# GPT-5.2Medium > Source: Benchize (https://benchize.com) — https://benchize.com/models/gpt-5-2-medium. When citing or reusing this content, credit "Benchize" and link to https://benchize.com/models/gpt-5-2-medium. OpenAI Canonical URL: https://benchize.com/models/gpt-5-2-medium Last updated: Thu, 22 Oct 2026 07:32:33 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 | | | --- | --- | --- | --- | --- | --- | --- | | [DesignArena Browser game generation](https://benchize.com/benchmarks/designarena%3Agame-dev.md) | 1,184elo | — | 53 / 117 | — | [designarena · public](https://www.designarena.ai/api/leaderboard#board=game-dev) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `elo` \| 1184 \| elo \| game-dev \| Higher is better \| ### Configuration arenaType models category gamedev inputModality Not reported Reasoning effort medium sourceModelVersion rockhopper thinkingEnabled true variationName public ### Reported statistics averageGenerationTimeMs 187134 battles 3775 losses 1783 standardError Not reported winRate 52.8 wins 1992 ### Source [Original source](https://www.designarena.ai/api/leaderboard#board=game-dev) Source designarena Original model label GPT-5.2 (Medium) Source version public Observed 2026-10-21T16:38:01.100Z Evidence SHA-256 `53db6a89112ce8cdf644568c666d4b8309aece764cfcedb291ffd52ae3934e30` Source locator `/data/82` | | | | | | | | [DesignArena 3D design generation](https://benchize.com/benchmarks/designarena%3A3d-design.md) | 1,079elo | — | 71 / 110 | — | [designarena · public](https://www.designarena.ai/api/leaderboard#board=3d-design) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `elo` \| 1079 \| elo \| 3d-design \| Higher is better \| ### Configuration arenaType models category 3d inputModality Not reported Reasoning effort medium sourceModelVersion rockhopper thinkingEnabled true variationName public ### Reported statistics averageGenerationTimeMs 138446 battles 4927 losses 2884 standardError Not reported winRate 41.5 wins 2043 ### Source [Original source](https://www.designarena.ai/api/leaderboard#board=3d-design) Source designarena Original model label GPT-5.2 (Medium) Source version public Observed 2026-10-21T16:37:58.515Z Evidence SHA-256 `bcc0267f7bc7e9ec112306b3a35413cf78bbccbfaa838356232d5d5ed0b83d0f` Source locator `/data/115` | | | | | | | | [ARC-AGI-2](https://benchize.com/benchmarks/arc-prize%3Av2_Semi_Private.md) | 26.67% | — | 128 / 243 | 0.76usd per task | [arc prize · v2](https://arcprize.org/media/data/leaderboard/v2.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `score` \| 0.2667 \| score_fraction \| v2_Semi_Private \| Higher is better \| \| `cost_per_task` \| 0.7594 \| usd_per_task \| v2_Semi_Private \| Lower is better \| ### Configuration evaluationSplit v2_Semi_Private harness Not reported modelGroup gpt-5-2-2025-12-11-thinking modelType CoT Reasoning effort medium sourceModelVersion gpt-5-2-2025-12-11-thinking-medium thinkingEnabled true ### Source [Original source](https://arcprize.org/media/data/leaderboard/v2.json) Source arc prize Original model label GPT-5.2 (Medium) Source version v2 Observed 2026-10-22T05:20:04.306Z Evidence SHA-256 `4351eb696e78113b0459e9bb5f0258318b905efef34f473dcea51ce641b0d94d` Source locator `/evaluations/104` | | | | | | | | [DesignArena UI component generation](https://benchize.com/benchmarks/designarena%3Aui-components.md) | 1,190elo | — | 51 / 112 | — | [designarena · public](https://www.designarena.ai/api/leaderboard#board=ui-components) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `elo` \| 1190 \| elo \| ui-components \| Higher is better \| ### Configuration arenaType models category uicomponent inputModality Not reported Reasoning effort medium sourceModelVersion rockhopper thinkingEnabled true variationName public ### Reported