Updated daily at 05:00 UTC
- Released
- 13 Nov 2025
- Status
- Retired
- Retired
- 23 Jul 2026
- Context
- 400K
- Max output
- 128K
- Input per 1M tokens
- $0.25
- Output per 1M tokens
- $2.00
- Open weights
- No
- License
- proprietary
- Parameters
- —
- Knowledge cutoff
- 30 Sep 2024
- Reasoning
- Yes
- Modalities
- text, image → text
Category scores
Out of 100, from independent and third-party results only, by method category-2026-09-29.1.
| Category | Score | Rank | Coverage |
|---|---|---|---|
| Human preference | 28.9 | Not ranked | 1 of 5 |
Benchmark results
Every result we hold for this model, with who ran it and where it was published.
Coding & software engineering
| Benchmark | Metric | Value | Provenance | Setting | Evaluated | Source |
|---|---|---|---|---|---|---|
| Terminal-Bench 2.0 | Accuracy (mean over trials) | 61.6% | Third party | — | — | https://www.tbench.ai/leaderboard/terminal-bench/2.0 via Epoch AI |
| Terminal-Bench 2.0 | Accuracy (mean over trials) | 43.1% | Third party | — | — | https://www.tbench.ai/leaderboard/terminal-bench/2.0 via Epoch AI |
| Terminal-Bench 2.0 | Accuracy (mean over trials) | 43.1% | Third party | — | — | Terminal-Bench v2 Leaderboard via Epoch AI |
Human preference
| Benchmark | Metric | Value | Provenance | Setting | Evaluated | Source |
|---|---|---|---|---|---|---|
| Code Arena: WebDev (arena.ai) | Arena score (Elo scale) | 1244 | Independent | — | 25 Sep 2026 | Arena |
| Code Arena: WebDev (arena.ai) | Votes | 1155 | Independent | — | 25 Sep 2026 | Arena |
Other Codex versions
- GPT-5.3-Codex-Spark12 Feb 2026
- GPT-5.3-Codex5 Feb 2026
- GPT-5.2-Codex14 Jan 2026
- GPT-5.1-Codex-Max19 Nov 2025
- GPT-5.1-Codex13 Nov 2025
- GPT-5-Codex15 Sep 2025
- codex-mini15 May 2025
- Codex (code-davinci-002)15 Mar 2022
- Codex (code-cushman-001)Aug 2021
- Codex (code-davinci-001)Aug 2021