# GPT-5.4 MiniLow

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

OpenAI

Canonical URL: https://benchize.com/models/gpt-5-4-mini-low
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 | Cost | Source |  |
| --- | --- | --- | --- | --- | --- |
| [NC Bench](https://benchize.com/benchmarks/nc-bench%3Aoverall.md) | 83.57% | 112 / 144 | — | [nc bench](https://www.nc-bench.com/models) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `score` \| 83.57 \| percent \| reported \| Higher is better \| \| `tooling` \| 100 \| percent \| category \| Higher is better \| \| `creative_writing` \| 87.72 \| percent \| category \| Higher is better \| \| `language` \| 92.45 \| percent \| category \| Higher is better \| \| `utility` \| 88.49 \| percent \| category \| Higher is better \| \| `reasoning` \| 74.5 \| percent \| category \| Higher is better \| \| `text_editing` \| 92.63 \| percent \| category \| Higher is better \| \| `rule_following` \| 33.99 \| percent \| category \| Higher is better \| \| `hallucination` \| 98.78 \| percent \| category \| Higher is better \| ### Configuration Reasoning effort low Model configuration GPT-5.4 Mini (Reasoning, Low) thinkingEnabled true ### Source [Original source](https://www.nc-bench.com/models) Source nc bench Original model label GPT-5.4 Mini (Reasoning, Low) Observed 2026-10-22T06:10:03.426Z Evidence SHA-256 `ec261022458543624b08a136d01f5a2f0666cd52ffb49c64d6ca983e8543d1b5` Source locator `/rows/145` |  |  |  |  |  |
| [FrontierCode 1.1 extended](https://benchize.com/benchmarks/frontiercode%3Av1_1%3Aextended.md) | 20.58% | 125 / 125 | $0.33 | [frontiercode](https://cognition.com/data/frontiercode-leaderboard/data.json) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `score` \| 0.2058 \| score_fraction \| blocking_criteria_adjusted \| Higher is better \| \| `correct` \| 0.2302 \| score_fraction \| raw_rubric \| Higher is better \| \| `cost` \| 0.3288 \| USD \| per_rollout \| Lower is better \| ### Configuration harness codex Reasoning effort low sourceVersion v1_1 subset extended ### Reported statistics flaggedRate 0 sampleSize 150 ### Source [Original source](https://cognition.com/data/frontiercode-leaderboard/data.json) Source frontiercode Original model label GPT-5.4-mini Observed 2026-10-22T05:40:03.220Z Evidence SHA-256 `ff0040778b7bdf69c705ad7474f771fb5e53cfaf5cf8573b3a4614153543d75f` Source locator `/v1_1/data/GPT-5.4-mini/low/extended` |  |  |  |  |  |
| [FrontierCode 1.1 main](https://benchize.com/benchmarks/frontiercode%3Av1_1%3Amain.md) | 9.25% | 125 / 125 | $0.36 | [frontiercode](https://cognition.com/data/frontiercode-leaderboard/data.json) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `score` \| 0.0925 \| score_fraction \| blocking_criteria_adjusted \| Higher is better \| \| `correct` \| 0.106 \| score_fraction \| raw_rubric \| Higher is better \| \| `cost` \| 0.3642 \| USD \| per_rollout \| Lower is better \| ### Configuration harness codex Reasoning effort low sourceVersion v1_1 subset main ### Reported statistics flaggedRate 0 sampleSize 100 ### Source [Original source](https://cognition.com/data/frontiercode-leaderboard/data.json) Source frontiercode Original model label GPT-5.4-mini Observed 2026-10-22T05:40:03.220Z Evidence SHA-256 `ff0040778b7bdf69c705ad7474f771fb5e53cfaf5cf8573b3a4614153543d75f` Source locator `/v1_1/data/GPT-5.4-mini/low/main` |  |  |  |  |  |
