Search: “benchmark”

arXiv:2502.20780v2 Announce Type: replace-cross Abstract: The increasing use of vision-language models (VLMs) in healthcare applications presents great challenges related to hallucinations, in which t

Ethan Mollick highlights that large, currently under‑explored benchmarks (e.g., ARC‑AGI, GDPval, METR long horizons, ASI cyber tasks) are growing in complexity, yet they increasingly lack systematic h

arXiv:2601.06300v2 Announce Type: replace Abstract: Clinical trial amendments frequently introduce delays, increased costs, and administrative burden, with eligibility criteria being the most commonly

arXiv:2607.26791v1 Announce Type: cross Abstract: Large Language Model (LLM) agents are increasingly adopted in real-world security operations with access to host artifacts and command-line interfaces

arXiv:2607.22689v1 Announce Type: new Abstract: Graphical user interface (GUI) agents are systems powered by large multimodal models (LMMs). They perceive screen state and execute user instructions th

arXiv:2607.23507v1 Announce Type: cross Abstract: Choosing the right text embedding model is one of the most consequential -- and most frequently under-examined -- decisions in building a retrieval or

arXiv:2607.24016v1 Announce Type: new Abstract: Recent advances in generative models have shifted AI-generated image detection from identifying easily distinguishable, fully synthetic images to identi

arXiv:2607.24449v1 Announce Type: cross Abstract: International recruitment in France requires navigating a layered legal framework absent from existing legal AI benchmarks. We present a publicly avai

arXiv:2607.24368v1 Announce Type: new Abstract: Long-term memory systems store what a user says in an external store and retrieve it when a related query arrives. This interface rests on an assumption

On FrontierCode 1.1, our benchmark for real-world engineering tasks that grades mergeability and quality, Opus 5 scores 63.6% with a 69.6% pass rate on Extended — approaching Fable 5 at half the cost.

arXiv:2607.20558v1 Announce Type: cross Abstract: AI Assistants are increasingly deployed in high-stakes settings, such as healthcare or government services. Yet their real-world behavior remains poor

arXiv:2607.19772v1 Announce Type: new Abstract: Dynamic RGBT (DRGBT) tracking aims to continuously localize a target when the available sensing modalities and observation platforms vary over time. Com

arXiv:2607.11192v2 Announce Type: replace Abstract: A large share of day-to-day work in professional domains happens inside PDF files: benefits packets, leases, datasheets, clinical guidelines, constr

arXiv:2607.08093v1 Announce Type: new Abstract: Large language models (LLMs) increasingly act as integrated data-science agents, combining abstract reasoning with advanced tool use. Yet the relevant b

GROK 4.5 LEADS ON REAL PROFESSIONAL WORK BENCHMARK New data from Snorkel shows Grok 4.5 outperforming other frontier models on real-world professional tasks. On their GDPval+ benchmark (expert-created

arXiv:2607.07391v1 Announce Type: new Abstract: Mathematical reasoning benchmarks typically provide all facts needed to solve each problem, while interactive benchmarks often mix reasoning with tools,

The metrics discussion at OpenAI is a little confusing to me. I appreciate the clarification about bad benchmarks, but they spent a lot of money developing a very good benchmark of autonomous model ab

arXiv:2607.01751v1 Announce Type: cross Abstract: Existing medical video benchmarks primarily evaluate whether a model produces the correct answer, but rarely assess whether it answers at the right ti

arXiv:2606.19096v2 Announce Type: replace Abstract: European Portuguese (pt-PT) is largely absent from OCR benchmarks, which skew toward high-resource languages. The few benchmarks that cover pt-PT fo

arXiv:2406.08311v3 Announce Type: replace-cross Abstract: Existing evaluations of tabular synthesis models rely primarily on low-order statistics and downstream task performance, leaving multivariate

arXiv:2606.30452v1 Announce Type: new Abstract: Tabular data dominate the landscape of data science, increasingly attracting innovative machine learning models and tailored benchmarks. Yet, little is

arXiv:2509.26468v3 Announce Type: replace Abstract: Benchmark quality is critical for meaningful evaluation and sustained progress in time series forecasting, particularly with the rise of pretrained

arXiv:2606.23716v1 Announce Type: cross Abstract: Legal AI benchmark research frequently invokes the assumption that large language models can improve access to justice, including for people who canno

