# GPT-5.3 Codex > Source: Benchize (https://benchize.com) — https://benchize.com/models/gpt-5-3-codex. When citing or reusing this content, credit "Benchize" and link to https://benchize.com/models/gpt-5-3-codex. OpenAI Canonical URL: https://benchize.com/models/gpt-5-3-codex 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 SVG generation](https://benchize.com/benchmarks/designarena%3Asvgs.md) | 1,129elo | — | 48 / 77 | — | [designarena · public](https://www.designarena.ai/api/leaderboard#board=svgs) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `elo` \| 1129 \| elo \| svgs \| Higher is better \| ### Configuration arenaType models category svg inputModality Not reported sourceModelVersion gpt-5.3-codex variationName public ### Reported statistics averageGenerationTimeMs 17590 battles 3026 losses 1392 standardError Not reported winRate 54 wins 1634 ### Source [Original source](https://www.designarena.ai/api/leaderboard#board=svgs) Source designarena Original model label GPT-5.3 Codex Source version public Observed 2026-10-21T16:38:03.249Z Evidence SHA-256 `8cbc34a474a66ef5c64f3ffe557df9b55bf7e13368c07c0214223e3ed8f3f21e` Source locator `/data/78` | | | | | | | | [Vending-Bench 2](https://benchize.com/benchmarks/vendingbench%3Av2.md) | — | — | — | $5,940.12 | [vendingbench](https://andonlabs.com/_app/immutable/chunks/Cjn0_qj9.js) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `final_balance` \| 5940.124000000002 \| USD \| one_simulated_year \| Higher is better \| \| `geometric_mean_balance` \| 5711.741277241385 \| USD \| positive_final_balances \| Higher is better \| ### Configuration Reasoning effort unknown Model configuration GPT-5.3-Codex thinkingEnabled Not reported ### Reported statistics confidenceHalfWidth95 1560.1183339384527 positiveBalanceRuns 5 runCount 5 standardDeviation 1779.8625753214783 standardError 795.978741805333 ### Source [Original source](https://andonlabs.com/_app/immutable/chunks/Cjn0_qj9.js) Source vendingbench Original model label GPT-5.3-Codex Observed 2026-10-21T16:36:40.592Z Evidence SHA-256 `1a0b043147050298c405bcb743d73e425d532464202231cd18c27f836fa5f223` Source locator `/rows/29` | | | | | | | | [HiL-Bench (Human-in-Loop Benchmark)](https://benchize.com/benchmarks/scale%3Ahil.md) | 4.33source score | CI 1.39–7.27 | 22 / 22 | — | [scale](https://labs.scale.com/leaderboard/hil) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `score` \| 4.33 \| source_score \| reported \| Higher is better \| ### Configuration Reasoning effort unknown Model configuration GPT 5.3 Codex sourceModelVersion Not reported thinkingEnabled Not reported ### Reported statistics Uncertainty Confidence interval: 1.39–7.27 contaminationWarning Not reported rank 30 reportedConfidenceHalfWidth 2.94 ### Source [Original source](https://labs.scale.com/leaderboard/hil) Source scale Original model label GPT 5.3 Codex Observed 2026-10-22T03:30:07.512Z Evidence SHA-256 `fb954dc9c4a01e066526b773b8a269f2c27e73cfb0f1a943ec328ecd5be154c1` Source locator `/rows/29` | | | | | | | | [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 sourceModelVersion gpt-5.3-codex variationName public ### Reported statistics averageGenerationTimeMs 24046 battles 258 losses 126 standardError Not reported winRate 51.2 wins 132 ### Source [Original source](https://www.designarena.ai/api/leaderboard#board=ascii) Source designarena Original model label GPT-5.3 Codex Source version public Observed 2026-10-21T16:38:03.513Z Evidence SHA-256 `0603b8c65b44ee887f5b566feb469465f59635137a6ac5c6d94c23bcf3776311` Source locator `/data/51` | | | | | | | | [SVGBench Arena](https://benchize.com/benchmarks/svgbench%3Aarena.md) | 1,668 | — | 12 / 191 | — | [svgbench](https://svgbench.ai/api/leaderboard?shape=2) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1668 \| rating \| reported \| Higher is better \| ### Configuration Reasoning effort unknown sourceModelId model_openai_gpt_5_3_codex ### Reported statistics coverageCount 27 draws 24 judged 611 losses 293 rank 17 ratingDeviation 28 wins 294 ### Source [Original source](https://svgbench.ai/api/leaderboard?shape=2) Source svgbench Original model label GPT-5.3-Codex Observed 2026-10-22T04:30:04.538Z Evidence SHA-256 `5c0a9c869593820d57d2c05f6d416e1b44a740b4835e66c66e9ad8b8edc59e2c` Source locator `/rows/16` | | | | | | | | [DesignArena Mobile application development](https://benchize.com/benchmarks/designarena%3Amobileapps.md) | 1,053elo | SE ±12.02 | 33 / 33 | — | [designarena · public](https://www.designarena.ai/api/leaderboard#board=mobileapps) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `elo` \| 1053 \| elo \| mobileapps \| Higher is better \| ### Configuration arenaType agents category mobileapps inputModality Not reported sourceModelVersion gpt-5.3-codex variationName public ### Reported statistics Uncertainty Standard error: ±12.02 averageGenerationTimeMs Not reported battles 955 losses 560 standardError 12.0188 winRate 41.4 wins 395 ### Source [Original source](https://www.designarena.ai/api/leaderboard#board=mobileapps) Source designarena Original model label GPT-5.3 Codex Source version public Observed 2026-10-21T16:38:02.538Z Evidence SHA-256 `40af33d0e93e729486da375cbe954633e2458af0dd6ca6d9fbdcda90da650f7d` Source locator `/data/51` | | | | | | | | [DesignArena UI component generation](https://benchize.com/benchmarks/designarena%3Aui-components.md) | 1,137elo | — | 79 / 112 | — | [designarena · public](https://www.designarena.ai/api/leaderboard#board=ui-components) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `elo` \| 1137 \| elo \| ui-components \| Higher is better \| ### Configuration arenaType models category uicomponent inputModality Not reported sourceModelVersion gpt-5.3-codex variationName public ### Reported statistics averageGenerationTimeMs 36215 battles 1051 losses 554 standardError Not reported winRate 47.3 wins 497 ### Source [Original source](https://www.designarena.ai/api/leaderboard#board=ui-components) Source designarena Original model label GPT-5.3 Codex Source version public Observed 2026-10-21T16:37:57.993Z Evidence SHA-256 `46482ec1b4012638eace65493daea4750e2088098018fd9d5fc46126fc1f8557` Source locator `/data/116` | | | | | | | | [DesignArena Full-stack application development](https://benchize.com/benchmarks/designarena%3Afullstack.md) | 983elo | SE ±11.32 | 31 / 31 | — | [designarena · public](https://www.designarena.ai/api/leaderboard#board=fullstack) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `elo` \| 983 \| elo \| fullstack \| Higher is better \| ### Configuration arenaType agents category fullstack inputModality Not reported sourceModelVersion gpt-5.3-codex variationName public ### Reported statistics Uncertainty Standard error: ±11.32 averageGenerationTimeMs Not reported battles 1110 losses 705 standardError 11.3238 winRate 36.5 wins 405 ### Source [Original source](https://www.designarena.ai/api/leaderboard#board=fullstack) Source designarena Original model label GPT-5.3 Codex Source version public Observed 2026-10-21T16:38:00.857Z Evidence SHA-256 `aa171459dd44cfad57fba8da746c40b27832b57dc731b1198bdb71c73ddd0f97` Source locator `/data/48` | | | | | | | | [FinanceBenchmark v2](https://benchize.com/benchmarks/financebenchmark%3Av2.md) | 65.85% | CI 54.88–75.61% | 18 / 21 | — | [financebenchmark](https://finbenchmark.ai/) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `pass_at_1` \| 0.658537 \| score_fraction \| reported \| Higher is better \| \| `accuracy` \| 0.67094 \| score_fraction \| reported \| Higher is better \| \| `knowledge` \| 1 \| score_fraction \| category \| Higher is better \| \| `analysis` \| 