Frontier language models' no-chain-of-thought task-completion time horizon has grown steadily across model generations since 2019.
3 events · 1 assessment · 1 decision
Assessed
First pass. Left atomic: evidence is a single measurement programme (Think Fast, arXiv 2606.07157) plus Greenblatt's math no-CoT horizon; no contested sub-proposition warrants a node. Recorded two instances. Importance 0.35, contestation 0.25. Assessed supported, credence 0.85, confidence 0.75; caveats on 'steadily', recall, wide CI, single-group provenance.
Assessed Supported
verdict confidence 0.75 · credence 0.85
The main evidence is a June 2026 study by Ward, Gould, Woodruff and colleagues ("Think Fast", arXiv 2606.07157). It measured 14 models, from GPT-2 to GPT-5.5, on 43 benchmarks while preventing any visible reasoning. Each model's 50% time horizon is the length of task, measured by how long it takes a human, that the model completes about half the time. The study finds that this horizon for frontier models has doubled roughly every year since 2019. The reported doubling time is about 373 days, with a 95% interval of roughly 167 to 691 days, and GPT-5.5 reaches a horizon of a little over three minutes. An earlier and narrower measurement by Ryan Greenblatt of single-forward-pass math problems points the same way, with a doubling time of about nine months. The direction of the trend is well supported. The word "steadily" is weaker ground. The trend comes from a log-linear fit across only 14 models, and the interval on the doubling time is wide. Some of the measured horizon reflects recall of memorised knowledge rather than internal reasoning. Human time estimates for short tasks are also coarse. Few independent groups have so far replicated the measurement. Evidence that would weaken the claim includes a replication with a different task set that found a flat or irregular trend, or a showing that the horizon gain disappears once memorisation is controlled for.
Claim entered the graph