arXiv:2606.12117v1 Announce Type: cross Abstract: Benchmark scores often misrepresent a large language model's (LLM's) knowledge, because they rely, e.g., on the model's ability to follow specific for

arXiv:2509.17455v2 Announce Type: replace-cross Abstract: State-of-the-art NLP benchmarks require interpretation of natural language that specifies conditions, procedures, and exceptions, often relyin

arXiv:2606.05241v1 Announce Type: cross Abstract: Public benchmarks enable fair and reproducible evaluation of LLM reasoning, but they become fragile for deep research agents that actively search the

arXiv:2507.21638v2 Announce Type: replace Abstract: The development of reinforcement learning (RL) algorithms has been largely driven by ambitious challenge tasks and benchmarks. Games have dominated

arXiv:2512.07795v2 Announce Type: replace Abstract: Benchmark scores for LLM reasoning systems are reported as single numbers, yet the same model, strategy, and task can produce meaningfully different

arXiv:2505.17163v2 Announce Type: replace-cross Abstract: Recent advancements in multimodal slow-thinking systems have demonstrated remarkable performance across various visual reasoning tasks. Howeve

arXiv:2605.25272v1 Announce Type: new Abstract: While aggregate leaderboard scores drive AI development, they contain substantial measurement noise whose sources and magnitudes remain unquantified, ma

arXiv:2605.24945v1 Announce Type: cross Abstract: Accurate evaluation of weather forecasting models is critical for their reliable deployment in real-world applications. However, existing benchmarks p

arXiv:2605.25492v1 Announce Type: new Abstract: Pairwise model comparisons drawn from foundation-model benchmarks ('A is safer than B') are read as quantitative verdicts but hinge on harness choices b

arXiv:2605.23215v1 Announce Type: cross Abstract: LLM-based agents for GPU kernel generation are advancing rapidly, yet their progress is fundamentally constrained by the benchmarks they optimize agai

arXiv:2605.23701v1 Announce Type: new Abstract: We study a protocol-level test for weak-label benchmarks: whether benchmark outputs change when the provided evidence is intervened on. Metadata-only sh

arXiv:2605.23170v1 Announce Type: cross Abstract: Position-controlled evaluation is standard for retrieval tasks such as Needle-in-a-Haystack and RULER, but mainstream reasoning benchmarks do not cont

arXiv:2605.21543v1 Announce Type: new Abstract: Benchmark data contamination has become a central challenge in LLM evaluation: when evaluation examples appear in the training data of one or more audit

For anyone who isn't sure, this is how you release a model and talk about the performance. Not 3-5 cherry-picked benchmarks. Performance：Qwen3.7-Max performs strongly across benchmarks in coding agent

arXiv:2605.21479v1 Announce Type: new Abstract: Visual Question Answering (VQA) benchmarks have largely emphasized perception-based tasks that can be solved from visual content alone. In contrast, man

arXiv:2601.11895v3 Announce Type: replace-cross Abstract: DevBench is a telemetry-driven benchmark designed to evaluate Large Language Models (LLMs) on realistic code completion tasks. It includes 1,8

arXiv:2605.14537v1 Announce Type: new Abstract: We introduce extsc{Cattle Trade, a multi-agent benchmark for evaluating large language models (LLMs) as agents in strategic reasoning under imperfect in

arXiv:2605.14167v1 Announce Type: new Abstract: Every AI benchmark operationalizes theoretical assumptions about the capability it claims to assess. When assumptions function as unexamined commitments

arXiv:2605.12361v1 Announce Type: new Abstract: Evaluating large language models (LLMs) in the biomedical domain requires benchmarks that can distinguish reasoning from pattern matching and remain dis

arXiv:2605.10448v1 Announce Type: new Abstract: Interactive agent benchmarks map an agent run to a binary outcome through outcome checks. When these checks rely on surface level signals or fail to cap

arXiv:2605.08197v1 Announce Type: cross Abstract: Most causal benchmarks for language models score local answers or graph structure. We introduce ReplaySCM, a 1,300 item benchmark for executable causa

arXiv:2603.24946v2 Announce Type: replace-cross Abstract: Large language models (LLMs) have shown strong performance on automated software engineering tasks, yet existing benchmarks focus primarily on

arXiv:2605.02003v1 Announce Type: new Abstract: Machine Learning (ML) has transformed many scientific fields, yet key applications still lack standardized benchmarks. Raman spectroscopy, a widely used