statistics averageGenerationTimeMs 140379 battles 1773 losses 863 standardError Not reported winRate 51.3 wins 910 ### Source [Original source](https://www.designarena.ai/api/leaderboard#board=ui-components) Source designarena Original model label GPT-5.2 (Medium) Source version public Observed 2026-10-21T16:37:57.993Z Evidence SHA-256 `46482ec1b4012638eace65493daea4750e2088098018fd9d5fc46126fc1f8557` Source locator `/data/81` | | | | | | | | [DesignArena Data visualization generation](https://benchize.com/benchmarks/designarena%3Adata-viz.md) | 1,156elo | — | 72 / 99 | — | [designarena · public](https://www.designarena.ai/api/leaderboard#board=data-viz) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `elo` \| 1156 \| elo \| data-viz \| Higher is better \| ### Configuration arenaType models category dataviz inputModality Not reported Reasoning effort medium sourceModelVersion rockhopper thinkingEnabled true variationName public ### Reported statistics averageGenerationTimeMs 140591 battles 1296 losses 697 standardError Not reported winRate 46.2 wins 599 ### Source [Original source](https://www.designarena.ai/api/leaderboard#board=data-viz) Source designarena Original model label GPT-5.2 (Medium) Source version public Observed 2026-10-21T16:37:58.264Z Evidence SHA-256 `a895f6f1a25fa8eb01f821c2097ddec4f884de7bd22f1b8a22e82e6679b71849` Source locator `/data/105` | | | | | | | | [DesignArena SVG generation](https://benchize.com/benchmarks/designarena%3Asvgs.md) | 1,139elo | — | 42 / 77 | — | [designarena · public](https://www.designarena.ai/api/leaderboard#board=svgs) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `elo` \| 1139 \| elo \| svgs \| Higher is better \| ### Configuration arenaType models category svg inputModality Not reported Reasoning effort medium sourceModelVersion rockhopper thinkingEnabled true variationName public ### Reported statistics averageGenerationTimeMs 44484 battles 5056 losses 2341 standardError Not reported winRate 53.7 wins 2715 ### Source [Original source](https://www.designarena.ai/api/leaderboard#board=svgs) Source designarena Original model label GPT-5.2 (Medium) Source version public Observed 2026-10-21T16:38:03.249Z Evidence SHA-256 `8cbc34a474a66ef5c64f3ffe557df9b55bf7e13368c07c0214223e3ed8f3f21e` Source locator `/data/72` | | | | | | | | [Short Story Writing — Pairwise Comparison](https://benchize.com/benchmarks/lechmazur-short-story%3Apairwise.md) | 0.33 | 95% CI 0.18–0.47 | 26 / 50 | — | [lechmazur short story · 8ba548d1cffefa5c472d3832e05f64e119a88fa4](https://api.github.com/repos/lechmazur/writing/contents/data/writing_gemini_argon_20261013/ratings.csv?ref=8ba548d1cffefa5c472d3832e05f64e119a88fa4) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `thurstone_rating` \| 0.33259015486618937 \| index \| pooled_observed_panel \| Higher is better \| \| `win_probability` \| 0.5499731475522392 \| score_fraction \| comparison_pool \| Higher is better \| ### Configuration benchmarkScope data/writing_gemini_argon_20261013 Reasoning effort medium thinkingEnabled true ### Reported statistics Uncertainty 95% confidence interval: 0.18–0.47 bootstrapSamples 300 confidenceInterval95 ["0.18370605578987498","0.47450018520360404"] sourceRank 26 ### Source [Original source](https://api.github.com/repos/lechmazur/writing/contents/data/writing_gemini_argon_20261013/ratings.csv?ref=8ba548d1cffefa5c472d3832e05f64e119a88fa4) Source lechmazur short story Original model label GPT-5.2 (medium) Source version 8ba548d1cffefa5c472d3832e05f64e119a88fa4 Observed 2026-10-22T07:10:06.634Z Evidence SHA-256 `c36baebed9f302ff7ad8fe97907d72e1757a015a39b6a3b23437597cf8e3bff6` Source locator `/rows/25` | | | | | | | | [ARC-AGI-1](https://benchize.com/benchmarks/arc-prize%3Av1_Semi_Private.md) | 72.67% | — | 128 / 245 | 0.34usd per task | [arc prize · v1](https://arcprize.org/media/data/leaderboard/v1.