| [FrontierCode 1 extended](https://benchize.com/benchmarks/frontiercode%3Av1%3Aextended.md) | 17.4% | 34 / 39 | $0.3 | [frontiercode](https://cognition.com/data/frontiercode-leaderboard/data.json) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `score` \| 0.174 \| score_fraction \| blocking_criteria_adjusted \| Higher is better \| \| `correct` \| 0.194 \| score_fraction \| raw_rubric \| Higher is better \| \| `cost` \| 0.3 \| USD \| per_rollout \| Lower is better \| ### Configuration harness codex Reasoning effort low sourceVersion v1 subset extended ### Reported statistics flaggedRate Not reported sampleSize 150 ### Source [Original source](https://cognition.com/data/frontiercode-leaderboard/data.json) Source frontiercode Original model label GPT-5.4-mini Observed 2026-10-22T05:40:03.220Z Evidence SHA-256 `ff0040778b7bdf69c705ad7474f771fb5e53cfaf5cf8573b3a4614153543d75f` Source locator `/v1/data/GPT-5.4-mini/low/extended` |  |  |  |  |  |
| [ARC-AGI-2](https://benchize.com/benchmarks/arc-prize%3Av2_Semi_Private.md) | 1.11% | 218 / 243 | 0.06usd per task | [arc prize · v2](https://arcprize.org/media/data/leaderboard/v2.json) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `score` \| 0.0111 \| score_fraction \| v2_Semi_Private \| Higher is better \| \| `cost_per_task` \| 0.06 \| usd_per_task \| v2_Semi_Private \| Lower is better \| ### Configuration evaluationSplit v2_Semi_Private harness Not reported modelGroup gpt-5-4-mini-reasoning modelType CoT Reasoning effort low sourceModelVersion gpt-5-4-mini-low thinkingEnabled true ### Source [Original source](https://arcprize.org/media/data/leaderboard/v2.json) Source arc prize Original model label GPT-5.4 Mini (Low) Source version v2 Observed 2026-10-22T05:20:04.306Z Evidence SHA-256 `4351eb696e78113b0459e9bb5f0258318b905efef34f473dcea51ce641b0d94d` Source locator `/evaluations/138` |  |  |  |  |  |
| [FrontierCode 1 main](https://benchize.com/benchmarks/frontiercode%3Av1%3Amain.md) | 4.7% | 36 / 39 | $0.4 | [frontiercode](https://cognition.com/data/frontiercode-leaderboard/data.json) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `score` \| 0.047 \| score_fraction \| blocking_criteria_adjusted \| Higher is better \| \| `correct` \| 0.054 \| score_fraction \| raw_rubric \| Higher is better \| \| `cost` \| 0.4 \| USD \| per_rollout \| Lower is better \| ### Configuration harness codex Reasoning effort low sourceVersion v1 subset main ### Reported statistics flaggedRate Not reported sampleSize 100 ### Source [Original source](https://cognition.com/data/frontiercode-leaderboard/data.json) Source frontiercode Original model label GPT-5.4-mini Observed 2026-10-22T05:40:03.220Z Evidence SHA-256 `ff0040778b7bdf69c705ad7474f771fb5e53cfaf5cf8573b3a4614153543d75f` Source locator `/v1/data/GPT-5.4-mini/low/main` |  |  |  |  |  |
| [ARC-AGI-1](https://benchize.com/benchmarks/arc-prize%3Av1_Semi_Private.md) | 13% | 224 / 245 | 0.04usd per task | [arc prize · v1](https://arcprize.org/media/data/leaderboard/v1.json) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `score` \| 0.13 \| score_fraction \| v1_Semi_Private \| Higher is better \| \| `cost_per_task` \| 0.04 \| usd_per_task \| v1_Semi_Private \| Lower is better \| ### Configuration evaluationSplit v1_Semi_Private harness Not reported modelGroup gpt-5-4-mini-reasoning modelType CoT Reasoning effort low sourceModelVersion gpt-5-4-mini-low thinkingEnabled true ### Source [Original source](https://arcprize.org/media/data/leaderboard/v1.json) Source arc prize Original model label GPT-5.4 Mini (Low) Source version v1 Observed 2026-10-22T05:20:04.066Z Evidence SHA-256 `2bf68d22dafba37047d07ad833ebc0e8199c9aa2f9eeaed50c75c1b704462836` Source locator `/evaluations/137` |  |  |  |  |  |

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