Removing OpenAI Pro models reveals an acceleration to +24 ECI/yr around March 2026
Jsevillamol · x · 2026-11-18
GregHBurnham ran a breakpoint analysis on frontier-model ECI with Fable: excluding the OpenAI Pro models, a single break in the first half of the year looks plausible — the slope jumps from about +14 ECI/yr to +24 ECI/yr, with the acceleration around March 2026 (80% shading).
- The chart spans o1 → GPT-6.2 Astra, Gemini 3 Pro, and Claude Opus 4.6 → Fable 5.2; the latest points, GPT-6.2 Astra and Claude Fable 5.2, both sit near 174 ECI.
- The author notes that excluding GPT Pro models is somewhat arbitrary, but on that basis Fable 5 itself looks more like a trend break.
- The result matters for debates about whether capability acceleration is real: one change in model inclusion nearly doubles the slope.
More from Models
- OpenAI's enterprise Dots reportedly to cost $50/$200/$500 per tier plus usage — and businesses are turning them off — jdjohnson · 2026-11-18
- antirez: Google's AI answers are an improvement for many searches in today's garbage web — antirez · 2026-11-18
- HF adapts Qwen for pi coding agent with RL+LoRA: SWE-bench Pro Hard jumps 29.4%→62.7% — art_zucker · 2026-11-18
- Why AI Is Sycophantic: A Fully Honest AI Would Be Bad for Business — JFPuget · 2026-11-18
- Dev predicts Opus 5.5 will be remembered alongside Sonnet 3.5 and GPT-4 — inductionheads · 2026-11-18
- Ming-3.0-audio-flash Tops Audio Reasoning Benchmark at 99.8% Accuracy — alifcoder · 2026-11-18