# EffiEval: Efficient and Generalizable Model Evaluation via Capability Coverage Maximization

arXiv: https://arxiv.org/abs/2508.09662 · HTML: https://mlsanity.com/paper/2508.09662/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- Builds on 9 of its 17 references that are in the map.
- First posted on arXiv 13 Aug 2025.

## Builds on (most cited first, 9 of 9)

- [Training Verifiers to Solve Math Word Problems](https://mlsanity.com/paper/2110.14168/) (2021)
- [Measuring Massive Multitask Language Understanding](https://mlsanity.com/paper/2009.03300/) (2020)
- [Scaling Laws for Neural Language Models](https://mlsanity.com/paper/2001.08361/) (2020)
- [Think you have Solved Question Answering? Try ARC, the AI2 Reasoning Challenge](https://mlsanity.com/paper/1803.05457/) (2018)
- [HellaSwag: Can a Machine Really Finish Your Sentence?](https://mlsanity.com/paper/1905.07830/) (2019)
- [Qwen2.5-Math Technical Report: Toward Mathematical Expert Model via Self-Improvement](https://mlsanity.com/paper/2409.12122/) (2024)
- [100 instances is all you need: predicting the success of a new LLM on unseen data by testing on a few instances](https://mlsanity.com/paper/2409.03563/) (2024)
- [LLMs-as-Instructors: Learning from Errors Toward Automating Model Improvement](https://mlsanity.com/paper/2407.00497/) (2024)
- [Model Utility Law: Evaluating LLMs beyond Performance through Mechanism Interpretable Metric](https://mlsanity.com/paper/2504.07440/) (2025)

## Built on by (most cited first, 9 of 9)

- [Do LLMs Signal When They're Right? Evidence from Neuron Agreement](https://mlsanity.com/paper/2510.26277/) (2025)
- [SparseEval: Efficient Evaluation of Large Language Models by Sparse Optimization](https://mlsanity.com/paper/2602.07909/) (2026)
- [Beyond Benchmarks: Understanding Mixture-of-Experts Models through Internal Mechanisms](https://mlsanity.com/paper/2509.23933/) (2025)
- [ErrorMap and ErrorAtlas: Charting the Failure Landscape of Large Language Models](https://mlsanity.com/paper/2601.15812/) (2026)
- [Learning More from Less: Unlocking Internal Representations for Benchmark Compression](https://mlsanity.com/paper/2602.00710/) (2026)
- [Efficient Benchmarking Is Just Feature Selection and Multiple Regression](https://mlsanity.com/paper/2605.25773/) (2026)
- [Zipbench: Low-Cost Framework for Compressing Comprehensive Benchmarks of Large Language Models](https://mlsanity.com/paper/2609.12475/) (2026)
- [Belief-Trajectory Energy: Measuring the Path to a Prediction](https://mlsanity.com/paper/2610.05114/) (2026)
- [Are We Testing Too Much? A Survey of Benchmark Compression for Efficient Evaluation of Large Language Models](https://mlsanity.com/paper/2610.18248/) (2026)

## Abstract (arXiv)

The rapid advancement of large language models (LLMs) and the development of increasingly large and diverse evaluation benchmarks have introduced substantial computational challenges for model assessment. In this paper, we present EffiEval, a training-free approach for efficient benchmarking that effectively addresses data redundancy while maintaining high evaluation reliability. Our method is specifically designed to meet three key criteria for high-quality evaluation: representativeness, by ensuring comprehensive coverage of model capabilities; fairness, by remaining independent of model performance during sample selection to avoid bias; and generalizability, by enabling flexible transfer across datasets and model families without reliance on large-scale evaluation data. Unlike traditional methods that rely on absolute performance or require extensive evaluation data, our approach adaptively selects high-quality representative subsets based on the Model Utility Index (MUI). Extensive experiments on multiple public benchmarks and diverse LLMs demonstrate that EffiEval achieves strong ranking consistency with full-dataset evaluation using only a small fraction of the original data. Furthermore, our method is flexible and scalable in size, allowing users to balance evaluation efficiency and representativeness according to specific needs. Overall, EffiEval provides a practical and generalizable solution for reliable, fair, and efficient evaluation in the era of LLMs.