When Models Can't Follow: Testing Instruction Adherence Across 256 LLMs

• URL: http://arxiv.org/abs/2510.18892v1
• Date: Sat, 18 Oct 2025 16:33:15 GMT
• Title: When Models Can't Follow: Testing Instruction Adherence Across 256 LLMs
• Authors: Richard J. Young, Brandon Gillins, Alice M. Matthews,
• Abstract summary: This paper presents a streamlined evaluation framework using twenty carefully designed prompts to assess instruction-following.<n>We demonstrate this framework through a large-scale empirical study conducted on October 14, 2025.<n>Our findings reveal consistent failure modes and identify specific instruction types posing particular challenges.
• Score: 0.0
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: Despite widespread deployment of Large Language Models, systematic evaluation of instruction-following capabilities remains challenging. While comprehensive benchmarks exist, focused assessments that quickly diagnose specific instruction adherence patterns are valuable. As newer models may be trained on existing benchmarks, novel evaluation approaches are needed to assess genuine capabilities rather than memorized performance. This paper presents a streamlined evaluation framework using twenty carefully designed prompts to assess LLM instruction-following across diverse task categories. We demonstrate this framework through a large-scale empirical study conducted on October 14, 2025, testing 256 verified working models from 331 available via OpenRouter. To ensure methodological rigor and prevent selection bias, we first verified each model's basic functionality before inclusion. Unlike large-scale benchmarks requiring extensive computational resources, our approach offers a practical diagnostic tool researchers and practitioners can readily apply. Our methodology builds upon verifiable instructions while introducing a compact test suite balancing comprehensiveness with efficiency. Each prompt targets distinct aspects of instruction following, including format compliance, content constraints, logical sequencing, and multi-step task execution. We evaluate models from major providers (OpenAI, Anthropic, Google, Meta, Mistral) and emerging implementations (Qwen, DeepSeek, community models), providing comparative performance analysis. Our findings reveal consistent failure modes and identify specific instruction types posing particular challenges. This work contributes both a practical evaluation tool and one of the most comprehensive empirical analyses of instruction-following capabilities across the contemporary LLM landscape.

