# Evaluating LLM Metrics Through Real-World Capabilities

arXiv: https://arxiv.org/abs/2505.08253 · HTML: https://mlsanity.com/paper/2505.08253/

## Key facts

- Cited by 18 papers in the map (data through 14 Oct 2026).
- Builds on 39 of its 97 references that are in the map.
- First posted on arXiv 13 May 2025.

## Builds on (most cited first, 30 of 39)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [Training language models to follow instructions with human feedback](https://mlsanity.com/paper/2203.02155/) (2022)
- [Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer](https://mlsanity.com/paper/1910.10683/) (2019)
- [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)
- [Constitutional AI: Harmlessness from AI Feedback](https://mlsanity.com/paper/2212.08073/) (2022)
- [GPQA: A Graduate-Level Google-Proof Q&A Benchmark](https://mlsanity.com/paper/2311.12022/) (2023)
- [LiveCodeBench: Holistic and Contamination Free Evaluation of Large Language Models for Code](https://mlsanity.com/paper/2403.07974/) (2024)
- [MMLU-Pro: A More Robust and Challenging Multi-Task Language Understanding Benchmark](https://mlsanity.com/paper/2406.01574/) (2024)
- [τ-bench: A Benchmark for Tool-Agent-User Interaction in Real-World Domains](https://mlsanity.com/paper/2406.12045/) (2024)
- [Chatbot Arena: An Open Platform for Evaluating LLMs by Human Preference](https://mlsanity.com/paper/2403.04132/) (2024)
- [Large Language Models are not Fair Evaluators](https://mlsanity.com/paper/2305.17926/) (2023)
- [AGIEval: A Human-Centric Benchmark for Evaluating Foundation Models](https://mlsanity.com/paper/2304.06364/) (2023)
- [Phi-4 Technical Report](https://mlsanity.com/paper/2412.08905/) (2024)
- [Can LLM Already Serve as A Database Interface? A BIg Bench for Large-Scale Database Grounded Text-to-SQLs](https://mlsanity.com/paper/2305.03111/) (2023)
- [Humanity's Last Exam](https://mlsanity.com/paper/2501.14249/) (2025)
- [Artificial Intelligence, Values and Alignment](https://mlsanity.com/paper/2001.09768/) (2020)
- [Measuring short-form factuality in large language models](https://mlsanity.com/paper/2411.04368/) (2024)
- [Effect of Confidence and Explanation on Accuracy and Trust Calibration in AI-Assisted Decision Making](https://mlsanity.com/paper/2001.02114/) (2020)
- [Leak, Cheat, Repeat: Data Contamination and Evaluation Malpractices in Closed-Source LLMs](https://mlsanity.com/paper/2402.03927/) (2024)
- [Generative AI](https://mlsanity.com/paper/2309.07930/) (2023)
- [CodeElo: Benchmarking Competition-level Code Generation of LLMs with Human-comparable Elo Ratings](https://mlsanity.com/paper/2501.01257/) (2025)
- [WritingBench: A Comprehensive Benchmark for Generative Writing](https://mlsanity.com/paper/2503.05244/) (2025)
- [SWE-Bench+: Enhanced Coding Benchmark for LLMs](https://mlsanity.com/paper/2410.06992/) (2024)
- [Which Economic Tasks are Performed with AI? Evidence from Millions of Claude Conversations](https://mlsanity.com/paper/2503.04761/) (2025)
- [Michelangelo: Long Context Evaluations Beyond Haystacks via Latent Structure Queries](https://mlsanity.com/paper/2409.12640/) (2024)
- [A Systematic Survey and Critical Review on Evaluating Large Language Models: Challenges, Limitations, and Recommendations](https://mlsanity.com/paper/2407.04069/) (2024)
- [A Complete Survey on LLM-based AI Chatbots](https://mlsanity.com/paper/2406.16937/) (2024)
- [The Leaderboard Illusion](https://mlsanity.com/paper/2504.20879/) (2025)

