GPT-5-Codex
Coding-optimized GPT model for repository edits, reviews, and agentic software work
- Strongest at
- Science Better than 20% of the past year's models · one benchmark so far
- Context window
- 400K tokens in · 128K out
Capability profile
Where it lands among 91 models released in the past year. 50 is the average model.
Where these scores come from
Each capability combines the published benchmarks listed here, rescaled so 50 is the reference average and 15 points is one standard deviation. A hollow marker rests on a single benchmark.
- Science WeirdML v2
The GPT-5.3 Codex line
4 releases in the GPT-5.3 Codex line.
A newer release is out: GPT-5.3 Codex.
Epoch benchmark boards
Best result on each board it has run. The tick marks the leader.
OpenAI's past year
24 release days in the past year, about one every 15 days. The next is expected around Nov 8, 2026. Forecasts ↗
Specifications
Specifications and prices from Models.dev; availability and limits may differ by provider. Benchmarks from Epoch AI (CC BY 4.0), LiveBench and the other sources named above.