GPT-5.3-Codex: corrected Terminal-Bench 2.0 from 78.4% to OpenAI’s published 77.3%
Tracker updates GPT-5.3-Codex’s Terminal-Bench 2.0 score
Corrected Terminal-Bench 2.0 from 78.4% to OpenAI’s published 77.3% — verified by the OnAirToday AI Progress Tracker against OpenAI's published documentation.
OnAirToday
Newsroom
The OnAirToday AI Progress Tracker recorded a verified change to OpenAI's GPT-5.3-Codex (version gpt-5.3-codex): Corrected Terminal-Bench 2.0 from 78.4% to OpenAI’s published 77.3%.
GPT-5.3-Codex is OpenAI’s coding-focused agent model, combining software-engineering capabilities with broader reasoning and professional knowledge. It supports extended, tool-driven workflows and interactive steering, but generated code and consequential actions still require testing, review and appropriate permissions.
What changed in this review:
- SWE-bench Verified: Not yet confirmed by public reporting.
Teams building on GPT-5.3-Codex should confirm limits, pricing and benchmark coverage against the vendor's own documentation before relying on these figures.
The full profile — capabilities, benchmark citations, known flaws and risk guidance — is on the tracker at /ai-models/gpt-5-3-codex.
References:
- https://openai.com/index/introducing-gpt-5-3-codex/
- https://platform.openai.com/docs/models/gpt-5.3-codex
Generated insight by OnAirToday AI
A correction matters because benchmark figures can shape comparisons between AI models. The update aligns the tracker’s Terminal-Bench 2.0 result with OpenAI’s published documentation.
Comments
Keep comments relevant and respectful. No links, advertising, self-promotion, or spam.