# GPT-5.4Thinking

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

OpenAI

Canonical URL: https://benchize.com/models/gpt-5-4-thinking
Last updated: Thu, 22 Oct 2026 06:20:09 GMT

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

OpenAI

## Benchmarks

| Benchmark | Score | Rank |  |
| --- | --- | --- | --- |
| [NC Bench](https://benchize.com/benchmarks/nc-bench%3Aoverall.md) | 93.85% | 18 / 144 |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `score` \| 93.85 \| percent \| reported \| Higher is better \| \| `tooling` \| 100 \| percent \| category \| Higher is better \| \| `creative_writing` \| 91.17 \| percent \| category \| Higher is better \| \| `language` \| 94.9 \| percent \| category \| Higher is better \| \| `utility` \| 96.89 \| percent \| category \| Higher is better \| \| `reasoning` \| 94.89 \| percent \| category \| Higher is better \| \| `text_editing` \| 98.42 \| percent \| category \| Higher is better \| \| `rule_following` \| 79.29 \| percent \| category \| Higher is better \| \| `hallucination` \| 95.22 \| percent \| category \| Higher is better \| ### Configuration Reasoning effort unknown Model configuration GPT-5.4 (Reasoning) thinkingEnabled true ### Source [Original source](https://www.nc-bench.com/models) Source nc bench Original model label GPT-5.4 (Reasoning) Observed 2026-10-22T06:10:03.426Z Evidence SHA-256 `ec261022458543624b08a136d01f5a2f0666cd52ffb49c64d6ca983e8543d1b5` Source locator `/rows/22` |  |  |  |

---
Cite as: GPT-5.4Thinking — Benchize, https://benchize.com/models/gpt-5-4-thinking (retrieved 2026-10-22)