# Growing Pains: Extensible and Efficient LLM Benchmarking Via Fixed Parameter Calibration

arXiv: https://arxiv.org/abs/2604.12843 · HTML: https://mlsanity.com/paper/2604.12843/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 9 of its 24 references that are in the map.
- First posted on arXiv 14 Apr 2026.

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

- [Revealing the structure of language model capabilities](https://mlsanity.com/paper/2306.10062/) (2023)
- [metabench -- A Sparse Benchmark of Reasoning and Knowledge in Large Language Models](https://mlsanity.com/paper/2407.12844/) (2024)
- [A Rosetta Stone for AI Benchmarks](https://mlsanity.com/paper/2512.00193/) (2025)
- [Fluid Language Model Benchmarking](https://mlsanity.com/paper/2509.11106/) (2025)
- [Reliable and Efficient Amortized Model-based Evaluation](https://mlsanity.com/paper/2503.13335/) (2025)
- [Adaptive Testing for LLM Evaluation: A Psychometric Alternative to Static Benchmarks](https://mlsanity.com/paper/2511.04689/) (2025)
- [Do These LLM Benchmarks Agree? Fixing Benchmark Evaluation with BenchBench](https://mlsanity.com/paper/2407.13696/) (2024)
- [Sloth: scaling laws for LLM skills to predict multi-benchmark performance across families](https://mlsanity.com/paper/2412.06540/) (2024)
- [From Benchmarks to Skills: Low-Rank Factors for LLM Evaluation](https://mlsanity.com/paper/2507.20208/) (2025)

## Abstract (arXiv)

The rapid release of both language models and benchmarks makes it increasingly costly to evaluate every model on every dataset. In practice, models are often evaluated on different samples, making scores difficult to compare across studies. To address this, we propose a framework based on multidimensional Item Response Theory (IRT) that uses anchor items to calibrate new benchmarks to the evaluation suite while holding previously calibrated item parameters fixed. Our approach supports a realistic evaluation setting in which datasets are introduced over time and models are evaluated only on the datasets available at the time of evaluation, while a fixed anchor set for each dataset is used so that results from different evaluation periods can be compared directly. In large-scale experiments on more than 400 models, our framework predicts full-evaluation performance within 2-3 percentage points using only 100 anchor questions per dataset, with Spearman ρ ≥ 0.9 for ranking preservation preservation. This shows that benchmark suites can grow over time while preserving score comparability, since adding a new dataset requires running existing models only on that dataset's anchors. Code and data are available at: https://eliyahabba.github.io/growing-pains/