# GENIUS: Generative Fluid Intelligence Evaluation Suite Source: [GENIUS: Generative Fluid Intelligence Evaluation Suite]() Collection index: [llms.txt]() Data updated: 2026-02-15T06:00:01.820Z Authors: Ruichuan An, Sihan Yang, Ziyu Guo, Wei Dai, Zijun Shen, Haodong Li, Renrui Zhang, Xinyu Wei, Guopeng Li, Wenshan Wu, Wentao Zhang Published: 2026-02-11T18:55:54.000Z ## Abstract Unified Multimodal Models (UMMs) have shown remarkable progress in visual generation. Yet, existing benchmarks predominantly assess $\\textit{Crystallized Intelligence}$, which relies on recalling accumulated knowledge and learned schemas. This focus overlooks $\\textit{Generative Fluid Intelligence (GFI)}$: the capacity to induce patterns, reason through constraints, and adapt to novel scenarios on the fly. To rigorously assess this capability, we introduce $\\textbf{GENIUS}$ ($\\textbf{GEN}$ Fluid $\\textbf{I}$ntelligence Eval$\\textbf{U}$ation $\\textbf{S}$uite). We formalize $\\textit{GFI}$ as a synthesis of three primitives. These include $\\textit{Inducing Implicit Patterns}$ (e.g., inferring personalized visual preferences), $\\textit{Executing Ad-hoc Constraints}$ (e.g., visualizing abstract metaphors), and $\\textit{Adapting to Contextual Knowledge}$ (e.g., simulating counter-intuitive physics). Collectively, these primitives challenge models to solve problems grounded entirely in the immediate context. Our systematic evaluation of 12 representative models reveals significant performance deficits in these tasks. Crucially, our diagnostic analysis disentangles these failure modes. It demonstrates that deficits stem from limited context comprehension rather than insufficient intrinsic generative capability. To bridge this gap, we propose a training-free attention intervention strategy. Ultimately, $\\textbf{GENIUS}$ establishes a rigorous standard for $\\textit{GFI}$, guiding the field beyond knowledge utilization toward dynamic, general-purpose reasoning. Our dataset and code will be released at: $\\href{https://github.com/arctanxarc/GENIUS}{https://github.com/arctanxarc/GENIUS}$. ## Recorded benchmark results A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage. - [Contextual Knowledge Adaptation (Multi-Semantic) on GENIUS](): Contextual Knowledge Adaptation (Multi-Semantic); Genius; RC: 34.22. - [Ad-hoc Constraint Execution (Symbolic Constraint) on GENIUS](): Ad-hoc Constraint Execution (Symbolic Constraint); Genius; RC: 36.54. - [Implicit Pattern Induction on GENIUS 1.0 (test)](): Implicit Pattern Induction; GENIUS 1.0 (test); RC: 39.54. - [Ad-hoc Constraint Execution (Visual Constraint) on GENIUS](): Ad-hoc Constraint Execution (Visual Constraint); Genius; RC Score: 30.45. - [Generative Fluid Intelligence (Overall) on GENIUS 1.0 (test)](): Generative Fluid Intelligence (Overall); GENIUS 1.0 (test); Overall Score: 32.92. - [Generative Fluid Intelligence on GENIUS](): Generative Fluid Intelligence; Genius; Overall Score: 23.91. - [Contextual Knowledge Adaptation (Prior-Conflicting) on GENIUS](): Contextual Knowledge Adaptation (Prior-Conflicting); Genius; RC Score: 23.67. ## Original sources and implementation [Original paper]() [PDF]()