AI intelligence-cost Pareto frontier shifted fast: GPT-5 mini at 17 ($0.05) to Claude Opus 5.5 at 58 ($5.98)
ArtificialAnlys · x · 2026-09-30
Artificial Analysis compared its Intelligence Index vs. Cost per Task Pareto frontier across 18 months:
- A year ago, the highest-scoring model was GPT-5 mini (high) at 17 on v4.3 of the Intelligence Index, costing $0.05 per task.
- Last week, Claude Opus 5.5 set the highest score to date of 58 at $5.98 per task.
- Top-tier intelligence scores roughly 2.4x'd in about a year, while cost per task rose 120x — a dramatic reshaping of the intelligence-vs-cost frontier.
Index v4.3 also replaced 𝜏³-Banking with AutomationBench-AA and upgraded Terminal-Bench to 4.0.
More from Infra
- Heavy user proposes pairing OAI Pro with a 512GB Mac Studio running GLM-5.3 locally — paperchow · 2026-09-30
- Raja Koduri: Western AI compute costs $50-60B per gigawatt, China targets under $10B — RajaXg · 2026-09-30
- DeepSeek open-sources DeepGEMM Ascend port, hitting 99.8% of hardware limit on GEMM — zheanxu · 2026-09-30
- Google's Project Suncatcher to fly TPUs in space for the first time on Oct 1 — allisondman · 2026-09-30
- Photon 2.6 ships FP8 + speculative decoding, runs Qwen3.5 27B at 400+ tok/s on B200 — Bedrovelsen · 2026-09-30
- SGLang turns Qwen3.8-27B into a decision model that beats Pokémon FireRed at sub-100ms — zhaoran_wang · 2026-09-30