# GPT-5.2Low > Source: Benchize (https://benchize.com) — https://benchize.com/models/gpt-5-2-low. When citing or reusing this content, credit "Benchize" and link to https://benchize.com/models/gpt-5-2-low. OpenAI Canonical URL: https://benchize.com/models/gpt-5-2-low 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 | | | --- | --- | --- | --- | --- | --- | --- | | [DesignArena UI component generation](https://benchize.com/benchmarks/designarena%3Aui-components.md) | 1,159elo | — | 66 / 112 | — | [designarena · public](https://www.designarena.ai/api/leaderboard#board=ui-components) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `elo` \| 1159 \| elo \| ui-components \| Higher is better \| ### Configuration arenaType models category uicomponent inputModality Not reported Reasoning effort low sourceModelVersion macaroni thinkingEnabled true variationName public ### Reported statistics averageGenerationTimeMs 138724 battles 1420 losses 733 standardError Not reported winRate 48.4 wins 687 ### Source [Original source](https://www.designarena.ai/api/leaderboard#board=ui-components) Source designarena Original model label GPT-5.2 (Low) Source version public Observed 2026-10-21T16:37:57.993Z Evidence SHA-256 `46482ec1b4012638eace65493daea4750e2088098018fd9d5fc46126fc1f8557` Source locator `/data/99` | | | | | | | | [DesignArena Data visualization generation](https://benchize.com/benchmarks/designarena%3Adata-viz.md) | 1,186elo | — | 54 / 99 | — | [designarena · public](https://www.designarena.ai/api/leaderboard#board=data-viz) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `elo` \| 1186 \| elo \| data-viz \| Higher is better \| ### Configuration arenaType models category dataviz inputModality Not reported Reasoning effort low sourceModelVersion macaroni thinkingEnabled true variationName public ### Reported statistics averageGenerationTimeMs 144055 battles 1093 losses 525 standardError Not reported winRate 52 wins 568 ### Source [Original source](https://www.designarena.ai/api/leaderboard#board=data-viz) Source designarena Original model label GPT-5.2 (Low) Source version public Observed 2026-10-21T16:37:58.264Z Evidence SHA-256 `a895f6f1a25fa8eb01f821c2097ddec4f884de7bd22f1b8a22e82e6679b71849` Source locator `/data/81` | | | | | | | | [ARC-AGI-2](https://benchize.com/benchmarks/arc-prize%3Av2_Semi_Private.md) | 9.72% | — | 148 / 243 | 0.26usd per task | [arc prize · v2](https://arcprize.org/media/data/leaderboard/v2.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `score` \| 0.0972 \| score_fraction \| v2_Semi_Private \| Higher is better \| \| `cost_per_task` \| 0.2642 \| 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 low sourceModelVersion gpt-5-2-2025-12-11-thinking-low thinkingEnabled true ### Source [Original source](https://arcprize.org/media/data/leaderboard/v2.json) Source arc prize Original model label GPT-5.2 (Low) Source version v2 Observed 2026-10-22T05:20:04.306Z Evidence SHA-256 `4351eb696e78113b0459e9bb5f0258318b905efef34f473dcea51ce641b0d94d` Source locator `/evaluations/103` | | | | | | | | [DesignArena 3D design generation](https://benchize.com/benchmarks/designarena%3A3d-design.md) | 1,067elo | — | 76 / 110 | — | [designarena · public](https://www.designarena.ai/api/leaderboard#board=3d-design) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `elo` \| 1067 \| elo \| 3d-design \| Higher is better \| ### Configuration arenaType models category 3d inputModality Not reported Reasoning effort low sourceModelVersion macaroni thinkingEnabled true variationName public ### Reported statistics averageGenerationTimeMs 127243 battles 3744 losses 2169 standardError Not reported winRate 42.1 wins 1575 ### Source [Original source](https://www.designarena.ai/api/leaderboard#board=3d-design) Source designarena Original model label GPT-5.2 (Low) Source version public Observed 2026-10-21T16:37:58.515Z