# GPT-5.4

> Source: Benchize (https://benchize.com) — https://benchize.com/models/gpt-5-4. When citing or reusing this content, credit "Benchize" and link to https://benchize.com/models/gpt-5-4.

OpenAI

Canonical URL: https://benchize.com/models/gpt-5-4
Last updated: Thu, 22 Oct 2026 07:10:12 GMT

Reproduction and quotation must name Benchize, link to the canonical HTML URL, and retain individual source citations.

OpenAI

## Benchmarks

| Benchmark | Score | ± | Rank | Cost | Latency | Source |  |
| --- | --- | --- | --- | --- | --- | --- | --- |
| [Vending-Bench 2](https://benchize.com/benchmarks/vendingbench%3Av2.md) | — | — | — | $6,144.18 | — | [vendingbench](https://andonlabs.com/_app/immutable/chunks/Cjn0_qj9.js) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `final_balance` \| 6144.176 \| USD \| one_simulated_year \| Higher is better \| \| `geometric_mean_balance` \| 5795.766108948811 \| USD \| positive_final_balances \| Higher is better \| ### Configuration Reasoning effort unknown Model configuration GPT-5.4 thinkingEnabled Not reported ### Reported statistics confidenceHalfWidth95 1707.3534403159324 positiveBalanceRuns 5 runCount 5 standardDeviation 1947.835894981916 standardError 871.0986940387411 ### Source [Original source](https://andonlabs.com/_app/immutable/chunks/Cjn0_qj9.js) Source vendingbench Original model label GPT-5.4 Observed 2026-10-21T16:36:40.592Z Evidence SHA-256 `1a0b043147050298c405bcb743d73e425d532464202231cd18c27f836fa5f223` Source locator `/rows/30` |  |  |  |  |  |  |  |
| [Long-Horizon Terminal-Bench](https://benchize.com/benchmarks/lhtb%3Aoverall.md) | 27.2% | — | 15 / 19 | $27.57 | — | [lhtb](https://zli12321.github.io/LHTB/script.js) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `mean_reward` \| 0.272 \| score_fraction \| reported \| Higher is better \| \| `solved_count` \| 1 \| tasks \| reward_gte_0_95 \| Higher is better \| \| `cost_per_task` \| 27.57 \| 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-5.4 Observed 2026-10-22T05:00:05.057Z Evidence SHA-256 `8b9c27664cc6298fa234c607ca27c953ec91b2eb9d116b8530cfaaa6722fa39e` Source locator `/rows/16` |  |  |  |  |  |  |  |
| [Arena vision style control / english](https://benchize.com/benchmarks/lmarena%3Avision_style_control%3Aenglish.md) | 1,277.21 | — | 23 / 92 | — | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/vision_style_control/latest) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1277.2069981240597 \| rating \| reported \| Higher is better \| ### Configuration category english config vision_style_control ### Reported statistics lower 1268.3755052115055 rank 27 upper 1286.038491036614 variance 20.303554119683326 votes 9595 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/vision_style_control/latest) Source Arena Original model label GPT-5.4 Observed 2026-10-22T06:45:03.380Z Evidence SHA-256 `38568936995f36625aae49e9ea05557d55c1b1df9b2954f5c50cee523f26fe92` Source locator `/rows/616/row` |  |  |  |  |  |  |  |
| [Vibe Code Bench v1.1 / overall](https://benchize.com/benchmarks/vals-ai%3Avibe-code%3Aoverall.md) | 48.47% | SE ±5.07 pp | 40 / 59 | $7.51 | 1,075.4source duration | [Vals AI · 1.1](https://www.vals.ai/_astro/benchmark_view_vibe_code_bench.DcEBMbCA.json) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 48.474 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 7.50518 \| USD \| per_test \| Lower is better \| \| `latency` \| 1075.396 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Codex maxOutputTokens Not reported provider OpenAI reasoning Not reported Reasoning effort unknown Temperature Not reported topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±5.07 pp sourcePopulation 116 stderr 5.07 tokenTotals {"cache_read_tokens":410377472,"cache_write_tokens":null,"input_tokens":428145333,"output_tokens":3610264,"reasoning_tokens":934026} ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_vibe_code_bench.DcEBMbCA.json) Source Vals AI Original model label openai/gpt-5.4 Source version 1.1 Observed 2026-10-22T02:10:23.531Z Evidence SHA-256 `0e8c23f521a0f751c5592952620e197b376cade41c78578461b7aa5740a173e7` Source locator `/tasks/overall/openai~1gpt-5.4` |  |  |  |  |  |  |  |
