Knowledge Index of Noah's Ark
2026-06-03 • Artificial Intelligence
Artificial Intelligence
AI summaryⓘ
The authors developed KINA, a new test with 899 questions covering 261 detailed subject areas to better measure knowledge in language models. They created a method to ensure the test fairly represents many fields and proved a new payment system encourages higher quality reviews. Testing 42 models showed significant differences in performance, with the best models scoring around 53% and many others scoring much lower, indicating room for improvement. They also studied how stable rankings are when budgets limit testing, helping to interpret model comparisons more carefully.
Knowledge benchmarksLarge language modelsDisciplinary representativenessGreedy approximationIncentive compatibilityBonus-on-bar tournamentRanking stabilityBootstrappingTool augmentation
Authors
Sheng Jin, Minghao Liu, Yunze Xiao, Zeqi Zhou, Heli Qi, Yifan Yao, Meishu Song, Kaijing Ma, Xuan Zhang, Sicong Jiang, Yizhe Li, Ningshan Ma, Jie Wei, Ziniu Li, Minglai Yang, Bangya Liu, Yiming Liang, Xiao Fang, Qingcheng Zeng, Jiarui Liu, Rui Yang, Shen Yan, Wenhao Huang, Jiaheng Liu, Zihan Wang, Weihao Xuan, Ge Zhang
Abstract
Knowledge benchmarks for LLMs face three issues: scaling-driven designs that do not operationalize disciplinary representativeness; flat-payment annotation that permits lazy consensus; and unaudited ranking instability under bounded test budgets. We introduce KINA, an 899-item benchmark across 261 fine-grained disciplines, with two formal results. First, we cast representativeness as a coverage-style objective over expert-elicited anchors and operationalize disciplinary representativeness through a proxy, yielding a (1-1/e) greedy approximation (Proposition 1); the guarantee applies to the proxy, not to population representativeness. Second, we prove a bonus-on-bar tournament weakly FOSD-dominates flat payment in released-review quality, with incentive-compatibility threshold B > Delta C / Delta p_min (Theorem 1). Evaluating 42 models from 13 labs, the top model, Gemini-3.1-Pro-Preview, reaches 53.17%, followed by Claude-Opus-4.6 at 49.92% and GPT-5.4 at 48.55%, leaving substantial headroom below saturation. The full leaderboard shows a tiered structure rather than a smooth total order: a small frontier tier lies above 48%, a dense strong-model tier spans roughly 38-45%, and low-performing models remain only modestly above the 10% chance baseline. Tool augmentation adds up to 5.17 points across the five tool-use evaluations, with gains varying substantially across models. We report bootstrap ranking-stability statistics to make bounded-budget variance explicit and to discourage over-interpretation of adjacent ranks.