# GPT-5.4 Pro

> Source: Benchize (https://benchize.com) — https://benchize.com/models/gpt-5-4-pro. When citing or reusing this content, credit "Benchize" and link to https://benchize.com/models/gpt-5-4-pro.

OpenAI

Canonical URL: https://benchize.com/models/gpt-5-4-pro
Last updated: Wed, 21 Oct 2026 18:52:20 GMT

Reproduction and quotation must name Benchize, link to the canonical HTML URL, and retain individual source citations.

OpenAI

## Benchmarks

| Benchmark | Score | Rank |  |
| --- | --- | --- | --- |
| [SVGBench Arena](https://benchize.com/benchmarks/svgbench%3Aarena.md) | 2,058 | 1 / 191 |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 2058 \| rating \| reported \| Higher is better \| ### Configuration Reasoning effort unknown sourceModelId model_gpt54pro ### Reported statistics coverageCount 26 draws 39 judged 1073 losses 417 rank 1 ratingDeviation 28 wins 617 ### Source [Original source](https://svgbench.ai/api/leaderboard?shape=2) Source svgbench Original model label GPT-5.4 Pro Observed 2026-10-21T16:32:23.388Z Evidence SHA-256 `5c0a9c869593820d57d2c05f6d416e1b44a740b4835e66c66e9ad8b8edc59e2c` Source locator `/rows/0` |  |  |  |

---
Cite as: GPT-5.4 Pro — Benchize, https://benchize.com/models/gpt-5-4-pro (retrieved 2026-10-21)