# GPT-5.4Low > Source: Benchize (https://benchize.com) — https://benchize.com/models/gpt-5-4-low. When citing or reusing this content, credit "Benchize" and link to https://benchize.com/models/gpt-5-4-low. OpenAI Canonical URL: https://benchize.com/models/gpt-5-4-low Last updated: Thu, 22 Oct 2026 06:20:09 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 | | | --- | --- | --- | --- | --- | --- | --- | | [DesignArena 3D design generation](https://benchize.com/benchmarks/designarena%3A3d-design.md) | 1,066elo | — | 77 / 110 | — | [designarena · public](https://www.designarena.ai/api/leaderboard#board=3d-design) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `elo` \| 1066 \| elo \| 3d-design \| Higher is better \| ### Configuration arenaType models category 3d inputModality Not reported Reasoning effort low sourceModelVersion gpt-5.4-low thinkingEnabled true variationName public ### Reported statistics averageGenerationTimeMs 64820 battles 4300 losses 2626 standardError Not reported winRate 38.9 wins 1674 ### Source [Original source](https://www.designarena.ai/api/leaderboard#board=3d-design) Source designarena Original model label GPT-5.4 (Low) Source version public Observed 2026-10-21T16:37:58.515Z Evidence SHA-256 `bcc0267f7bc7e9ec112306b3a35413cf78bbccbfaa838356232d5d5ed0b83d0f` Source locator `/data/122` | | | | | | | | [DesignArena SVG generation](https://benchize.com/benchmarks/designarena%3Asvgs.md) | 1,142elo | — | 39 / 77 | — | [designarena · public](https://www.designarena.ai/api/leaderboard#board=svgs) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `elo` \| 1142 \| elo \| svgs \| Higher is better \| ### Configuration arenaType models category svg inputModality Not reported Reasoning effort low sourceModelVersion gpt-5.4-low thinkingEnabled true variationName public ### Reported statistics averageGenerationTimeMs 23361 battles 3842 losses 1797 standardError Not reported winRate 53.2 wins 2045 ### Source [Original source](https://www.designarena.ai/api/leaderboard#board=svgs) Source designarena Original model label GPT-5.4 (Low) Source version public Observed 2026-10-21T16:38:03.249Z Evidence SHA-256 `8cbc34a474a66ef5c64f3ffe557df9b55bf7e13368c07c0214223e3ed8f3f21e` Source locator `/data/69` | | | | | | | | [DesignArena Overall frontend coding](https://benchize.com/benchmarks/designarena%3Acode.md) | 1,180elo | SE ±2.53 | 54 / 116 | — | [designarena · public](https://www.designarena.ai/api/leaderboard#board=code) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `elo` \| 1180 \| elo \| code \| Higher is better \| ### Configuration arenaType models category allcategories inputModality text Reasoning effort low sourceModelVersion gpt-5.4-low thinkingEnabled true variationName public ### Reported statistics Uncertainty Standard error: ±2.53 averageGenerationTimeMs 85870 battles 21154 losses 10745 standardError 2.5311 winRate 49.2 wins 10409 ### Source [Original source](https://www.designarena.ai/api/leaderboard#board=code) Source designarena Original model label GPT-5.4 (Low) Source version public Observed 2026-10-21T16:37:57.301Z Evidence SHA-256 `0c897b58670f5e352bd123db999a40c0d1781a443964c502b90774a76a3a7758` Source locator `/data/86` | | | | | | | | [AutomationBench](https://benchize.com/benchmarks/zapier%3Aautomationbench.md) | 1.52% | — | 102 / 113 | $0.13 | [zapier](https://framerusercontent.com/sites/4WTSl4BNjd1q9QFEFibC6h/lOvLnhItj8S8-1vyjH_s33Jn-WmUXPmiJ5Diajl0Q38.CMutaHYl.mjs) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `score` \| 1.52 \| percent \| reported \| Higher is better \| \| `cost` \| 0.13 \| USD \| per_task \| Lower is better \| ### Configuration benchmarkVersion 1.0.6 costFootnote false Fallback policy Not reported Reasoning effort low Model configuration GPT-5.4 (Low) thinkingEnabled true ### Reported statistics rank 115 ### Source [Original source](https://framerusercontent.com/sites/4WTSl4BNjd1q9QFEFibC6h/lOvLnhItj8S8-1vyjH_s33Jn-WmUXPmiJ5Diajl0Q38.CMutaHYl.mjs) Source zapier