Evidence SHA-256 `bcc0267f7bc7e9ec112306b3a35413cf78bbccbfaa838356232d5d5ed0b83d0f` Source locator `/data/121` | | | | | | | | [DesignArena Browser game generation](https://benchize.com/benchmarks/designarena%3Agame-dev.md) | 1,195elo | — | 47 / 117 | — | [designarena · public](https://www.designarena.ai/api/leaderboard#board=game-dev) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `elo` \| 1195 \| elo \| game-dev \| Higher is better \| ### Configuration arenaType models category gamedev inputModality Not reported Reasoning effort low sourceModelVersion macaroni thinkingEnabled true variationName public ### Reported statistics averageGenerationTimeMs 180980 battles 3324 losses 1461 standardError Not reported winRate 56 wins 1863 ### Source [Original source](https://www.designarena.ai/api/leaderboard#board=game-dev) Source designarena Original model label GPT-5.2 (Low) Source version public Observed 2026-10-21T16:38:01.100Z Evidence SHA-256 `53db6a89112ce8cdf644568c666d4b8309aece764cfcedb291ffd52ae3934e30` Source locator `/data/75` | | | | | | | | [DesignArena Overall frontend coding](https://benchize.com/benchmarks/designarena%3Acode.md) | 1,166elo | SE ±2.32 | 67 / 116 | — | [designarena · public](https://www.designarena.ai/api/leaderboard#board=code) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `elo` \| 1166 \| elo \| code \| Higher is better \| ### Configuration arenaType models category allcategories inputModality text Reasoning effort low sourceModelVersion macaroni thinkingEnabled true variationName public ### Reported statistics Uncertainty Standard error: ±2.32 averageGenerationTimeMs 166020 battles 25463 losses 12664 standardError 2.3207 winRate 50.3 wins 12799 ### Source [Original source](https://www.designarena.ai/api/leaderboard#board=code) Source designarena Original model label GPT-5.2 (Low) Source version public Observed 2026-10-21T16:37:57.301Z Evidence SHA-256 `0c897b58670f5e352bd123db999a40c0d1781a443964c502b90774a76a3a7758` Source locator `/data/101` | | | | | | | | [ArXivMath 01/2026](https://benchize.com/benchmarks/matharena%3Aarxiv--january.md) | 47.9% | 95% CI 40.66–55.14% | 17 / 18 | 0.05usd per problem | [matharena · arxiv--january](https://matharena.ai/competition_tables/arxiv--january) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 47.90 \| percent \| competition \| Higher is better \| \| `cost_per_problem` \| 0.047 \| usd_per_problem \| competition \| Lower is better \| ### Configuration competition arxiv--january predicted false Reasoning effort low sourceModelName GPT-5.2 (low) sourceModelVersion openai/gpt-52-low thinkingEnabled true ### Reported statistics Uncertainty 95% confidence interval: 40.66–55.14% confidenceInterval95 7.24 problems 23 ### Source [Original source](https://matharena.ai/competition_tables/arxiv--january) Source matharena Original model label GPT-5.2 (low) Source version arxiv--january Observed 2026-10-22T05:30:07.835Z Evidence SHA-256 `e895f6ccd0711bb1a512b580bab39de8f977c57f83bf492527e4fc710315d706` Source locator `/table/rows/22` | | | | | | | | [ArXivMath 12/2025](https://benchize.com/benchmarks/matharena%3Aarxiv--december.md) | 32.35% | 95% CI 21.23–43.47% | 12 / 12 | 0.05usd per problem | [matharena · arxiv--december](https://matharena.ai/competition_tables/arxiv--december) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 32.35 \| percent \| competition \| Higher is better \| \| `cost_per_problem` \| 0.048 \| usd_per_problem \| competition \| Lower is better \| ### Configuration competition arxiv--december predicted false Reasoning effort low sourceModelName GPT-5.2 (low) sourceModelVersion openai/gpt-52-low thinkingEnabled true ### Reported statistics Uncertainty 95% confidence interval: 21.23–43.47% confidenceInterval95 11.12 problems 17 ### Source [Original source](https://matharena.ai/competition_tables/arxiv--december) Source matharena