# ExpertLongBench: Benchmarking Language Models on Expert-Level Long-Form Generation Tasks with Structured Checklists

arXiv: https://arxiv.org/abs/2506.01241 · HTML: https://mlsanity.com/paper/2506.01241/

## Key facts

- Cited by 24 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 2 Jun 2025.

## Built on by (most cited first, 24 of 24)

- [Rubrics as Rewards: Reinforcement Learning Beyond Verifiable Domains](https://mlsanity.com/paper/2507.17746/) (2025)
- [ResearchRubrics: A Benchmark of Prompts and Rubrics For Evaluating Deep Research Agents](https://mlsanity.com/paper/2511.07685/) (2025)
- [VitaBench: Benchmarking LLM Agents with Versatile Interactive Tasks in Real-world Applications](https://mlsanity.com/paper/2509.26490/) (2025)
- [DeepResearch Arena: The First Exam of LLMs' Research Abilities via Seminar-Grounded Tasks](https://mlsanity.com/paper/2509.01396/) (2025)
- [FinDeepResearch: Evaluating Deep Research Agents in Rigorous Financial Analysis](https://mlsanity.com/paper/2510.13936/) (2025)
- [DRACO: a Cross-Domain Benchmark for Deep Research Accuracy, Completeness, and Objectivity](https://mlsanity.com/paper/2602.11685/) (2026)
- [DEER: A Benchmark for Evaluating Deep Research Agents on Expert Report Generation](https://mlsanity.com/paper/2512.17776/) (2025)
- [DeepFact: Co-Evolving Benchmarks and Agents for Deep Research Factuality](https://mlsanity.com/paper/2603.05912/) (2026)
- [Scaling Policy Compliance Assessment in Language Models with Policy Reasoning Traces](https://mlsanity.com/paper/2509.23291/) (2025)
- [RefGrader: Automated Grading of Mathematical Competition Proofs using Agentic Workflows](https://mlsanity.com/paper/2510.09021/) (2025)
- [Beyond Single-shot Writing: Deep Research Agents are Unreliable at Multi-turn Report Revision](https://mlsanity.com/paper/2601.13217/) (2026)
- [From Holistic Evaluation to Structured Criteria: Rubrics Across the Evolving LLM Landscape](https://mlsanity.com/paper/2606.08625/) (2026)
- [FrontierFinance: A Challenging Benchmark for Measuring Frontier Intelligence of Finance Agents](https://mlsanity.com/paper/2608.11683/) (2026)
- [JADE: Expert-Grounded Dynamic Evaluation for Open-Ended Professional Tasks](https://mlsanity.com/paper/2602.06486/) (2026)
- [Two-Level Meta-Rubrics for Evaluating Open-Ended Generation: GAMUT, a Benchmark for Factual Completeness](https://mlsanity.com/paper/2607.19322/) (2026)
- [DR3-Eval: Towards Realistic and Reproducible Deep Research Evaluation](https://mlsanity.com/paper/2604.14683/) (2026)
- [UsefulBench: Towards Decision-Useful Information as a Target for Information Retrieval](https://mlsanity.com/paper/2604.15827/) (2026)
- [Can AI Agents Synthesize Scientific Conclusions?](https://mlsanity.com/paper/2606.11337/) (2026)
- [CLINB: A Climate Intelligence Benchmark for Foundational Models](https://mlsanity.com/paper/2511.11597/) (2025)
- [Feedback-to-Rubrics: Can We Learn Expert Criteria from Inline Comments?](https://mlsanity.com/paper/2605.29857/) (2026)
- [Decomposer: Learning to Decompile Symbolic Music to Programs](https://mlsanity.com/paper/2607.01849/) (2026)
- [Expectation Alignment of Language Models for Real-World User Expectations](https://mlsanity.com/paper/2607.20485/) (2026)
- [A rubric landscape for evaluating clinical reasoning in large language models: what exists, what is missing, and what needs to be combined](https://mlsanity.com/paper/2610.01938/) (2026)
- [Hindsight Structured Advice Distillation: Steering Executor Agents with Advisors Trained on Their Failures and Task Characteristics](https://mlsanity.com/paper/2610.13000/) (2026)

## Abstract (arXiv)

This paper introduces ExpertLongBench, an expert-level benchmark containing 11 tasks from 9 domains that reflect realistic expert workflows and applications. Beyond question answering, the application-driven tasks in ExpertLongBench demand long-form outputs that can exceed 5,000 tokens and strict adherence to domain-specific requirements. Notably, each task in ExpertLongBench includes a rubric, designed or validated by domain experts, to specify task requirements and guide output evaluation. Furthermore, we propose CLEAR, an evaluation framework that supports accurate evaluation of long-form model outputs in our benchmark. To achieve fine-grained, expert-aligned evaluation, CLEAR derives checklists from both model outputs and references by extracting information corresponding to items in the task-specific rubric. Checklist items of model outputs are then compared with corresponding items of reference outputs to assess their correctness, enabling grounded evaluation. We benchmark 13 popular large language models (LLMs) and analyze components in CLEAR, showing that (1) existing LLMs, with the top performer Gemini-2.5-Pro achieving only a 33.4 F1 score, require significant improvement for expert-level tasks; (2) models can generate content corresponding to the required aspects, but far from correct; and (3) accurate checklist extraction and comparison in CLEAR can be achieved by open-weight models for more scalable, reproducible, and low-cost usage.