OpenAI·GPT

GPT-5.2 Codex

5.2 Codex

Aliases: gpt-5.2-codex, gpt-5-2-codex

Canonical ID

openai-gpt-5.2-codex

Independent sources

Composite eligibility

Eligible

Public benchmark scores

Source ranks stay intact; incompatible raw scores are not added.

FreshHigh confidence

SWE-benchSWE-bench bash-only · result 2026-02-19Updated: 8/10/2026

72.8% resolved

#7 · 87th percentile

FreshHigh confidence

LiveBenchLiveBench 2026-06-25 · ReasoningUpdated: 6/25/2026

77.7 / 100

#35 · 19th percentile

This model has scores from 2 independent sources and is eligible for the ToolCenter composite reference.

Historical snapshots are available on the source score cards.