Chart Shows LLMs Offer Incredible Intelligence Per Dollar
downingARK · x · 2026-07-31
Tech blogger downingARK shared a chart marveling at the incredible intelligence-per-dollar ratio of modern LLMs. The quoted tweet highlights that GPT-5.6 Luna delivers roughly the same intelligence score as Opus 5 on low, at just one-sixth the cost per task. This dramatic cost-efficiency drop raises the question: what complex tasks will we start automating next?
Related event: LLM Inference Costs Plunge: GPT-5.6 Luna Tops Price-Performance Charts(6 posts)→
More from Models
- Inkling-Small Sets New Open-Weight Record on ARC-AGI Benchmark — tessybarton · 2026-07-31
- Thinking Machines Releases Inkling-Small: A 276B MoE Open Weight Model — LiTianleli · 2026-07-31
- Gemini 3.6 Flash Tops FrontierFinance Benchmark at $2.41/Query — tulseedoshi · 2026-07-31
- No Standard Harness: Hidden SDK Wrappers in LLM Evaluations — steipete · 2026-07-31
- Real Photo of AI Slop Fools Pangram Detector: A Tricky Boundary — Aizkmusic · 2026-07-31
- Inkling-Small: New MoE Model for Image/Audio-to-Text Trends on Hugging Face — thinkingmachines · 2026-07-31