Artificial Analysis puts model intelligence and cost on San Francisco billboards
ArtificialAnlys · x · 2026-07-24
Artificial Analysis says its San Francisco billboards are now showing an Intelligence Index vs. Cost per Task chart for leading models.
- It argues cost efficiency is now a primary model-evaluation dimension.
- In its chart, Fable 5 tops the Intelligence Index at 60 but costs $2.75 per task.
- Grok 4.5 (high) scores 54 at $0.31 per task, about 9× cheaper, and is said to sit on the Pareto frontier.
- DeepSeek v4 Flash scores 44 at $0.04 per task, roughly 69× cheaper than Fable.
- The company defines the Pareto frontier as models that are not beaten on both intelligence and cost by any other model.
Related event: Artificial Analysis Puts AI Cost-Performance on SF Billboards(2 posts)→
More from Infra
- DeepSpeed shows AutoEP/AutoTP/AutoSP parallelism gains, hosts office hours — PyTorch · 2026-10-27
- Cloudflare Durable Objects validated as top architecture for AI agent WebSocket servers — tristanbob · 2026-10-27
- Gary Marcus: With Q3 data added, Anthropic's compute-efficiency growth shows deceleration — GaryMarcus · 2026-10-27
- SpaceX locks in $40B GPU financing deal with Apollo, the largest ever committed — TechCrunch AI · 2026-10-27
- Inference is just Kubernetes with a multi-trillion-dollar market, and the communities overlap — matt_slotnick · 2026-10-27
- vLLM eyes Rust migration as inference engines race to rewrite the stack — AccBalanced · 2026-10-27