1 \| score_fraction \| category \| Higher is better \| \| `quant` \| 0.55 \| score_fraction \| category \| Higher is better \| \| `portfolio_mgmt` \| 0.5 \| score_fraction \| category \| Higher is better \| \| `credit_underwriting` \| 0.333333 \| score_fraction \| category \| Higher is better \| \| `banking_regulation` \| 0.2 \| score_fraction \| category \| Higher is better \| \| `derivatives_structuring` \| 0.833333 \| score_fraction \| category \| Higher is better \| \| `corporate_finance` \| 0.4 \| score_fraction \| category \| Higher is better \| ### Configuration harnessVersion 0.2.0 Reasoning effort unknown sourceRunId 3449f0a0-6ebf-4878-b53d-9f3af9672648 taskSetVersion v2 ### Reported statistics Uncertainty Confidence interval: 54.88–75.61% confidenceInterval [0.5488,0.7561] confidenceMethod percentile bootstrap over tasks, n=5000, alpha=0.05 sampleSize 82 ### Source [Original source](https://finbenchmark.ai/) Source financebenchmark Original model label gpt-5.3-codex Evaluated 2026-07-15T21:13:00.61605+00:00 Observed 2026-10-22T04:10:04.512Z Evidence SHA-256 `f9e7dab8846b092fc0befeca8c5cd02a8187c0f5b6b10c32ab2c7ab60f7af575` Source locator `/rows/22` | | | | | | | | [DesignArena Website generation](https://benchize.com/benchmarks/designarena%3Awebsite.md) | 1,163elo | — | 80 / 123 | — | [designarena · public](https://www.designarena.ai/api/leaderboard#board=website) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `elo` \| 1163 \| elo \| website \| Higher is better \| ### Configuration arenaType models category website inputModality text sourceModelVersion gpt-5.3-codex variationName public ### Reported statistics averageGenerationTimeMs 52340 battles 8724 losses 4482 standardError Not reported winRate 48.6 wins 4242 ### Source [Original source](https://www.designarena.ai/api/leaderboard#board=website) Source designarena Original model label GPT-5.3 Codex Source version public Observed 2026-10-21T16:37:57.757Z Evidence SHA-256 `51873e97776a3c5ae706b24cc2c60384793dd18398df970e213a8e7c276d8ac0` Source locator `/data/116` | | | | | | | | [DesignArena 3D design generation](https://benchize.com/benchmarks/designarena%3A3d-design.md) | 1,008elo | — | 93 / 110 | — | [designarena · public](https://www.designarena.ai/api/leaderboard#board=3d-design) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `elo` \| 1008 \| elo \| 3d-design \| Higher is better \| ### Configuration arenaType models category 3d inputModality Not reported sourceModelVersion gpt-5.3-codex variationName public ### Reported statistics averageGenerationTimeMs 45992 battles 2219 losses 1436 standardError Not reported winRate 35.3 wins 783 ### Source [Original source](https://www.designarena.ai/api/leaderboard#board=3d-design) Source designarena Original model label GPT-5.3 Codex Source version public Observed 2026-10-21T16:37:58.515Z Evidence SHA-256 `bcc0267f7bc7e9ec112306b3a35413cf78bbccbfaa838356232d5d5ed0b83d0f` Source locator `/data/146` | | | | | | | | [Long-Horizon Terminal-Bench](https://benchize.com/benchmarks/lhtb%3Aoverall.md) | 21.5% | — | 18 / 19 | $8.2 | [lhtb](https://zli12321.github.io/LHTB/script.js) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `mean_reward` \| 0.215 \| score_fraction \| reported \| Higher is better \| \| `solved_count` \| 2 \| tasks \| reward_gte_0_95 \| Higher is better \| \| `cost_per_task` \| 8.2 \| USD \| per_task \| Lower is better \| ### Configuration harness official_common_harness Reasoning effort unknown reportOrigin paper ### Reported statistics sampleSize 46 sourceThresholdCounts Not reported ### Source [Original source](https://zli12321.github.io/LHTB/script.js) Source lhtb Original model label GPT-5.3 Codex Observed 2026-10-22T05:00:05.057Z Evidence SHA-256 `8b9c27664cc6298fa234c607ca27c953ec91b2eb9d116b8530cfaaa6722fa39e` Source