| [Arena text style control / industry software and it services](https://benchize.com/benchmarks/lmarena%3Atext_style_control%3Aindustry_software_and_it_services.md) | 1,498.61 | — | 47 / 173 | — | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1498.6089987910907 \| rating \| reported \| Higher is better \| ### Configuration category industry_software_and_it_services config text_style_control ### Reported statistics lower 1493.4763823555024 rank 60 upper 1503.7416152266792 variance 6.857746680234419 votes 26970 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label GPT-5.4 Observed 2026-10-22T06:45:03.380Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/6760/row` |  |  |  |  |  |  |  |
| [OfficeQA Pro — Agent Harness](https://benchize.com/benchmarks/officeqa-pro%3Aagent.md) | 41.4% | — | 8 / 13 | — | — | [officeqa pro · sha256:07c23a70c189c84ab808067929402d3b636ce81e46520faca981a178e02065ad](https://api.github.com/repos/databricks/officeqa/git/blobs/125bf765bb37397a7a6b41a49ea04e6117eb95b8) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `correctness` \| 41.4 \| percent \| agent_full_tools \| Higher is better \| ### Configuration harness Codex SDK ### Reported statistics sampleSize 133 ### Source [Original source](https://api.github.com/repos/databricks/officeqa/git/blobs/125bf765bb37397a7a6b41a49ea04e6117eb95b8) Source officeqa pro Original model label GPT-5.4 Source version sha256:07c23a70c189c84ab808067929402d3b636ce81e46520faca981a178e02065ad Observed 2026-10-22T07:00:05.158Z Evidence SHA-256 `094af719408a1dea8ccb110965da3cc1b83056de87ba0b95e99bf603955f42b1` Source locator `/chart-labels/4` |  |  |  |  |  |  |  |
| [Creative Writing v3](https://benchize.com/benchmarks/eq-bench%3Acreative-writing-v3.md) | 1,839.7elo | — | 20 / 90 | — | — | [eq bench · creative-writing-v3](https://eqbench.com/creative_writing.js) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `elo_score` \| 1839.7 \| elo \| overall \| Higher is better \| \| `creative_writing_score` \| 16.89 \| rubric_score \| overall \| Higher is better \| ### Configuration interactiveAdjustments none protocol creative-writing-v3 sourceModelVersion gpt-5.4 ### Source [Original source](https://eqbench.com/creative_writing.js) Source eq bench Original model label gpt-5.4 Source version creative-writing-v3 Observed 2026-10-22T05:10:05.433Z Evidence SHA-256 `722ddb132e8d3a5e5c39b8d445f8475f3f7e24893a007260c6f3e3cce5c1ee18` Source locator `/leaderboardDataCreativeWritingV3/21` |  |  |  |  |  |  |  |
| [AutomationBench](https://benchize.com/benchmarks/zapier%3Aautomationbench.md) | 0.15% | — | 110 / 113 | $0.07 | — | [zapier](https://framerusercontent.com/sites/4WTSl4BNjd1q9QFEFibC6h/lOvLnhItj8S8-1vyjH_s33Jn-WmUXPmiJ5Diajl0Q38.CMutaHYl.mjs) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `score` \| 0.15 \| percent \| reported \| Higher is better \| \| `cost` \| 0.07 \| USD \| per_task \| Lower is better \| ### Configuration benchmarkVersion 1.0.6 costFootnote false Fallback policy Not reported Reasoning effort unknown Model configuration GPT-5.4 thinkingEnabled Not reported ### Reported statistics rank 125 ### Source [Original source](https://framerusercontent.com/sites/4WTSl4BNjd1q9QFEFibC6h/lOvLnhItj8S8-1vyjH_s33Jn-WmUXPmiJ5Diajl0Q38.CMutaHYl.mjs) Source zapier Original model label GPT-5.4 Observed 2026-10-21T16:34:56.783Z Evidence SHA-256 `43978e38f018789fa59c11de5328abe9e5905bfa9a5a4d601fa3aa4d9c153b0d` Source locator `/rows/124` |  |  |  |  |  |  |  |
