GPT-5.5 Codex — benchmark results

Provider: OpenAI. Access: API.

Unified ELO 1932 ± 29, rank #17 of 1465 rated models, from 8 benchmark results.

Interactive version: aibenchmarks.dev/model?slug=gpt-5-5-codex · How the rankings work · Data refreshed daily, snapshot 2026-07-10.