BRIDGE: Predicting Human Task Completion Time From Model Performance
This addresses the costly and noisy scaling of human annotations for evaluating AI systems, though it is incremental as it builds on existing psychometric methods.
The paper tackles the problem of grounding AI benchmark performance in human-interpretable measures by proposing BRIDGE, a framework that predicts human task completion time from model performance, achieving a result where the 50% solvable task horizon doubles approximately every 6 months.
Evaluating the real-world capabilities of AI systems requires grounding benchmark performance in human-interpretable measures of task difficulty. Existing approaches that rely on direct human task completion time annotations are costly, noisy, and difficult to scale across benchmarks. In this work, we propose BRIDGE, a unified psychometric framework that learns the latent difficulty scale from model responses and anchors it to human task completion time. Using a two-parameter logistic Item Response Theory model, we jointly estimate latent task difficulty and model capability from model performance data across multiple benchmarks. We demonstrate that latent task difficulty varies linearly with the logarithm of human completion time, allowing human task completion time to be inferred for new benchmarks from model performance alone. Leveraging this alignment, we forecast frontier model capabilities in terms of human task length and independently reproduce METR's exponential scaling results, with the 50% solvable task horizon doubling approximately every 6 months.