# DocPuzzle: A Process-Aware Benchmark for Evaluating Realistic Long-Context Reasoning Capabilities

arXiv: https://arxiv.org/abs/2502.17807 · HTML: https://mlsanity.com/paper/2502.17807/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Placed in Reasoning benchmarks and evaluation, one of 17 directions in LLM reasoning.
- Builds on 10 of its 35 references that are in the map.
- First posted on arXiv 25 Feb 2025.

## Placed in

- LLM reasoning / [Reasoning benchmarks and evaluation](https://mlsanity.com/lr/reasoning-benchmarks-and-evaluation/)
- Knowledge distillation / [Knowledge distillation for LLMs](https://mlsanity.com/distill/knowledge-distillation-for-llms/)

## Builds on (most cited first, 10 of 10)

- [DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning](https://mlsanity.com/paper/2501.12948/) (2025)
- [Qwen2.5 Technical Report](https://mlsanity.com/paper/2412.15115/) (2024)
- [Large Language Models are Zero-Shot Reasoners](https://mlsanity.com/paper/2205.11916/) (2022)
- [Let's Verify Step by Step](https://mlsanity.com/paper/2305.20050/) (2023)
- [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)
- [DeepSeek-V3 Technical Report](https://mlsanity.com/paper/2412.19437/) (2024)
- [Did Aristotle Use a Laptop? A Question Answering Benchmark with Implicit Reasoning Strategies](https://mlsanity.com/paper/2101.02235/) (2021)
- [SFT Memorizes, RL Generalizes: A Comparative Study of Foundation Model Post-training](https://mlsanity.com/paper/2501.17161/) (2025)
- [Humanity's Last Exam](https://mlsanity.com/paper/2501.14249/) (2025)

## Built on by (most cited first, 4 of 4)

- [Context Is What You Need: The Maximum Effective Context Window for Real World Limits of LLMs](https://mlsanity.com/paper/2509.21361/) (2025)
- [Hidden in the Haystack: Smaller Needles are More Difficult for LLMs to Find](https://mlsanity.com/paper/2505.18148/) (2025)
- [LongReasonArena: A Long Reasoning Benchmark for Large Language Models](https://mlsanity.com/paper/2508.19363/) (2025)
- [LongHarness: Advancing Agentic Reasoning over 100M-Token Corpora via Stateful Evidence Management](https://mlsanity.com/paper/2610.13075/) (2026)

## Abstract (arXiv)

We present DocPuzzle, a rigorously constructed benchmark for evaluating long-context reasoning capabilities in large language models (LLMs). This benchmark comprises 100 expert-level QA problems requiring multi-step reasoning over long real-world documents. To ensure the task quality and complexity, we implement a human-AI collaborative annotation-validation pipeline. DocPuzzle introduces an innovative evaluation framework that mitigates guessing bias through checklist-guided process analysis, establishing new standards for assessing reasoning capacities in LLMs. Our evaluation results show that: 1)Advanced slow-thinking reasoning models like o1-preview(69.7%) and DeepSeek-R1(66.3%) significantly outperform best general instruct models like Claude 3.5 Sonnet(57.7%); 2)Distilled reasoning models like DeepSeek-R1-Distill-Qwen-32B(41.3%) falls far behind the teacher model, suggesting challenges to maintain the generalization of reasoning capabilities relying solely on distillation.