Model Releases
AI reviewers then ranked the submissions, and gave the same ordering every time, regardless of model doing the ranking: Codex GPT-5.4 > GPT-…
AI reviewers then ranked the submissions, and gave the same ordering every time, regardless of model doing the ranking: Codex GPT-5.4 > GPT-5.3-Codex > Opus 4.6 > humans. Paper: http://claude-code-eco
AI reviewers then ranked the submissions, and gave the same ordering every time, regardless of model doing the ranking: Codex GPT-5.4 > GPT-5.3-Codex > Opus 4.6 > humans. Paper: http://claude-code-economist.com/data/paper.pdf
Source: Ethan Mollick (X) | 2026-04-20