Related papers

• TraceLLM: Leveraging Large Language Models with Prompt Engineering for Enhanced Requirements Traceability [4.517933493143603]
  This paper introduces TraceLLM, a framework for enhancing requirements traceability through prompt engineering and demonstration selection.<n>We assess prompt generalization and robustness using eight state-of-the-art LLMs on four benchmark datasets.
  arXiv  Detail & Related papers  (2026-02-01T14:29:13Z)
• OODEval: Evaluating Large Language Models on Object-Oriented Design [10.295093285299403]
  We evaluate 29 large language models (LLMs) on object-oriented design tasks.<n>Top-performing LLMs nearly match the average performance of undergraduates, but remain significantly below the level of the best human designers.
  arXiv  Detail & Related papers  (2026-01-12T14:51:31Z)
• Previously on... Automating Code Review [4.096540146408279]
  Modern Code Review (MCR) is a standard practice in software engineering, yet it demands substantial time and resource investments.<n>Recent research has increasingly explored automating core review tasks using machine learning (ML) and deep learning (DL)<n>This study provides the first comprehensive analysis of MCR automation research.
  arXiv  Detail & Related papers  (2025-08-25T13:12:48Z)
• How Many Instructions Can LLMs Follow at Once? [0.16874375111244325]
  We introduce IFScale, a simple benchmark of 500 keyword-inclusion instructions for a business report writing task to measure how instruction-following performance degrades as instruction density increases.<n>We evaluate 20 state-of-the-art models across seven major providers and find that even the best frontier models only achieve 68% accuracy at the max density of 500 instructions.<n>Our insights can help inform design of instruction-dense prompts in real-world applications and highlight important performance-latency tradeoffs.
  arXiv  Detail & Related papers  (2025-07-15T17:59:42Z)
• Tests as Prompt: A Test-Driven-Development Benchmark for LLM Code Generation [1.7268889851975326]
  We introduce WebApp1K, a novel benchmark for evaluating large language models (LLMs) in test-driven development (TDD) tasks.<n>Unlike traditional approaches relying on natural language prompts, our benchmark emphasizes the ability of LLMs to interpret and implement functionality directly from test cases.
  arXiv  Detail & Related papers  (2025-05-13T23:47:12Z)
• Meeseeks: A Feedback-Driven, Iterative Self-Correction Benchmark evaluating LLMs' Instruction Following Capability [21.96694731466089]
  We introduce Meeseeks, a fully automated instruction-following benchmark equipped with an integrated feedback mechanism.<n>Meeseeks identifies erroneous components in model responses and provides corresponding feedback accurately, thereby iteratively guiding the model toward self-correction.<n>We conducted comprehensive analysis from both macro and instance levels, uncovering numerous common issues prevalent in current state-of-the-art models.
  arXiv  Detail & Related papers  (2025-04-30T13:28:19Z)
• StructTest: Benchmarking LLMs' Reasoning through Compositional Structured Outputs [78.84060166851805]
  StructTest is a novel benchmark that evaluates large language models (LLMs) on their ability to follow compositional instructions and generate structured outputs.<n> Assessments are conducted deterministically using a rule-based evaluator, which can be easily extended to new tasks and datasets.<n>We demonstrate that StructTest remains challenging even for top-performing models like Deepseek-V3/R1 and GPT-4o.
  arXiv  Detail & Related papers  (2024-12-23T22:08:40Z)
• MME-Survey: A Comprehensive Survey on Evaluation of Multimodal LLMs [97.94579295913606]
  Multimodal Large Language Models (MLLMs) have garnered increased attention from both industry and academia.<n>In the development process, evaluation is critical since it provides intuitive feedback and guidance on improving models.<n>This work aims to offer researchers an easy grasp of how to effectively evaluate MLLMs according to different needs and to inspire better evaluation methods.
  arXiv  Detail & Related papers  (2024-11-22T18:59:54Z)
• Beyond Content Relevance: Evaluating Instruction Following in Retrieval Models [25.301280441283147]
  This study evaluates the instruction-following capabilities of various retrieval models beyond content relevance.<n>We develop a novel retrieval evaluation benchmark spanning six document-level attributes.<n>Our findings indicate that although fine-tuning models on instruction-aware retrieval datasets enhance performance, most models still fall short of instruction compliance.
  arXiv  Detail & Related papers  (2024-10-31T11:47:21Z)
• Benchmarks as Microscopes: A Call for Model Metrology [76.64402390208576]
  Modern language models (LMs) pose a new challenge in capability assessment. To be confident in our metrics, we need a new discipline of model metrology.
  arXiv  Detail & Related papers  (2024-07-22T17:52:12Z)
• BLESS: Benchmarking Large Language Models on Sentence Simplification [55.461555829492866]
  We present BLESS, a performance benchmark of the most recent state-of-the-art large language models (LLMs) on the task of text simplification (TS) We assess a total of 44 models, differing in size, architecture, pre-training methods, and accessibility, on three test sets from different domains (Wikipedia, news, and medical) under a few-shot setting. Our evaluation indicates that the best LLMs, despite not being trained on TS, perform comparably with state-of-the-art TS baselines.
  arXiv  Detail & Related papers  (2023-10-24T12:18:17Z)
• OPT-IML: Scaling Language Model Instruction Meta Learning through the Lens of Generalization [101.37439352091612]
  We describe the effect of instruction-tuning decisions on downstream task performance when scaling both model and benchmark sizes. We present insights about instruction-tuning decisions as applied to OPT-30B and further exploit these insights to train OPT-IML 30B and 175B, which are instruction-tuned versions of OPT.
  arXiv  Detail & Related papers  (2022-12-22T19:56:09Z)
• NEVIS'22: A Stream of 100 Tasks Sampled from 30 Years of Computer Vision Research [96.53307645791179]
  We introduce the Never-Ending VIsual-classification Stream (NEVIS'22), a benchmark consisting of a stream of over 100 visual classification tasks. Despite being limited to classification, the resulting stream has a rich diversity of tasks from OCR, to texture analysis, scene recognition, and so forth. Overall, NEVIS'22 poses an unprecedented challenge for current sequential learning approaches due to the scale and diversity of tasks.
  arXiv  Detail & Related papers  (2022-11-15T18:57:46Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.