benchmarking/
No mentions found
This entity hasn't been tracked yet, or Iris is still building its knowledge base.
Related Articles from SNS
When AI Benchmarks Plateau: A Systematic Study of Benchmark Saturation
arXiv:2602.16763v2 Announce Type: replace Abstract: Artificial intelligence benchmarks are an important mechanism for measuring model progress and guiding deployment decisions. However, benchmarks quickly "saturate", making it difficult to differentiate models and diminishing their long-term value. In this study, we define benchmark saturation and analyze it across 60 language model benchmarks using 14 properties that relate to saturation.
Benchmarking Local LLMs for Natural-Language-to-SQL Querying in Biopharmaceutical Manufacturing: An Empirical Benchmark on Consumer-Grade Hardware
arXiv:2606.01338v1 Announce Type: new Abstract: Biopharmaceutical manufacturing organizations operate under regulatory frameworks such as FDA guidance, EU Good Manufacturing Practice (GMP), and the EU AI Act, which can restrict the use of cloud-based artificial intelligence systems. Locally deployed large language models (LLMs) offer a privacy-preserving alternative, but their suitability for pharmaceutical manufacturing tasks remains underexplored. This study evaluates four open-source LLMs...
Uncovering Competency Gaps in Large Language Models and Their Benchmarks
arXiv:2512.20638v2 Announce Type: replace Abstract: The evaluation of large language models relies heavily on standardized benchmarks. These benchmarks provide useful aggregated metrics, but can obscure (i) particular sub-areas where the models are weak ("model gaps") and (ii) imbalanced coverage in the benchmarks themselves ("benchmark gaps"). To automatically uncover both types of gaps, we propose a simple new method using concept activations from sparse autoencoders, to identify...
Rethinking RL Evaluation: Can Benchmarks Truly Reveal Failures of RL Methods?
arXiv:2510.10541v2 Announce Type: replace Abstract: Current benchmarks are inadequate for evaluating progress in reinforcement learning (RL) for large language models (LLMs).Despite recent benchmark gains reported for RL, we find that training on these benchmarks' training sets achieves nearly the same performance as training directly on the test sets, suggesting that the benchmarks cannot reliably separate further progress. To study this phenomenon, we introduce a diagnostic suite and the...
RealClawBench: Live OpenClaw Benchmarks from Real Developer-Agent Sessions
arXiv:2606.03889v1 Announce Type: new Abstract: Agent benchmarks should reflect what users actually ask deployed agents to do, yet existing benchmarks often miss key realism properties of real developer-agent sessions. We introduce RealClawBench, a live benchmark framework built from real OpenClaw sessions to capture the distribution, diversity, and real-world difficulty of deployed agent use. Real user requests are challenging to benchmark because they often depend on local execution...
Efficient Benchmarking Is Just Feature Selection and Multiple Regression
Announce Type: replace-cross Abstract: Efficient benchmarking techniques aim to lower the computational cost of evaluating LLMs by predicting full benchmark scores using only a subset of a benchmark's questions. By reframing this problem as an instance of multiple regression with feature selection, we find that existing efficient benchmarking methods can be greatly improved by simply using kernel ridge regression at the prediction stage. Additionally, using an information-theoretic...
RealClawBench: Live OpenClaw Benchmarks from Real Developer-Agent Sessions
Announce Type: replace Abstract: Agent benchmarks should reflect what users actually ask deployed agents to do, yet existing benchmarks often miss key realism properties of real developer-agent sessions. We introduce RealClawBench, a live benchmark framework built from real OpenClaw sessions to capture the distribution, diversity, and real-world difficulty of deployed agent use. Real user requests are challenging to benchmark because they often depend on local execution environments, involve...
Welfare, Improvability, and Variance: A Principal-Agent Approach to Optimal Benchmark Item Aggregation
arXiv:2605.30916v1 Announce Type: new Abstract: AI benchmarks have well-documented limitations, with prior work examining contamination, saturation, and construct underspecification. Aggregation has received far less attention: benchmarks are typically summarized by uniformly averaging item-level scores, implicitly treating every test item as equally valuable. We model benchmarking as a multitask principal-agent game and show that the welfare loss from a benchmark is determined jointly by...
Benchmarking at the Edge of Comprehension
arXiv:2602.14307v4 Announce Type: replace Abstract: As frontier Large Language Models (LLMs) increasingly saturate new benchmarks shortly after they are published, benchmarking itself is at a juncture: if frontier models keep improving, it will become increasingly hard for humans to generate discriminative tasks, provide accurate ground-truth answers, or evaluate complex solutions. If benchmarking becomes infeasible, our ability to measure any progress in AI is at stake. We refer to this...
Auditing LLM Benchmarks with Item Response Theory
Announce Type: new Abstract: LLM benchmark labels are frozen at release and silently propagated into downstream benchmarks, errors and all. We introduce an Item Response Theory-based indicator that surfaces likely mislabels at 95% precision in the top 200 examples across seven preference and multiple-choice benchmarks using responses from 114 models, outperforming a supervised classifier. We trace these errors to mechanical labeling heuristics, upstream annotation mistakes inherited...