| [Longform Creative Writing](https://benchize.com/benchmarks/eq-bench%3Alongform-writing.md) | 78.3% | — | 18 / 93 | — | — | [eq bench · longform-writing](https://eqbench.com/creative_writing_longform.js) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `overall_score_100` \| 78.3 \| percent \| overall \| Higher is better \| \| `chapter1_avg` \| 16.44 \| rubric_score \| overall \| Higher is better \| \| `chapter2_avg` \| 16.47 \| rubric_score \| overall \| Higher is better \| \| `chapter3_avg` \| 15.84 \| rubric_score \| overall \| Higher is better \| \| `chapter4_avg` \| 15.93 \| rubric_score \| overall \| Higher is better \| \| `chapter5_avg` \| 16.32 \| rubric_score \| overall \| Higher is better \| \| `chapter6_avg` \| 16.23 \| rubric_score \| overall \| Higher is better \| \| `chapter7_avg` \| 16.02 \| rubric_score \| overall \| Higher is better \| \| `chapter8_avg` \| 16.17 \| rubric_score \| overall \| Higher is better \| \| `final_judgement_avg` \| 15.85 \| rubric_score \| overall \| Higher is better \| ### Configuration interactiveAdjustments none protocol longform-writing sourceModelVersion gpt-5.4 ### Source [Original source](https://eqbench.com/creative_writing_longform.js) Source eq bench Original model label gpt-5.4 Source version longform-writing Observed 2026-10-22T05:10:05.903Z Evidence SHA-256 `3ba283ce357ac7620e16db640a961879c30fe3ddc50a27de9a8ed4290784825c` Source locator `/leaderboardDataLongformV3/95` |  |  |  |  |  |  |  |
| [HiL-Bench (Human-in-Loop Benchmark)](https://benchize.com/benchmarks/scale%3Ahil.md) | 9.67source score | CI 5.8–13.54 | 20 / 22 | — | — | [scale](https://labs.scale.com/leaderboard/hil) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `score` \| 9.67 \| source_score \| reported \| Higher is better \| ### Configuration Reasoning effort unknown Model configuration GPT 5.4 sourceModelVersion Not reported thinkingEnabled Not reported ### Reported statistics Uncertainty Confidence interval: 5.8–13.54 contaminationWarning Not reported rank 28 reportedConfidenceHalfWidth 3.87 ### Source [Original source](https://labs.scale.com/leaderboard/hil) Source scale Original model label GPT 5.4 Observed 2026-10-22T03:30:07.512Z Evidence SHA-256 `fb954dc9c4a01e066526b773b8a269f2c27e73cfb0f1a943ec328ecd5be154c1` Source locator `/rows/27` |  |  |  |  |  |  |  |
| [Arena vision / ocr (config: vision)](https://benchize.com/benchmarks/benchmark%3Avision%3Aocr--config-vision.md) | 1,299.2 | — | 26 / 84 | — | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/vision/latest) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1299.1982985333382 \| rating \| reported \| Higher is better \| ### Configuration category ocr config vision ### Reported statistics lower 1292.6271604606777 rank 27 upper 1305.7694366059986 variance 11.240483781149749 votes 16434 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/vision/latest) Source Arena Original model label GPT-5.4 Observed 2026-10-22T06:45:03.380Z Evidence SHA-256 `06e61305486dce3fec5dc776ac2fd8321104e84c346cf9e08fa6f8e8a66ce0d7` Source locator `/rows/1045/row` |  |  |  |  |  |  |  |
