# GPT-5.4 MiniMedium

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

OpenAI

Canonical URL: https://benchize.com/models/gpt-5-4-mini-medium
Last updated: Thu, 22 Oct 2026 08:00:11 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 |  |
| --- | --- | --- | --- | --- | --- |
| [FrontierCode 1 extended](https://benchize.com/benchmarks/frontiercode%3Av1%3Aextended.md) | 28.89% | 30 / 39 | $0.76 | [frontiercode](https://cognition.com/data/frontiercode-leaderboard/data.json) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `score` \| 0.2889 \| score_fraction \| blocking_criteria_adjusted \| Higher is better \| \| `correct` \| 0.3219 \| score_fraction \| raw_rubric \| Higher is better \| \| `cost` \| 0.7602 \| USD \| per_rollout \| Lower is better \| ### Configuration harness codex Reasoning effort medium 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/medium/extended` |  |  |  |  |  |
| [FrontierCode 1.1 main](https://benchize.com/benchmarks/frontiercode%3Av1_1%3Amain.md) | 20.78% | 117 / 125 | $0.78 | [frontiercode](https://cognition.com/data/frontiercode-leaderboard/data.json) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `score` \| 0.2078 \| score_fraction \| blocking_criteria_adjusted \| Higher is better \| \| `correct` \| 0.2373 \| score_fraction \| raw_rubric \| Higher is better \| \| `cost` \| 0.7833 \| USD \| per_rollout \| Lower is better \| ### Configuration harness codex Reasoning effort medium 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/medium/main` |  |  |  |  |  |
| [ARC-AGI-1](https://benchize.com/benchmarks/arc-prize%3Av1_Semi_Private.md) | 40.83% | 179 / 245 | 0.16usd per task | [arc prize · v1](https://arcprize.org/media/data/leaderboard/v1.json) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `score` \| 0.4083 \| score_fraction \| v1_Semi_Private \| Higher is better \| \| `cost_per_task` \| 0.16 \| 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 medium sourceModelVersion gpt-5-4-mini-medium thinkingEnabled true ### Source [Original source](https://arcprize.org/media/data/leaderboard/v1.json) Source arc prize Original model label GPT-5.4 Mini (Medium) Source version v1 Observed 2026-10-22T05:20:04.066Z Evidence SHA-256 `2bf68d22dafba37047d07ad833ebc0e8199c9aa2f9eeaed50c75c1b704462836` Source locator `/evaluations/136` |  |  |  |  |  |
| [FrontierCode 1 main](https://benchize.com/benchmarks/frontiercode%3Av1%3Amain.md) | 12.05% | 30 / 39 | $0.89 | [frontiercode](https://cognition.com/data/frontiercode-leaderboard/data.json) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `score` \| 0.1205 \| score_fraction \| blocking_criteria_adjusted \| Higher is better \| \| `correct` \| 0.137 \| score_fraction \| raw_rubric \| Higher is better \| \| `cost` \| 0.8851 \| USD \| per_rollout \| Lower is better \| ### Configuration harness codex Reasoning effort medium 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/medium/main` |  |  |  |  |  |
| [FrontierCode 1.1 extended](https://benchize.com/benchmarks/frontiercode%3Av1_1%3Aextended.md) | 35.06% | 116 / 125 | $0.67 | [frontiercode](https://cognition.com/data/frontiercode-leaderboard/data.json) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `score` \| 0.3506 \| score_fraction \| blocking_criteria_adjusted \| Higher is better \| \| `correct` \| 0.3922 \| score_fraction \| raw_rubric \| Higher is better \| \| `cost` \| 0.6716 \| USD \| per_rollout \| Lower is better \| ### Configuration harness codex Reasoning effort medium 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/medium/extended` |  |  |  |  |  |
| [ARC-AGI-2](https://benchize.com/benchmarks/arc-prize%3Av2_Semi_Private.md) | 4.44% | 171 / 243 | 0.33usd per task | [arc prize · v2](https://arcprize.org/media/data/leaderboard/v2.json) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `score` \| 0.0444 \| score_fraction \| v2_Semi_Private \| Higher is better \| \| `cost_per_task` \| 0.33 \| 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 medium sourceModelVersion gpt-5-4-mini-medium thinkingEnabled true ### Source [Original source](https://arcprize.org/media/data/leaderboard/v2.json) Source arc prize Original model label GPT-5.4 Mini (Medium) Source version v2 Observed 2026-10-22T05:20:04.306Z Evidence SHA-256 `4351eb696e78113b0459e9bb5f0258318b905efef34f473dcea51ce641b0d94d` Source locator `/evaluations/137` |  |  |  |  |  |

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