REVIEW 15 cited by
Long Code Arena: a Set of Benchmarks for Long-Context Code Models
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
Long Code Arena: a Set of Benchmarks for Long-Context Code Models
read the original abstract
Nowadays, the fields of code and natural language processing are evolving rapidly. In particular, models become better at processing long context windows - supported context sizes have increased by orders of magnitude over the last few years. However, there is a shortage of benchmarks for code processing that go beyond a single file of context, while the most popular ones are limited to a single method. With this work, we aim to close this gap by introducing Long Code Arena, a suite of six benchmarks for code processing tasks that require project-wide context. These tasks cover different aspects of code processing: library-based code generation, CI builds repair, project-level code completion, commit message generation, bug localization, and module summarization. For each task, we provide a manually verified dataset for testing, an evaluation suite, and open-source baseline solutions based on popular LLMs to showcase the usage of the dataset and to simplify adoption by other researchers. We publish the benchmark page on HuggingFace Spaces with the leaderboard, links to HuggingFace Hub for all the datasets, and link to the GitHub repository with baselines: https://huggingface.co/spaces/JetBrains-Research/long-code-arena.
Forward citations
Cited by 15 Pith papers
-
ORCA-bench: How Ready Are Language Model Agents for Oncall?
Frontier coding agents achieve at most 25.3% RCA accuracy on realistic medium oncall tasks and 10% on hard ones in a production-fidelity telemetry-plus-code benchmark.
-
LibEvoBench: Probing Temporal Knowledge Stratification in Code Generation Models
LibEvoBench benchmark shows LLMs are version-oblivious on evolving APIs, with documentation helping but version specification not.
-
RepoDoc: A Knowledge Graph-Based Framework to Automatic Documentation Generation and Incremental Updates
RepoDoc uses a repository knowledge graph with module clustering and semantic impact propagation to generate more complete documentation 3x faster with 85% fewer tokens and handle incremental updates 73% faster than p...
-
CodeComp: Structural KV Cache Compression for Agentic Coding
CodeComp uses Joern-extracted Code Property Graph priors for training-free structural KV cache compression, outperforming attention-only baselines on bug localization and code generation while matching full-context pa...
-
CodeOCR: On the Effectiveness of Vision Language Models in Code Understanding
Multimodal LLMs process code as images to achieve up to 8x token compression, with visual cues like syntax highlighting aiding tasks and clone detection remaining resilient or even improving under compression.
-
Understanding Axes of Difficulty For Long Context Tasks Via PredicateLongBench
Frontier LLMs systematically fail simple long-context subsequence-retrieval tasks as difficulty is scaled along decoys, quantifier complexity, search space, and predicate arity.
-
Retrieval-Oriented Code Representations in Agentic Bug Localization
Role-aware file summaries give the best cost-effectiveness for file-level bug localization, beating file paths by up to 40% Hit@5 at far smaller footprint than raw source.
-
UNIBROWSE: A Data-to-Agent Framework for Multimodal BrowseComp
A unified KG-plus-live-web data pipeline covering all three multimodal BrowseComp information-flow patterns, plus an exploration-degree filter, yields a 35B agent at 54.4 avg accuracy.
-
FlashRT: Towards Computationally and Memory Efficient Red-Teaming for Prompt Injection and Knowledge Corruption
FlashRT delivers 2x-7x speedup and 2x-4x GPU memory reduction for prompt injection and knowledge corruption attacks on long-context LLMs versus nanoGCG.
-
SPEED-Bench: A Unified and Diverse Benchmark for Speculative Decoding
A new benchmark for speculative decoding that maximizes semantic diversity and supports throughput evaluation across input lengths, exposing biases in synthetic benchmarks.
-
SPEED-Bench: A Unified and Diverse Benchmark for Speculative Decoding
SPEED-Bench is a new standardized benchmark for speculative decoding that supplies semantically diverse qualitative data and throughput-oriented splits across concurrency levels, integrated with vLLM and TensorRT-LLM.
-
Kimi Linear: An Expressive, Efficient Attention Architecture
Kimi Linear hybridizes linear attention with a new KDA module to beat full attention on tasks while slashing KV cache by 75% and speeding decoding up to 6x.
-
How can we assess human-agent interactions? Case studies in software agent design
PULSE combines sparse human ratings with prediction-powered inference to cut confidence intervals by ~40% and shows LLM choice matters more than scaffolding for user satisfaction.
-
TreeRanker: Fast and Model-agnostic Ranking System for Code Suggestions in IDEs
TreeRanker ranks static code completions by organizing candidates in a prefix tree and collecting token scores via a single greedy language-model decoding pass.
-
Challenge on Optimization of Context Collection for Code Completion
A new Python/Kotlin benchmark and competition show retrieval-based context can improve fill-in-the-middle code completion chrF scores, with a caveat about possible data leakage.
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.