| [Arena text style control / english](https://benchize.com/benchmarks/lmarena%3Atext_style_control%3Aenglish.md) | 1,467.95 | — | 50 / 173 | — | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1467.9463616643543 \| rating \| reported \| Higher is better \| ### Configuration category english config text_style_control ### Reported statistics lower 1463.0526232118007 rank 64 upper 1472.8401001169082 variance 6.234265980671434 votes 30857 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label GPT-5.4 Observed 2026-10-22T06:45:03.380Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/1700/row` |  |  |  |  |  |  |  |
| [FinanceBenchmark v2](https://benchize.com/benchmarks/financebenchmark%3Av2.md) | 63.01% | CI 52.05–73.97% | 19 / 21 | — | — | [financebenchmark](https://finbenchmark.ai/) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `pass_at_1` \| 0.630137 \| score_fraction \| reported \| Higher is better \| \| `accuracy` \| 0.621005 \| score_fraction \| reported \| Higher is better \| \| `knowledge` \| 1 \| score_fraction \| category \| Higher is better \| \| `analysis` \| 0.933333 \| score_fraction \| category \| Higher is better \| \| `quant` \| 0.333333 \| 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` \| 0.4 \| score_fraction \| category \| Higher is better \| \| `derivatives_structuring` \| 0.666667 \| score_fraction \| category \| Higher is better \| \| `corporate_finance` \| 0.2 \| score_fraction \| category \| Higher is better \| ### Configuration harnessVersion 0.1.0 Reasoning effort unknown sourceRunId 409d4e79-d03a-42c9-a4f1-51f3b9e5fff8 taskSetVersion v2 ### Reported statistics Uncertainty Confidence interval: 52.05–73.97% confidenceInterval [0.5205,0.7397] confidenceMethod percentile bootstrap over tasks, n=5000, alpha=0.05 sampleSize 73 ### Source [Original source](https://finbenchmark.ai/) Source financebenchmark Original model label gpt-5.4 Evaluated 2026-06-15T07:25:03.104929+00:00 Observed 2026-10-22T04:10:04.512Z Evidence SHA-256 `f9e7dab8846b092fc0befeca8c5cd02a8187c0f5b6b10c32ab2c7ab60f7af575` Source locator `/rows/23` |  |  |  |  |  |  |  |
| [DesignArena Native Android development](https://benchize.com/benchmarks/designarena%3Aandroid.md) | 1,038elo | — | 23 / 23 | — | — | [designarena · public](https://www.designarena.ai/api/leaderboard#board=android) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `elo` \| 1038 \| elo \| android \| Higher is better \| ### Configuration arenaType agents category nativeapps inputModality Not reported sourceModelVersion gpt-5.4 variationName public ### Reported statistics averageGenerationTimeMs Not reported battles 502 losses 264 standardError Not reported winRate 47.4 wins 238 ### Source [Original source](https://www.designarena.ai/api/leaderboard#board=android) Source designarena Original model label GPT-5.4 Source version public Observed 2026-10-21T16:38:03.000Z Evidence SHA-256 `d9d0cd4bea54b696c28f907a98ba42ebf8dd4da9da201b6c70c95f76de35f525` Source locator `/data/36` |  |  |  |  |  |  |  |
| [Arena text style control / german](https://benchize.com/benchmarks/lmarena%3Atext_style_control%3Agerman.md) | 1,449.53 | — | 53 / 149 | — | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1449.5273979624649 \| rating \| reported \| Higher is better \| ### Configuration category german config text_style_control ### Reported statistics lower 1429.794442600941 rank 73 upper 1469.2603533239887 variance 101.36501404160173 votes 1000 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label GPT-5.4 Observed 2026-10-22T06:45:03.380Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/3209/row` |  |  |  |  |  |  |  |
| [Arena text style control / polish](https://benchize.com/benchmarks/lmarena%3Atext_style_control%3Apolish.md) | 1,472.04 | — | 31 / 137 | — | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1472.0384851604963 \| rating \| reported \| Higher is better \| ### Configuration category polish config text_style_control ### Reported statistics lower 1455.258510696108 rank 41 upper 1488.8184596248843 variance 73.29703536289408 votes 1302 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label GPT-5.4 Observed 2026-10-22T06:45:03.380Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/10188/row` |  |  |  |  |  |  |  |