## Built on by (most cited first, 18 of 18)

- [Object Detection with Multimodal Large Vision-Language Models: An In-depth Review](https://mlsanity.com/paper/2508.19294/) (2025)
- [ATLAS: A High-Difficulty, Multidisciplinary Benchmark for Frontier Scientific Reasoning](https://mlsanity.com/paper/2511.14366/) (2025)
- [Paying Less Generalization Tax: A Cross-Domain Generalization Study of RL Training for LLM Agents](https://mlsanity.com/paper/2601.18217/) (2026)
- [Federate the Router: Learning Language Model Routers with Sparse and Decentralized Evaluations](https://mlsanity.com/paper/2601.22318/) (2026)
- [Robust Checkpoint Selection for Multimodal LLMs via Agentic Evaluation and Stability-Aware Ranking](https://mlsanity.com/paper/2605.18852/) (2026)
- [Do Language Models Think Consistently? A Study of Value Preferences Across Varying Response Lengths](https://mlsanity.com/paper/2506.02481/) (2025)
- [Mapping Overlaps in Benchmarks through Perplexity in the Wild](https://mlsanity.com/paper/2509.23488/) (2025)
- [Drawing Conclusions from Draws: Rethinking Preference Semantics in Arena-Style LLM Evaluation](https://mlsanity.com/paper/2510.02306/) (2025)
- [Simulated Self-Assessment in Large Language Models: A Psychometric Approach to AI Self-Efficacy](https://mlsanity.com/paper/2511.19872/) (2025)
- [Plausibility as Failure: How LLMs and Humans Co-Construct Epistemic Error](https://mlsanity.com/paper/2512.16750/) (2025)
- [NC-Bench: An LLM Benchmark for Evaluating Conversational Competence](https://mlsanity.com/paper/2601.06426/) (2026)
- [How to Ask the AI: A User Perspective Survey for Large Language Model Prompting](https://mlsanity.com/paper/2608.07494/) (2026)
- [Uncovering Competency Gaps in Large Language Models and Their Benchmarks](https://mlsanity.com/paper/2512.20638/) (2025)
- [Who Does What? Archetypes of Roles Assigned to LLMs During Human-AI Decision-Making](https://mlsanity.com/paper/2602.11924/) (2026)
- [Simulating Meaning, Nevermore! Introducing ICR: A Semiotic-Hermeneutic Metric for Evaluating Meaning in LLM Text Summaries](https://mlsanity.com/paper/2603.04413/) (2026)
- [RobustMAD: Evaluating Real-World Robustness of Multimodal Small Language Models for Deployable Anomaly Detection Assistants](https://mlsanity.com/paper/2607.16243/) (2026)
- [Beyond Leaderboards: Tokenomics of Agentic Small Language Model Ensembles](https://mlsanity.com/paper/2610.00954/) (2026)
- [Improving the Evaluation of Biomedical Question Answering with Few Human Preference Signals](https://mlsanity.com/paper/2610.16008/) (2026)

## Abstract (arXiv)

As generative AI becomes increasingly embedded in everyday workflows, it is important to evaluate its performance in ways that reflect real-world usage rather than abstract notions of intelligence. Unlike many existing benchmarks that assess general intelligence, our approach focuses on real-world utility, evaluating how well models support users in everyday tasks. While current benchmarks emphasize code generation or factual recall, users rely on AI for a much broader range of activities-from writing assistance and summarization to citation formatting and stylistic feedback. In this paper, we analyze large-scale survey data and usage logs to identify six core capabilities that represent how people commonly use Large Language Models (LLMs): Summarization, Technical Assistance, Reviewing Work, Data Structuring, Generation, and Information Retrieval. We then assess the extent to which existing benchmarks cover these capabilities, revealing significant gaps in coverage, efficiency measurement, and interpretability. Drawing on this analysis, we use human-centered criteria to identify gaps in how well current benchmarks reflect common usage that is grounded in five practical criteria: coherence, accuracy, clarity, relevance, and efficiency. For four of the six capabilities, we identify the benchmarks that best align with real-world tasks and use them to compare leading models. We find that Google Gemini outperforms other models-including OpenAI's GPT, xAI's Grok, Meta's LLaMA, Anthropic's Claude, DeepSeek, and Qwen from Alibaba-on these utility-focused metrics.