LongBench Pro: A More Realistic and Comprehensive Bilingual Long-Context Evaluation Benchmark

• URL: http://arxiv.org/abs/2601.02872v1
• Date: Tue, 06 Jan 2026 10:01:59 GMT
• Title: LongBench Pro: A More Realistic and Comprehensive Bilingual Long-Context Evaluation Benchmark
• Authors: Ziyang Chen, Xing Wu, Junlong Jia, Chaochen Gao, Qi Fu, Debing Zhang, Songlin Hu,
• Abstract summary: LongBench Pro is a more realistic benchmark of 1,500 naturally occurring long-context samples in English and Chinese.<n>It supports fine-grained analysis with task-specific metrics and a multi-dimensional taxonomy of context requirement.<n>LongBench Pro provides a robust testbed for advancing long-context understanding.
• Score: 24.104346815675886
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: The rapid expansion of context length in large language models (LLMs) has outpaced existing evaluation benchmarks. Current long-context benchmarks often trade off scalability and realism: synthetic tasks underrepresent real-world complexity, while fully manual annotation is costly to scale to extreme lengths and diverse scenarios. We present LongBench Pro, a more realistic and comprehensive bilingual benchmark of 1,500 naturally occurring long-context samples in English and Chinese spanning 11 primary tasks and 25 secondary tasks, with input lengths from 8k to 256k tokens. LongBench Pro supports fine-grained analysis with task-specific metrics and a multi-dimensional taxonomy of context requirement (full vs. partial dependency), length (six levels), and difficulty (four levels calibrated by model performance). To balance quality with scalability, we propose a Human-Model Collaborative Construction pipeline: frontier LLMs draft challenging questions and reference answers, along with design rationales and solution processes, to reduce the cost of expert verification. Experts then rigorously validate correctness and refine problematic cases. Evaluating 46 widely used long-context LLMs on LongBench Pro yields three findings: (1) long-context optimization contributes more to long-context comprehension than parameter scaling; (2) effective context length is typically shorter than the claimed context length, with pronounced cross-lingual misalignment; and (3) the "thinking" paradigm helps primarily models trained with native reasoning, while mixed-thinking designs offer a promising Pareto trade-off. In summary, LongBench Pro provides a robust testbed for advancing long-context understanding.

Related papers

• A Controllable Examination for Long-Context Language Models [62.845852724511964]
  This study introduces $textbfLongBioBench, a benchmark for evaluating long-context language models.<n>We show that most models still exhibit deficiencies in semantic understanding and elementary reasoning over retrieved results.<n>Our further analysis indicates some design choices employed by existing synthetic benchmarks, such as contextual non-coherence.
  arXiv  Detail & Related papers  (2025-06-03T14:23:06Z)
• 100-LongBench: Are de facto Long-Context Benchmarks Literally Evaluating Long-Context Ability? [28.694112253150983]
  Real-task-based long-context evaluation benchmarks have two major shortcomings.<n> benchmarks like LongBench often do not provide proper metrics to separate long-context performance from the model's baseline ability.<n>We introduce a length-controllable long-context benchmark and a novel metric that disentangles baseline knowledge from true long-context capabilities.
  arXiv  Detail & Related papers  (2025-05-25T19:58:31Z)
• Generalizing From Short to Long: Effective Data Synthesis for Long-Context Instruction Tuning [103.65680870130839]
  We investigate how to design instruction data for the post-training phase of a long context pre-trained model.<n>Our controlled study reveals that models instruction-tuned on short contexts can effectively generalize to longer ones.<n>Based on these findings, we propose context synthesis, a novel data synthesis framework.
  arXiv  Detail & Related papers  (2025-02-21T17:02:40Z)
• LongBench v2: Towards Deeper Understanding and Reasoning on Realistic Long-context Multitasks [74.96182906307654]
  This paper introduces LongBench v2, a benchmark designed to assess the ability of LLMs to handle long-context problems.<n>LongBench v2 consists of 503 challenging multiple-choice questions, with contexts ranging from 8k to 2M words, across six major task categories.<n>We employ both automated and manual review processes to maintain high quality and difficulty, resulting in human experts achieving only 53.7% accuracy under a 15-minute time constraint.
  arXiv  Detail & Related papers  (2024-12-19T18:59:17Z)
• How to Train Long-Context Language Models (Effectively) [75.5418485597276]
  We study continued training and supervised fine-tuning (SFT) of a language model (LM) to make effective use of long-context information.<n>We find that code repositories and books are excellent sources of long data, but it is crucial to combine them with high-quality short-context data.<n>Our final model, ProLong-8B, demonstrates state-of-the-art long-context performance among similarly sized models at a length of 128K.
  arXiv  Detail & Related papers  (2024-10-03T16:46:52Z)
• Leave No Document Behind: Benchmarking Long-Context LLMs with Extended Multi-Doc QA [71.04146366608904]
  Long-context modeling capabilities have garnered widespread attention, leading to the emergence of Large Language Models (LLMs) with ultra-context windows. We propose a novel long-context benchmark, Loong, aligning with realistic scenarios through extended multi-document question answering (QA) Loong introduces four types of tasks with a range of context lengths: Spotlight Locating, Comparison, Clustering, and Chain of Reasoning.
  arXiv  Detail & Related papers  (2024-06-25T09:42:56Z)
• XL$^2$Bench: A Benchmark for Extremely Long Context Understanding with Long-range Dependencies [45.31042312867939]
  Large Language Models (LLMs) have demonstrated remarkable performance across diverse tasks but are constrained by their small context window sizes. Various efforts have been proposed to expand the context window to accommodate even up to 200K input tokens. We introduce a benchmark for extremely long context understanding with long-range dependencies, XL$2$Bench.
  arXiv  Detail & Related papers  (2024-04-08T12:29:07Z)
• LongBench: A Bilingual, Multitask Benchmark for Long Context Understanding [58.20031627237889]
  LongBench is the first bilingual, multi-task benchmark for long context understanding. It comprises 21 datasets across 6 task categories in both English and Chinese, with an average length of 6,711 words (English) and 13,386 characters (Chinese)
  arXiv  Detail & Related papers  (2023-08-28T11:53:40Z)

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.