2406.17557/) (2024)
- [State of What Art? A Call for Multi-Prompt LLM Evaluation](https://mlsanity.com/paper/2401.00595/) (2023)
- [Leveraging Large Language Models for Multiple Choice Question Answering](https://mlsanity.com/paper/2210.12353/) (2022)
- [Global MMLU: Understanding and Addressing Cultural and Linguistic Biases in Multilingual Evaluation](https://mlsanity.com/paper/2412.03304/) (2024)
- [Adding Error Bars to Evals: A Statistical Approach to Language Model Evaluations](https://mlsanity.com/paper/2411.00640/) (2024)
- [FineWeb2: One Pipeline to Scale Them All -- Adapting Pre-Training Data Processing to Every Language](https://mlsanity.com/paper/2506.20920/) (2025)
- [When Benchmarks are Targets: Revealing the Sensitivity of Large Language Model Leaderboards](https://mlsanity.com/paper/2402.01781/) (2024)
- [OLMES: A Standard for Language Model Evaluations](https://mlsanity.com/paper/2406.08446/) (2024)
- [CroissantLLM: A Truly Bilingual French-English Language Model](https://mlsanity.com/paper/2402.00786/) (2024)
- [Why Has Predicting Downstream Capabilities of Frontier AI Models with Scale Remained Elusive?](https://mlsanity.com/paper/2406.04391/) (2024)
- [DataDecide: How to Predict Best Pretraining Data with Small Experiments](https://mlsanity.com/paper/2504.11393/) (2025)
- [Signal and Noise: A Framework for Reducing Uncertainty in Language Model Evaluation](https://mlsanity.com/paper/2508.13144/) (2025)
- [NoCoLA: The Norwegian Corpus of Linguistic Acceptability](https://mlsanity.com/paper/2306.07790/) (2023)
- [NorEval: A Norwegian Language Understanding and Generation Evaluation Benchmark](https://mlsanity.com/paper/2504.07749/) (2025)
- [NeurIPS 2025 E2LM Competition : Early Training Evaluation of Language Models](https://mlsanity.com/paper/2506.07731/) (2025)
- [Mix, MinHash, and Match: Cross-Source Agreement for Multilingual Pretraining Datasets](https://mlsanity.com/paper/2512.18834/) (2025)

## Abstract (arXiv)

Evaluation of large language models (LLMs) remains largely pre-scientific: it involves many design decisions, with little guidance on how to make them. These choices can substantially affect measured performance and, consequently, decisions about subsequent pretraining. To identify effective evaluation setups, we investigate 8 aspects, such as task formulation or the number of in-context examples. We compare the setups using three widely-used signal criteria, repurposed as normative meta-measures: monotonicity, non-randomness, and ranking consistency of the evaluation scores across intermediate checkpoints. In an early pretraining scenario, we evaluate these setups on 26 monolingual 2B-parameter models trained on different types of data, using 80 tasks in four languages. We also examine the setups on three larger LLMs (≥7B) in the same four languages and explore how the preferred setups change with model scale. Our results yield concrete recommendations: some choices, such as the use of multiple prompts, are consistently useful, whereas others, such as task formulation, depend on model scale. More generally, our framework serves as a recipe for the choice of evaluation setups in new scenarios.