| [DesignArena Mobile application development](https://benchize.com/benchmarks/designarena%3Amobileapps.md) | 1,087elo | SE ±8.86 | 32 / 33 | — | — | [designarena · public](https://www.designarena.ai/api/leaderboard#board=mobileapps) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `elo` \| 1087 \| elo \| mobileapps \| Higher is better \| ### Configuration arenaType agents category mobileapps inputModality Not reported sourceModelVersion gpt-5.4 variationName public ### Reported statistics Uncertainty Standard error: ±8.86 averageGenerationTimeMs Not reported battles 1929 losses 1040 standardError 8.8645 winRate 46.1 wins 889 ### Source [Original source](https://www.designarena.ai/api/leaderboard#board=mobileapps) Source designarena Original model label GPT-5.4 Source version public Observed 2026-10-21T16:38:02.538Z Evidence SHA-256 `40af33d0e93e729486da375cbe954633e2458af0dd6ca6d9fbdcda90da650f7d` Source locator `/data/48` |  |  |  |  |  |  |  |
| [Arena text style control / industry mathematical](https://benchize.com/benchmarks/lmarena%3Atext_style_control%3Aindustry_mathematical.md) | 1,470.91 | — | 54 / 169 | — | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1470.9083419135027 \| rating \| reported \| Higher is better \| ### Configuration category industry_mathematical config text_style_control ### Reported statistics lower 1460.5128011444044 rank 60 upper 1481.3038826826005 variance 28.131830360855904 votes 3736 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label GPT-5.4 Observed 2026-10-22T06:45:03.380Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/5972/row` |  |  |  |  |  |  |  |
| [Arena webdev / webdev-react](https://benchize.com/benchmarks/lmarena%3Awebdev%3Awebdev-react.md) | 1,388.36 | — | 69 / 97 | — | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/webdev/latest) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1388.3581471124426 \| rating \| reported \| Higher is better \| ### Configuration category webdev-react config webdev ### Reported statistics lower 1375.7350376872885 rank 93 upper 1400.981256537597 variance 41.479786455351366 votes 2805 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/webdev/latest) Source Arena Original model label GPT-5.4 Observed 2026-10-22T06:45:03.380Z Evidence SHA-256 `f82507859808110820a4ab6df15561b8864137ddefc1f6fb0c552af2e58ea738` Source locator `/rows/599/row` |  |  |  |  |  |  |  |
| [Arena text / spanish](https://benchize.com/benchmarks/lmarena%3Atext%3Aspanish.md) | 1,452.32 | — | 44 / 155 | — | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1452.3198610472168 \| rating \| reported \| Higher is better \| ### Configuration category spanish config text ### Reported statistics lower 1438.1530826266685 rank 56 upper 1466.4866394677651 variance 52.24515481872292 votes 2036 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) Source Arena Original model label GPT-5.4 Observed 2026-10-22T06:45:03.380Z Evidence SHA-256 `8e027ef69b8de06c4b2a8b217bfe816b1f1536269bb257fd295b4ef1ba8246ac` Source locator `/rows/10820/row` |  |  |  |  |  |  |  |
