Agent evaluations increasingly benchmark LLMs, but rankings can be swayed by evaluation conditions such as scaffolds or tasks, making reliability claim‑dependent. A Bayesian variance‑decomposition framework applied to 22 benchmarks shows that reliability varies with the measurement goal: fixed model‑scaffold systems rank reliably, while underlying‑model rankings are less stable. Scaffold choice can alter conclusions, and adding more tasks only modestly improves reliability when scaffold coverage is limited; however, pooling diverse benchmarks can substantially raise cross‑task ranking reliability and reduce cost.
arXiv:2608. 11323v1 Announce Type: new Abstract: Enterprise practitioners read agent leaderboards as if they ranked agent capability.
Enterprise practitioners read agent leaderboards as if they ranked agent capability. We show, across three open agent-trace benchmarks (TheAgentCompany, $τ^2$-bench, and AppWorld), that the agent main effect accounts for less than 3% of total variance in every dataset and check type, while the agent-by-task interaction accounts for 7-23%.
arXiv:2609.07785v1 Announce Type: new Abstract: An LLM-agent leaderboard invites a familiar inference: an agent ranked above another is the better agent. Public evaluation logs may not support that c...
arXiv:2608.21601v1 Announce Type: new Abstract: Benchmarks for scientific artificial intelligence are mostly written to be scored: multiple-choice questions, curated agent tasks with reference soluti...
arXiv:2606. 19704v1 Announce Type: new Abstract: Agent benchmarks are growing fast, but no single benchmark touches more than four or five of the dimensions that deployment exposes.
The paper introduces a low‑rank framework for ranking large language models (LLMs) on task‑specific benchmarks using sparse pairwise comparisons. By modeling the task‑by‑model ability matrix as low rank, the method shares information across related tasks while preserving task‑specific differences, and it provides uncertainty‑aware ranking through debiased estimators and simultaneous confidence sets. Experiments on synthetic data and the Chatbot Arena benchmark demonstrate improved sample efficiency and tighter, better‑calibrated ranking certificates, especially in the sparse comparison regime typical of real LLM evaluations.
arXiv:2607. 24063v1 Announce Type: new Abstract: On standard factuality tasks, frontier models now cluster near the top of the scale.
The paper introduces Balance of Benchmarks (BoB), a framework that improves task-conditioned model comparison by weighting benchmark evidence based on semantic density, equating scores across varying difficulty levels, and pooling task-relevant residuals. BoB retains all eligible benchmark data while adjusting its influence, outperforming uniform averaging on the WildScores dataset with higher Spearman correlation, lower MAE, and better shortlist hit rates. The method also reduces ranking instability when benchmarks are repeated or paraphrased, and lowers retrospective regret in model selection.
arXiv:2607. 22585v1 Announce Type: new Abstract: Public leaderboards for coding agents typically rank systems by model name and pass rate, while the surrounding harness (the scaffold that issues tools, manages context, and decides when to stop) is often under-specified.
arXiv:2606. 03650v1 Announce Type: cross Abstract: Choosing or ranking language models for a specific application is hardest when no task-specific labeled data exists, and standard public benchmarks cannot be trusted, their items having likely leaked into pretraining, so scores reflect memorization rather than fitness.
GAUGE is a new offline protocol that evaluates whether the common practice of using an LLM-as-a-judge to rank task‑oriented agents actually aligns with a verifiable reward. Across 25 agents from six providers on two benchmarks, GAUGE finds that user satisfaction scores are largely uncorrelated with task success, and that the judge’s ranking loses precision when agents are closely matched in performance. The study highlights a gap between ranking validity and construct validity in current evaluation practices.
arXiv:2607. 17044v1 Announce Type: cross Abstract: Multi-step enterprise agent tasks fail in a characteristic way: single-pass inference has no checkpoint between deciding an answer and committing to it.