GDPx: The General Agentic Benchmark

A benchmark called GDPx v1.0 was published to measure frontier model capabilities across 11 domains, built with 14 partners and 206 tasks. The GDPx results are presented on a cost-versus-performance Pareto frontier plotting GDPx score against average cost per task on a log scale, with Muse Wonder Full excluded because it has no public price. The benchmark also lets users compare models by domain.

v1.0 Measuring frontier model capabilities across the most valuable domains - 11 - domains - 14 - partners - 206 - tasks Cost vs. Performance Pareto Frontier ↑ GDPx scoreAvg cost per task log → Not shown: Muse Wonder Full, with no public price. by Compare models by domain ModelGDPx by Thanks to