v1.0
Measuring frontier model capabilities across the most valuable domains
- 11
- domains
- 14
- partners
- 206
- tasks
A collaboration with
14 specialized
data partners
14 specialized
data partners
ArithmeticCybersecurity
ArcverexChip DesignDatacurveSoftware Engineering
EmulatedMaterials ScienceChakraLegal
Living ContextFinanceFleetAlignment
ExtrapolateRecursive Self-Improvement
Beautiful MachinesHardware Design
AriaChip DesignLatchBioBiology
ErgodexChip Design
ValenceForgeMaterials Science
Third MomentQuant Trading
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