LibEvoBench benchmark shows LLMs are version-oblivious on evolving APIs, with documentation helping but version specification not.
Long Code Arena: a Set of Benchmarks for Long-Context Code Models
9 Pith papers cite this work, alongside 5 external citations. Polarity classification is still indexing.
9
Pith papers citing it
5
external citations · Pith
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.
citation-role summary
background 3
dataset 1
citation-polarity summary
representative citing papers
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 prior LLM-based tools.
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 patch quality.
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.
Frontier LLMs systematically fail simple long-context subsequence-retrieval tasks as difficulty is scaled along decoys, quantifier complexity, search space, and predicate arity.
FlashRT delivers 2x-7x speedup and 2x-4x GPU memory reduction for prompt injection and knowledge corruption attacks on long-context LLMs versus nanoGCG.
A new benchmark for speculative decoding that maximizes semantic diversity and supports throughput evaluation across input lengths, exposing biases in synthetic benchmarks.
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.
TreeRanker ranks static code completions by organizing candidates in a prefix tree and collecting token scores via a single greedy language-model decoding pass.
citing papers explorer
-
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 prior LLM-based tools.
-
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 patch quality.
-
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.
-
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.
-
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.
-
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.