locator `/rows/19` | | | | | | | | [DesignArena Agentic web applications](https://benchize.com/benchmarks/designarena%3Awebapps.md) | 1,032elo | SE ±8.07 | 38 / 39 | — | [designarena · public](https://www.designarena.ai/api/leaderboard#board=webapps) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `elo` \| 1032 \| elo \| webapps \| Higher is better \| ### Configuration arenaType agents category agon_webapps inputModality text sourceModelVersion gpt-5.3-codex variationName public ### Reported statistics Uncertainty Standard error: ±8.07 averageGenerationTimeMs Not reported battles 2245 losses 1416 standardError 8.0654 winRate 36.9 wins 829 ### Source [Original source](https://www.designarena.ai/api/leaderboard#board=webapps) Source designarena Original model label GPT-5.3 Codex Source version public Observed 2026-10-21T16:38:00.309Z Evidence SHA-256 `f955787274cf4ac627ada7cd33eaae2e08ef7297db92d3391340fcaa0b44a35f` Source locator `/data/50` | | | | | | | | [DesignArena Overall frontend coding](https://benchize.com/benchmarks/designarena%3Acode.md) | 1,145elo | SE ±2.92 | 81 / 116 | — | [designarena · public](https://www.designarena.ai/api/leaderboard#board=code) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `elo` \| 1145 \| elo \| code \| Higher is better \| ### Configuration arenaType models category allcategories inputModality text sourceModelVersion gpt-5.3-codex variationName public ### Reported statistics Uncertainty Standard error: ±2.92 averageGenerationTimeMs 52370 battles 15677 losses 8272 standardError 2.9155 winRate 47.2 wins 7405 ### Source [Original source](https://www.designarena.ai/api/leaderboard#board=code) Source designarena Original model label GPT-5.3 Codex Source version public Observed 2026-10-21T16:37:57.301Z Evidence SHA-256 `0c897b58670f5e352bd123db999a40c0d1781a443964c502b90774a76a3a7758` Source locator `/data/117` | | | | | | | | [DesignArena Browser game generation](https://benchize.com/benchmarks/designarena%3Agame-dev.md) | 1,161elo | — | 64 / 117 | — | [designarena · public](https://www.designarena.ai/api/leaderboard#board=game-dev) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `elo` \| 1161 \| elo \| game-dev \| Higher is better \| ### Configuration arenaType models category gamedev inputModality Not reported sourceModelVersion gpt-5.3-codex variationName public ### Reported statistics averageGenerationTimeMs 65135 battles 2963 losses 1444 standardError Not reported winRate 51.3 wins 1519 ### Source [Original source](https://www.designarena.ai/api/leaderboard#board=game-dev) Source designarena Original model label GPT-5.3 Codex Source version public Observed 2026-10-21T16:38:01.100Z Evidence SHA-256 `53db6a89112ce8cdf644568c666d4b8309aece764cfcedb291ffd52ae3934e30` Source locator `/data/97` | | | | | | | | [DesignArena Data visualization generation](https://benchize.com/benchmarks/designarena%3Adata-viz.md) | 1,164elo | — | 67 / 99 | — | [designarena · public](https://www.designarena.ai/api/leaderboard#board=data-viz) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `elo` \| 1164 \| elo \| data-viz \| Higher is better \| ### Configuration arenaType models category dataviz inputModality Not reported sourceModelVersion gpt-5.3-codex variationName public ### Reported statistics averageGenerationTimeMs 43451 battles 720 losses 356 standardError Not reported winRate 50.6 wins 364 ### Source [Original source](https://www.designarena.ai/api/leaderboard#board=data-viz) Source designarena Original model label GPT-5.3 Codex Source version public Observed 2026-10-21T16:37:58.264Z Evidence SHA-256 `a895f6f1a25fa8eb01f821c2097ddec4f884de7bd22f1b8a22e82e6679b71849` Source locator `/data/96` | | | | | | | --- Cite as: GPT-5.3 Codex — Benchize, https://benchize.com/models/gpt-5-3-codex (retrieved 2026-10-22)