Observed arrival · 2026-10-11

Nerdict puts AI model tests on the record

thenerdict.com Visit website

Editorial interest 78/100 Selection signal · not a rating of the site

Nerdict compares AI models on the same one-shot tasks, showing automated checks, individual runs, failures, speed, and estimated costs.

Landing page captured for the 2026-10-11 issue.

For: People comparing AI models on practical tasks
Worth noticing: The page lists 12 setups each for Galton board, Browser OS, astronomical clock, aquarium, and motion intro.

Field notes

The listed test set spans Galton board, Browser OS, an astronomical clock, an aquarium, and a motion intro, with 12 setups for each. The page names Claude Code 2.1.296 and Codex CLI 0.162.0 as the environments used for Anthropic and OpenAI models, respectively, and says no in-house harness is in place yet.

Observed signals

Read the marks

Editorial observations of this landing page, not a rating.

○OpenPublic substance visible

✦PrettyNotable craft visible

●ProPolished or operationally mature

◎NicheUnusually specific use

One card from the complete issue

Cloudless Mushrooms

372,187 arrived 1,000 judged 980 catalogued Enter the complete issue