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `score` \| 0.7267 \| score_fraction \| v1_Semi_Private \| Higher is better \| \| `cost_per_task` \| 0.3448 \| usd_per_task \| v1_Semi_Private \| Lower is better \| ### Configuration evaluationSplit v1_Semi_Private harness Not reported modelGroup gpt-5-2-2025-12-11-thinking modelType CoT Reasoning effort medium sourceModelVersion gpt-5-2-2025-12-11-thinking-medium thinkingEnabled true ### Source [Original source](https://arcprize.org/media/data/leaderboard/v1.json) Source arc prize Original model label GPT-5.2 (Medium) Source version v1 Observed 2026-10-22T05:20:04.066Z Evidence SHA-256 `2bf68d22dafba37047d07ad833ebc0e8199c9aa2f9eeaed50c75c1b704462836` Source locator `/evaluations/101` | | | | | | | | [DesignArena ASCII art generation](https://benchize.com/benchmarks/designarena%3Aascii.md) | 1,127elo | — | 47 / 65 | — | [designarena · public](https://www.designarena.ai/api/leaderboard#board=ascii) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `elo` \| 1127 \| elo \| ascii \| Higher is better \| ### Configuration arenaType models category ascii inputModality Not reported Reasoning effort medium sourceModelVersion rockhopper thinkingEnabled true variationName public ### Reported statistics averageGenerationTimeMs 42614 battles 421 losses 223 standardError Not reported winRate 47 wins 198 ### Source [Original source](https://www.designarena.ai/api/leaderboard#board=ascii) Source designarena Original model label GPT-5.2 (Medium) Source version public Observed 2026-10-21T16:38:03.513Z Evidence SHA-256 `0603b8c65b44ee887f5b566feb469465f59635137a6ac5c6d94c23bcf3776311` Source locator `/data/65` | | | | | | | | [DesignArena Overall frontend coding](https://benchize.com/benchmarks/designarena%3Acode.md) | 1,170elo | SE ±2.22 | 63 / 116 | — | [designarena · public](https://www.designarena.ai/api/leaderboard#board=code) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `elo` \| 1170 \| elo \| code \| Higher is better \| ### Configuration arenaType models category allcategories inputModality text Reasoning effort medium sourceModelVersion rockhopper thinkingEnabled true variationName public ### Reported statistics Uncertainty Standard error: ±2.22 averageGenerationTimeMs 173371 battles 27942 losses 14079 standardError 2.2239 winRate 49.6 wins 13863 ### Source [Original source](https://www.designarena.ai/api/leaderboard#board=code) Source designarena Original model label GPT-5.2 (Medium) Source version public Observed 2026-10-21T16:37:57.301Z Evidence SHA-256 `0c897b58670f5e352bd123db999a40c0d1781a443964c502b90774a76a3a7758` Source locator `/data/96` | | | | | | | | [DesignArena Website generation](https://benchize.com/benchmarks/designarena%3Awebsite.md) | 1,184elo | — | 62 / 123 | — | [designarena · public](https://www.designarena.ai/api/leaderboard#board=website) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `elo` \| 1184 \| elo \| website \| Higher is better \| ### Configuration arenaType models category website inputModality text Reasoning effort medium sourceModelVersion rockhopper thinkingEnabled true variationName public ### Reported statistics averageGenerationTimeMs 183710 battles 17219 losses 8447 standardError Not reported winRate 50.9 wins 8772 ### Source [Original source](https://www.designarena.ai/api/leaderboard#board=website) Source designarena Original model label GPT-5.2 (Medium) Source version public Observed 2026-10-21T16:37:57.757Z Evidence SHA-256 `51873e97776a3c5ae706b24cc2c60384793dd18398df970e213a8e7c276d8ac0` Source locator `/data/98` | | | | | | | --- Cite as: GPT-5.2Medium — Benchize, https://benchize.com/models/gpt-5-2-medium (retrieved 2026-10-22)