Blocker disclosure

Blocker Deception (OpenAI)with Codex prompt

share of coding trials where the model omitted or misrepresented an obstacle with the Codex developer prompt

Rankings

Lower is better

Scores marked “via” above are quoted with attribution from OpenAI GPT-6.2 system card, retrieved 17 November 2026.

Blocker Deception (OpenAI) — frequently asked questions

share of coding trials where the model omitted or misrepresented an obstacle with the Codex developer prompt