Original model label GPT-5.4 (Low) Observed 2026-10-21T16:34:56.783Z Evidence SHA-256 `43978e38f018789fa59c11de5328abe9e5905bfa9a5a4d601fa3aa4d9c153b0d` Source locator `/rows/114` | | | | | | | | [DesignArena Data visualization generation](https://benchize.com/benchmarks/designarena%3Adata-viz.md) | 1,196elo | — | 49 / 99 | — | [designarena · public](https://www.designarena.ai/api/leaderboard#board=data-viz) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `elo` \| 1196 \| elo \| data-viz \| Higher is better \| ### Configuration arenaType models category dataviz inputModality Not reported Reasoning effort low sourceModelVersion gpt-5.4-low thinkingEnabled true variationName public ### Reported statistics averageGenerationTimeMs 70128 battles 1191 losses 569 standardError Not reported winRate 52.2 wins 622 ### Source [Original source](https://www.designarena.ai/api/leaderboard#board=data-viz) Source designarena Original model label GPT-5.4 (Low) Source version public Observed 2026-10-21T16:37:58.264Z Evidence SHA-256 `a895f6f1a25fa8eb01f821c2097ddec4f884de7bd22f1b8a22e82e6679b71849` Source locator `/data/75` | | | | | | | | [DesignArena UI component generation](https://benchize.com/benchmarks/designarena%3Aui-components.md) | 1,215elo | — | 46 / 112 | — | [designarena · public](https://www.designarena.ai/api/leaderboard#board=ui-components) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `elo` \| 1215 \| elo \| ui-components \| Higher is better \| ### Configuration arenaType models category uicomponent inputModality Not reported Reasoning effort low sourceModelVersion gpt-5.4-low thinkingEnabled true variationName public ### Reported statistics averageGenerationTimeMs 61413 battles 129 losses 47 standardError Not reported winRate 63.6 wins 82 ### Source [Original source](https://www.designarena.ai/api/leaderboard#board=ui-components) Source designarena Original model label GPT-5.4 (Low) Source version public Observed 2026-10-21T16:37:57.993Z Evidence SHA-256 `46482ec1b4012638eace65493daea4750e2088098018fd9d5fc46126fc1f8557` Source locator `/data/70` | | | | | | | | [NC Bench](https://benchize.com/benchmarks/nc-bench%3Aoverall.md) | 90.91% | — | 48 / 144 | — | [nc bench](https://www.nc-bench.com/models) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `score` \| 90.91 \| percent \| reported \| Higher is better \| \| `tooling` \| 99.97 \| percent \| category \| Higher is better \| \| `creative_writing` \| 90.51 \| percent \| category \| Higher is better \| \| `language` \| 90.79 \| percent \| category \| Higher is better \| \| `utility` \| 95.32 \| percent \| category \| Higher is better \| \| `reasoning` \| 86.99 \| percent \| category \| Higher is better \| \| `text_editing` \| 98.01 \| percent \| category \| Higher is better \| \| `rule_following` \| 70.02 \| percent \| category \| Higher is better \| \| `hallucination` \| 95.71 \| percent \| category \| Higher is better \| ### Configuration Reasoning effort low Model configuration GPT-5.4 (Reasoning, Low) thinkingEnabled true ### Source [Original source](https://www.nc-bench.com/models) Source nc bench Original model label GPT-5.4 (Reasoning, Low) Observed 2026-10-22T06:10:03.426Z Evidence SHA-256 `ec261022458543624b08a136d01f5a2f0666cd52ffb49c64d6ca983e8543d1b5` Source locator `/rows/59` | | | | | | | | [DesignArena Website generation](https://benchize.com/benchmarks/designarena%3Awebsite.md) | 1,198elo | — | 52 / 123 | — | [designarena · public](https://www.designarena.ai/api/leaderboard#board=website) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `elo` \| 1198 \| elo \| website \| Higher is better \| ### Configuration arenaType models category website inputModality text Reasoning effort low sourceModelVersion gpt-5.4-low thinkingEnabled true variationName public ### Reported statistics averageGenerationTimeMs 89294 battles 12840 losses 6360 standardError Not reported winRate 50.5 wins 6480 ### Source [Original source](https://www.designarena.ai/api/leaderboard#board=website) Source