# GPT-5.4 Nano

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

OpenAI

Canonical URL: https://benchize.com/models/gpt-5-4-nano
Last updated: Thu, 22 Oct 2026 06:30:09 GMT

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

OpenAI

## Benchmarks

| Benchmark | Score | ± | Rank | Source |  |
| --- | --- | --- | --- | --- | --- |
| [NC Bench](https://benchize.com/benchmarks/nc-bench%3Aoverall.md) | 72.16% | — | 139 / 144 | [nc bench](https://www.nc-bench.com/models) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `score` \| 72.16 \| percent \| reported \| Higher is better \| \| `tooling` \| 91.85 \| percent \| category \| Higher is better \| \| `creative_writing` \| 80.5 \| percent \| category \| Higher is better \| \| `language` \| 80.82 \| percent \| category \| Higher is better \| \| `utility` \| 78.57 \| percent \| category \| Higher is better \| \| `reasoning` \| 58.53 \| percent \| category \| Higher is better \| \| `text_editing` \| 79.22 \| percent \| category \| Higher is better \| \| `rule_following` \| 20.94 \| percent \| category \| Higher is better \| \| `hallucination` \| 86.86 \| percent \| category \| Higher is better \| ### Configuration Reasoning effort unknown Model configuration GPT-5.4 Nano thinkingEnabled Not reported ### Source [Original source](https://www.nc-bench.com/models) Source nc bench Original model label GPT-5.4 Nano Observed 2026-10-22T06:10:03.426Z Evidence SHA-256 `ec261022458543624b08a136d01f5a2f0666cd52ffb49c64d6ca983e8543d1b5` Source locator `/rows/189` |  |  |  |  |  |
| [SVGBench Arena](https://benchize.com/benchmarks/svgbench%3Aarena.md) | 1,596 | — | 31 / 191 | [svgbench](https://svgbench.ai/api/leaderboard?shape=2) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1596 \| rating \| reported \| Higher is better \| ### Configuration Reasoning effort unknown sourceModelId model_openai_gpt_5_4_nano ### Reported statistics coverageCount 27 draws 4 judged 81 losses 33 rank 39 ratingDeviation 28 wins 44 ### Source [Original source](https://svgbench.ai/api/leaderboard?shape=2) Source svgbench Original model label GPT-5.4 Nano Observed 2026-10-22T04:30:04.538Z Evidence SHA-256 `5c0a9c869593820d57d2c05f6d416e1b44a740b4835e66c66e9ad8b8edc59e2c` Source locator `/rows/37` |  |  |  |  |  |
| [Longform Creative Writing](https://benchize.com/benchmarks/eq-bench%3Alongform-writing.md) | 57.8% | — | 59 / 93 | [eq bench · longform-writing](https://eqbench.com/creative_writing_longform.js) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `overall_score_100` \| 57.8 \| percent \| overall \| Higher is better \| \| `chapter1_avg` \| 14.15 \| rubric_score \| overall \| Higher is better \| \| `chapter2_avg` \| 13.10 \| rubric_score \| overall \| Higher is better \| \| `chapter3_avg` \| 13.01 \| rubric_score \| overall \| Higher is better \| \| `chapter4_avg` \| 12.72 \| rubric_score \| overall \| Higher is better \| \| `chapter5_avg` \| 12.92 \| rubric_score \| overall \| Higher is better \| \| `chapter6_avg` \| 12.70 \| rubric_score \| overall \| Higher is better \| \| `chapter7_avg` \| 12.24 \| rubric_score \| overall \| Higher is better \| \| `chapter8_avg` \| 11.99 \| rubric_score \| overall \| Higher is better \| \| `final_judgement_avg` \| 10.45 \| rubric_score \| overall \| Higher is better \| ### Configuration interactiveAdjustments none protocol longform-writing sourceModelVersion gpt-5.4-nano ### Source [Original source](https://eqbench.com/creative_writing_longform.js) Source eq bench Original model label gpt-5.4-nano Source version longform-writing Observed 2026-10-22T05:10:05.903Z Evidence SHA-256 `3ba283ce357ac7620e16db640a961879c30fe3ddc50a27de9a8ed4290784825c` Source locator `/leaderboardDataLongformV3/101` |  |  |  |  |  |
| [Judgemark v4](https://benchize.com/benchmarks/eq-bench%3Ajudgemark-v4.md) | 27.54% | CI 24.75–36.33% | 36 / 38 | [eq bench · judgemark-v4](https://eqbench.com/judgemark-v4.js) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `score` \| 0.275388 \| score_fraction \| overall \| Higher is better \| ### Configuration interactiveAdjustments none protocol judgemark-v4 sourceModelVersion gpt-5.4-nano ### Reported statistics Uncertainty Confidence interval: 24.75–36.33% confidenceIntervalHigh 0.363286 confidenceIntervalLow 0.247464 ### Source [Original source](https://eqbench.com/judgemark-v4.js) Source eq bench Original model label gpt-5.4-nano Source version judgemark-v4 Observed 2026-10-22T05:10:06.884Z Evidence SHA-256 `2b0d42aef4f614dd199dc38399be7b88075a919db52020c3759f190defc92a4d` Source locator `/leaderboardDataJudgemarkV4/38` |  |  |  |  |  |
| [Judgemark v2.1](https://benchize.com/benchmarks/eq-bench%3Ajudgemark-v2.md) | 64.47% | — | 25 / 39 | [eq bench · judgemark-v2](https://eqbench.com/judgemark-v2.js) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `judgemark_score` \| 64.47 \| percent \| overall \| Higher is better \| \| `stability` \| 0.468 \| score_fraction \| overall \| Higher is better \| \| `separability` \| 0.692 \| score_fraction \| overall \| Higher is better \| \| `human_corr` \| 0.633 \| correlation \| overall \| Higher is better \| ### Configuration interactiveAdjustments none protocol judgemark-v2 sourceModelVersion gpt-5.4-nano ### Source [Original source](https://eqbench.com/judgemark-v2.js) Source eq bench Original model label gpt-5.4-nano Source version judgemark-v2 Observed 2026-10-22T05:10:06.632Z Evidence SHA-256 `070cc3fbd6f0333dde2b52bec4329ea3fba7eccbf016bbbbef95e0f8b2197781` Source locator `/leaderboardDataV2/45` |  |  |  |  |  |

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