Original model label GPT-5.2 (low) Source version arxiv--december Observed 2026-10-22T05:30:07.569Z Evidence SHA-256 `6bbceef2706ad55e793e81bd959f7c1ec869f0ad04c6aa9013b2ad7b1a0820e3` Source locator `/table/rows/18` | | | | | | | | [DesignArena ASCII art generation](https://benchize.com/benchmarks/designarena%3Aascii.md) | 1,152elo | — | 36 / 65 | — | [designarena · public](https://www.designarena.ai/api/leaderboard#board=ascii) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `elo` \| 1152 \| elo \| ascii \| Higher is better \| ### Configuration arenaType models category ascii inputModality Not reported Reasoning effort low sourceModelVersion macaroni thinkingEnabled true variationName public ### Reported statistics averageGenerationTimeMs 45842 battles 371 losses 183 standardError Not reported winRate 50.7 wins 188 ### Source [Original source](https://www.designarena.ai/api/leaderboard#board=ascii) Source designarena Original model label GPT-5.2 (Low) Source version public Observed 2026-10-21T16:38:03.513Z Evidence SHA-256 `0603b8c65b44ee887f5b566feb469465f59635137a6ac5c6d94c23bcf3776311` Source locator `/data/53` | | | | | | | | [DesignArena SVG generation](https://benchize.com/benchmarks/designarena%3Asvgs.md) | 1,136elo | — | 43 / 77 | — | [designarena · public](https://www.designarena.ai/api/leaderboard#board=svgs) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `elo` \| 1136 \| elo \| svgs \| Higher is better \| ### Configuration arenaType models category svg inputModality Not reported Reasoning effort low sourceModelVersion macaroni thinkingEnabled true variationName public ### Reported statistics averageGenerationTimeMs 40484 battles 4773 losses 2237 standardError Not reported winRate 53.1 wins 2536 ### Source [Original source](https://www.designarena.ai/api/leaderboard#board=svgs) Source designarena Original model label GPT-5.2 (Low) Source version public Observed 2026-10-21T16:38:03.249Z Evidence SHA-256 `8cbc34a474a66ef5c64f3ffe557df9b55bf7e13368c07c0214223e3ed8f3f21e` Source locator `/data/74` | | | | | | | | [ARC-AGI-1](https://benchize.com/benchmarks/arc-prize%3Av1_Semi_Private.md) | 55.67% | — | 160 / 245 | 0.17usd per task | [arc prize · v1](https://arcprize.org/media/data/leaderboard/v1.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `score` \| 0.5567 \| score_fraction \| v1_Semi_Private \| Higher is better \| \| `cost_per_task` \| 0.1657 \| 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 low sourceModelVersion gpt-5-2-2025-12-11-thinking-low thinkingEnabled true ### Source [Original source](https://arcprize.org/media/data/leaderboard/v1.json) Source arc prize Original model label GPT-5.2 (Low) Source version v1 Observed 2026-10-22T05:20:04.066Z Evidence SHA-256 `2bf68d22dafba37047d07ad833ebc0e8199c9aa2f9eeaed50c75c1b704462836` Source locator `/evaluations/100` | | | | | | | | [DesignArena Website generation](https://benchize.com/benchmarks/designarena%3Awebsite.md) | 1,177elo | — | 69 / 123 | — | [designarena · public](https://www.designarena.ai/api/leaderboard#board=website) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `elo` \| 1177 \| elo \| website \| Higher is better \| ### Configuration arenaType models category website inputModality text Reasoning effort low sourceModelVersion macaroni thinkingEnabled true variationName public ### Reported statistics averageGenerationTimeMs 175209 battles 16104 losses 7900 standardError Not reported winRate 50.9 wins 8204 ### Source [Original source](https://www.designarena.ai/api/leaderboard#board=website) Source designarena Original model label GPT-5.2 (Low) Source version public Observed 2026-10-21T16:37:57.757Z Evidence SHA-256 `51873e97776a3c5ae706b24cc2c60384793dd18398df970e213a8e7c276d8ac0` Source locator `/data/104` | | | | | | | --- Cite as: GPT-5.2Low — Benchize, https://benchize.com/models/gpt-5-2-low (retrieved 2026-10-22)