# GPT-5 MiniMedium

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

OpenAI

Canonical URL: https://benchize.com/models/gpt-5-mini-medium
Last updated: Thu, 22 Oct 2026 08:20:15 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 |  |
| --- | --- | --- | --- | --- | --- |
| [ARC-AGI-1](https://benchize.com/benchmarks/arc-prize%3Av1_Semi_Private.md) | 37.33% | 183 / 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` \| 0.3733 \| score_fraction \| v1_Semi_Private \| Higher is better \| \| `cost_per_task` \| 0.0401 \| usd_per_task \| v1_Semi_Private \| Lower is better \| ### Configuration evaluationSplit v1_Semi_Private harness Not reported modelGroup gpt-5-mini-reasoning modelType CoT Reasoning effort medium sourceModelVersion gpt-5-mini-2025-08-07-medium thinkingEnabled true ### Source [Original source](https://arcprize.org/media/data/leaderboard/v1.json) Source arc prize Original model label GPT-5 Mini (Medium) Source version v1 Observed 2026-10-22T05:20:04.066Z Evidence SHA-256 `2bf68d22dafba37047d07ad833ebc0e8199c9aa2f9eeaed50c75c1b704462836` Source locator `/evaluations/64` |  |  |  |  |  |
| [SWE-bench Verified](https://benchize.com/benchmarks/swe-bench%3Averified.md) | 59.8% | 29 / 63 | — | [SWE-bench](https://www.swebench.com/) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `resolved` \| 59.8 \| percent \| verified \| Higher is better \| ### Configuration agent mini-SWE-agent agentOrganization SWE-agent models ["gpt-5-mini-2025-08-07"] Reasoning effort medium sourceSubmission 20250807_mini-v1.7.0_gpt-5-mini subset Verified system ["System: Attempts - 1"] ### Reported statistics instanceCalls 14.466 instanceCost 0.035477067300000005 sourceWarning Not reported ### Source [Original source](https://www.swebench.com/) Source SWE-bench Original model label GPT 5 mini Observed 2026-10-22T02:30:05.773Z Evidence SHA-256 `c862011a4ee1d1a7199fad6ca0905fa5c64f58216f7217ac1eddf37f28788433` Source locator `/leaderboard-data/2/results/78` |  |  |  |  |  |
| [ARC-AGI-2](https://benchize.com/benchmarks/arc-prize%3Av2_Semi_Private.md) | 4.03% | 173 / 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` \| 0.0403 \| score_fraction \| v2_Semi_Private \| Higher is better \| \| `cost_per_task` \| 0.0629 \| usd_per_task \| v2_Semi_Private \| Lower is better \| ### Configuration evaluationSplit v2_Semi_Private harness Not reported modelGroup gpt-5-mini-reasoning modelType CoT Reasoning effort medium sourceModelVersion gpt-5-mini-2025-08-07-medium thinkingEnabled true ### Source [Original source](https://arcprize.org/media/data/leaderboard/v2.json) Source arc prize Original model label GPT-5 Mini (Medium) Source version v2 Observed 2026-10-22T05:20:04.306Z Evidence SHA-256 `4351eb696e78113b0459e9bb5f0258318b905efef34f473dcea51ce641b0d94d` Source locator `/evaluations/66` |  |  |  |  |  |

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