4arXiv cs.CL (Computation and Language)·
DataGovBench: Benchmarking LLMs on Real-World Governmental Data Analysis Tasks
Researchers introduce DataGovBench, a benchmark derived from governmental open data designed to evaluate LLMs on practical data analysis tasks beyond simple fact retrieval from small tables. The benchmark covers two tasks: Table QA (complex decomposable questions with textual or visualization outputs) and Table Insight (exploratory data analysis for expert-level findings). Experiments with state-of-the-art LLMs, with and without agentic frameworks, reveal significant performance gaps, suggesting current systems fall well short of real-world data analytics demands.
Related guides (2)
Related events (8)
Paper challenges LLM expert-level claims by measuring variance and error magnitude in code-based data analysis tasks
A new arXiv paper argues that standard LLM benchmarks overstate model capabilities by focusing on average performance on training-data-adjacent tasks while ignoring response variance and error magnitude. The authors introduce a novel benchmark requiring frontier LLMs to write code for data analysis tasks, comparing results against human expert submissions. Human experts outperformed the frontier LLM on average across multiple metrics and showed lower performance variability. The findings challenge the prevailing narrative that LLMs perform at human-expert level on knowledge economy tasks.
Text Analytics Evaluation Framework: Benchmarking LLMs on Social Media NLP Tasks
Researchers introduce a 470-question evaluation framework to assess LLM performance on aggregated social media text, applied to Twitter datasets across sentiment analysis, hate speech detection, and emotion recognition. Results show performance degrades substantially as input scale exceeds 500 instances, particularly for open-weights models on numerical tasks. Multi-label and target-dependent scenarios also show notable performance drops, and task complexity progressively erodes accuracy from basic semantic identification to comparison and counting operations. The findings point to architectural bottlenecks in current LLMs for rigorous quantitative analysis over large text collections.
Judge Arena: Benchmarking LLMs as Evaluators
Hugging Face and Atla have launched Judge Arena, a platform for benchmarking large language models in their role as automated evaluators. The initiative uses an Elo-based ranking system to compare how well different LLMs judge the quality of model outputs, addressing the growing reliance on LLM-as-judge paradigms in evaluation pipelines. This fills a meta-evaluation gap: as LLM judges become standard practice, understanding their relative reliability and biases becomes critical infrastructure for the field.
SoundnessBench: Benchmarking LLMs as Evaluators of ML Research Proposal Viability
SoundnessBench is a new benchmark of 1,099 machine-learning research proposals derived from ICLR submissions, labeled with reviewer soundness scores, designed to test whether LLMs can reliably distinguish methodologically sound research ideas from unsound ones. Evaluated across 12 frontier LLMs, the benchmark reveals a pervasive optimism bias: models systematically rate low-soundness proposals as sound under standard prompting, with aggressive prompting shifting errors from false positives to false negatives rather than eliminating them. Controls for data contamination, surface features, and human audit quality suggest the bias is not attributable to a single confounder. The authors conclude that current LLMs are not yet reliable as standalone first-gate evaluators of scientific rigor, a critical bottleneck for autonomous AI research agents.
Benchmarking study finds LLMs fail at counterintuitive probability problems despite strong standard performance
A new arXiv paper evaluates 8 state-of-the-art LLMs on discrete probability problems using two datasets: standard exercises (average accuracy 0.96) and counterintuitive exercises designed to trigger heuristic reasoning (average accuracy 0.59). The authors document token bias causing 20%+ performance drops when canonical problem formulations are disguised, and up to 34% degradation when misleading suggestions are embedded in prompts. The findings argue that current LLMs are not genuine probabilistic reasoners despite their success on advanced math benchmarks.
AGC-Bench: A unified benchmark for measuring artificial general creativity in LLMs
Researchers introduce AGC-Bench, a comprehensive AI creativity benchmark built from a systematic review of 3,101 papers and 497 existing benchmarks, covering 78 datasets across brainstorming, STEM, narrative, figurative language, and humor. The work introduces Judge Response Theory to correct for LLM-as-judge bias and fine-tunes Qwen3-30B to produce AGC-Judge, an open-weight scoring model. Key findings include the recovery of a single creativity factor 'c' (analogous to the general intelligence 'g' factor) explaining 81.5% of variance across 83 LLMs, and evidence that top humans still outperform top LLMs on creativity tasks. The benchmark, leaderboard, and human data are released as open infrastructure.
Benchmark and study of LLM agents in deliberative multi-agent collaboration under partial observability
Researchers introduce a scalable benchmark for evaluating LLM agents on cooperative joint decision-making tasks where agents must exchange information under partial and asymmetric observations to reach a shared decision. A systematic evaluation of representative LLMs finds that state-of-the-art models still struggle with complex deliberative collaboration, failing in either information alignment or downstream reasoning even with external mathematical tools. Diagnostic analysis also reveals that deliberation can enable reflection and error correction, sometimes outperforming centralized baselines, offering a nuanced picture of multi-agent LLM capabilities.
SupraBench: First benchmark for evaluating LLMs on supramolecular chemistry reasoning
Researchers introduce SupraBench, the first benchmark designed to systematically evaluate LLMs on supramolecular chemistry tasks including binding affinity prediction, top-binder selection, solvent identification, and host-guest description. The work also releases SupraPMC, a 16M-token corpus of supramolecular chemistry articles from Europe PMC to support domain adaptation. Evaluation of broad open and proprietary LLMs reveals substantial headroom across all tasks, with domain pretraining improving in-distribution regression but creating format compliance tradeoffs. The benchmark targets a narrow but practically important scientific domain where LLM acceleration could reduce days-long dry-lab verification cycles.