Frontier Model Capability Premium Hits 100x Cost

ArtificialAnlys · x · 2026-07-07

Artificial Analysis released a capability index cost comparison: DeepSeek V4 Flash (max) completes tasks across six indices for under $0.04 each, yielding mid-tier scores, while GLM-5.2 (max) leads open-weight models at $0.26–$0.58 per task. On the "Strategy and Operations Index," Claude Fable 5 (falling back to Opus 4.8) outscored DeepSeek V4 Pro (max) by 12 points, but costs $3.48 per task compared to $0.03—a premium of over 100x, illustrating the massive cost premium of frontier capabilities.

Related event: Artificial Analysis Releases Six Industry Capability Indices(3 posts)→

Original post →

More from Models

Models channel →