Introduces nexbax, a diagnostic framework with three themes and 10 dimensions for evaluating AI economic viability, operational practicality, and societal integrity in next-billion-user contexts.
When AI Benchmarks Plateau: A Systematic Study of Benchmark Saturation
7 Pith papers cite this work. Polarity classification is still indexing.
7
Pith papers citing it
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. We find that nearly half of the our benchmarks exhibit saturation, with rates increasing with age. Further, we find that resilience to saturation is impacted by expert-curation, not by public test data. Our results suggest that design choices can extend benchmark longevity and inform more durable evaluation approaches.
citation-role summary
background 1
method 1
citation-polarity summary
years
2026 7representative citing papers
SEAL revives saturated benchmarks via adaptive LLM meta-judging in elimination matches, matching full pairwise accuracy with roughly half the calls across code, math, QA, and agent tasks.
The Generalized Turing Test defines relative intelligence as the inability of one agent to distinguish an imitator from the original through interaction.
EnactToM is an evolving benchmark of embodied multi-agent tasks that tests functional Theory of Mind by requiring agents to act optimally on implicit beliefs in partially observable 3D environments.
CivBench trains models on turn-level states in Civilization V to predict victory probabilities, providing a progress-based evaluation of LLM strategic capabilities across 307 games with 7 models.
A hybrid survey and conceptual framework introduces EvalSafetyGap to organize evaluation and alignment proxy failures in LLMs, supported by an audit of 10 models showing indeterminate capability-robustness links and governance-driven safety gaps.
Frontier models show positive capability coupling (r=0.72) across SWE-bench and GPQA, with lab-specific emphasis shifts measured by an h-field residual that distinguishes permanent pretraining changes from reversible post-training ones.
citing papers explorer
-
EnactToM: An Evolving Benchmark for Functional Theory of Mind in Embodied Agents
EnactToM is an evolving benchmark of embodied multi-agent tasks that tests functional Theory of Mind by requiring agents to act optimally on implicit beliefs in partially observable 3D environments.