designarena Original model label GPT-5.4 (Low) Source version public Observed 2026-10-21T16:37:57.757Z Evidence SHA-256 `51873e97776a3c5ae706b24cc2c60384793dd18398df970e213a8e7c276d8ac0` Source locator `/data/83` | | | | | | | | [DesignArena Browser game generation](https://benchize.com/benchmarks/designarena%3Agame-dev.md) | 1,191elo | — | 50 / 117 | — | [designarena · public](https://www.designarena.ai/api/leaderboard#board=game-dev) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `elo` \| 1191 \| elo \| game-dev \| Higher is better \| ### Configuration arenaType models category gamedev inputModality Not reported Reasoning effort low sourceModelVersion gpt-5.4-low thinkingEnabled true variationName public ### Reported statistics averageGenerationTimeMs 95576 battles 3767 losses 1778 standardError Not reported winRate 52.8 wins 1989 ### Source [Original source](https://www.designarena.ai/api/leaderboard#board=game-dev) Source designarena Original model label GPT-5.4 (Low) Source version public Observed 2026-10-21T16:38:01.100Z Evidence SHA-256 `53db6a89112ce8cdf644568c666d4b8309aece764cfcedb291ffd52ae3934e30` Source locator `/data/78` | | | | | | | | [ARC-AGI-2](https://benchize.com/benchmarks/arc-prize%3Av2_Semi_Private.md) | 29.17% | — | 124 / 243 | 0.27usd per task | [arc prize · v2](https://arcprize.org/media/data/leaderboard/v2.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `score` \| 0.2917 \| score_fraction \| v2_Semi_Private \| Higher is better \| \| `cost_per_task` \| 0.27 \| usd_per_task \| v2_Semi_Private \| Lower is better \| ### Configuration evaluationSplit v2_Semi_Private harness Not reported modelGroup gpt-5-4 modelType CoT Reasoning effort low sourceModelVersion gpt-5-4-low thinkingEnabled true ### Source [Original source](https://arcprize.org/media/data/leaderboard/v2.json) Source arc prize Original model label GPT-5.4 (Low) Source version v2 Observed 2026-10-22T05:20:04.306Z Evidence SHA-256 `4351eb696e78113b0459e9bb5f0258318b905efef34f473dcea51ce641b0d94d` Source locator `/evaluations/130` | | | | | | | | [DesignArena ASCII art generation](https://benchize.com/benchmarks/designarena%3Aascii.md) | 1,188elo | — | 27 / 65 | — | [designarena · public](https://www.designarena.ai/api/leaderboard#board=ascii) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `elo` \| 1188 \| elo \| ascii \| Higher is better \| ### Configuration arenaType models category ascii inputModality Not reported Reasoning effort low sourceModelVersion gpt-5.4-low thinkingEnabled true variationName public ### Reported statistics averageGenerationTimeMs 34395 battles 703 losses 334 standardError Not reported winRate 52.5 wins 369 ### Source [Original source](https://www.designarena.ai/api/leaderboard#board=ascii) Source designarena Original model label GPT-5.4 (Low) Source version public Observed 2026-10-21T16:38:03.513Z Evidence SHA-256 `0603b8c65b44ee887f5b566feb469465f59635137a6ac5c6d94c23bcf3776311` Source locator `/data/37` | | | | | | | | [ARC-AGI-1](https://benchize.com/benchmarks/arc-prize%3Av1_Semi_Private.md) | 68.17% | — | 136 / 245 | 0.15usd per task | [arc prize · v1](https://arcprize.org/media/data/leaderboard/v1.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `score` \| 0.6817 \| score_fraction \| v1_Semi_Private \| Higher is better \| \| `cost_per_task` \| 0.15 \| usd_per_task \| v1_Semi_Private \| Lower is better \| ### Configuration evaluationSplit v1_Semi_Private harness Not reported modelGroup gpt-5-4 modelType CoT Reasoning effort low sourceModelVersion gpt-5-4-low thinkingEnabled true ### Source [Original source](https://arcprize.org/media/data/leaderboard/v1.json) Source arc prize Original model label GPT-5.4 (Low) Source version v1 Observed 2026-10-22T05:20:04.066Z Evidence SHA-256 `2bf68d22dafba37047d07ad833ebc0e8199c9aa2f9eeaed50c75c1b704462836` Source locator `/evaluations/129` | | | | | | | --- Cite as: GPT-5.4Low — Benchize, https://benchize.com/models/gpt-5-4-low (retrieved 2026-10-22)