| [DesignArena Full-stack application development](https://benchize.com/benchmarks/designarena%3Afullstack.md) | 1,017elo | SE ±8.33 | 29 / 31 | — | — | [designarena · public](https://www.designarena.ai/api/leaderboard#board=fullstack) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `elo` \| 1017 \| elo \| fullstack \| Higher is better \| ### Configuration arenaType agents category fullstack inputModality Not reported sourceModelVersion gpt-5.4 variationName public ### Reported statistics Uncertainty Standard error: ±8.33 averageGenerationTimeMs Not reported battles 2152 losses 1273 standardError 8.3275 winRate 40.9 wins 879 ### Source [Original source](https://www.designarena.ai/api/leaderboard#board=fullstack) Source designarena Original model label GPT-5.4 Source version public Observed 2026-10-21T16:38:00.857Z Evidence SHA-256 `aa171459dd44cfad57fba8da746c40b27832b57dc731b1198bdb71c73ddd0f97` Source locator `/data/44` |  |  |  |  |  |  |  |
| [Arena text / instruction following](https://benchize.com/benchmarks/lmarena%3Atext%3Ainstruction_following.md) | 1,454.68 | — | 41 / 173 | — | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1454.6795101249566 \| rating \| reported \| Higher is better \| ### Configuration category instruction_following config text ### Reported statistics lower 1449.3348810862853 rank 48 upper 1460.024139163628 variance 7.435992651314607 votes 23383 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) Source Arena Original model label GPT-5.4 Observed 2026-10-22T06:45:03.380Z Evidence SHA-256 `8e027ef69b8de06c4b2a8b217bfe816b1f1536269bb257fd295b4ef1ba8246ac` Source locator `/rows/7581/row` |  |  |  |  |  |  |  |
| [Arena text style control / industry entertainment and sports and media](https://benchize.com/benchmarks/lmarena%3Atext_style_control%3Aindustry_entertainment_and_sports_and_media.md) | 1,431.69 | — | 51 / 173 | — | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1431.694762659959 \| rating \| reported \| Higher is better \| ### Configuration category industry_entertainment_and_sports_and_media config text_style_control ### Reported statistics lower 1425.44911893165 rank 68 upper 1437.940406388268 variance 10.154492707516782 votes 14780 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label GPT-5.4 Observed 2026-10-22T06:45:03.380Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/4760/row` |  |  |  |  |  |  |  |
| [Arena text style control / multi turn](https://benchize.com/benchmarks/lmarena%3Atext_style_control%3Amulti_turn.md) | 1,480.11 | — | 33 / 173 | — | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1480.1126517543125 \| rating \| reported \| Higher is better \| ### Configuration category multi_turn config text_style_control ### Reported statistics lower 1473.5568740847734 rank 40 upper 1486.6684294238512 variance 11.18799468079704 votes 12645 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label GPT-5.4 Observed 2026-10-22T06:45:03.380Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/9355/row` |  |  |  |  |  |  |  |
| [DesignArena Agentic web applications](https://benchize.com/benchmarks/designarena%3Awebapps.md) | 1,059elo | SE ±6.73 | 35 / 39 | — | — | [designarena · public](https://www.designarena.ai/api/leaderboard#board=webapps) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `elo` \| 1059 \| elo \| webapps \| Higher is better \| ### Configuration arenaType agents category agon_webapps inputModality text sourceModelVersion gpt-5.4 variationName public ### Reported statistics Uncertainty Standard error: ±6.73 averageGenerationTimeMs Not reported battles 3319 losses 1980 standardError 6.7266 winRate 40.3 wins 1339 ### Source [Original source](https://www.designarena.ai/api/leaderboard#board=webapps) Source designarena Original model label GPT-5.4 Source version public Observed 2026-10-21T16:38:00.309Z Evidence SHA-256 `f955787274cf4ac627ada7cd33eaae2e08ef7297db92d3391340fcaa0b44a35f` Source locator `/data/48` |  |  |  |  |  |  |  |
| [Arena text / chinese](https://benchize.com/benchmarks/lmarena%3Atext%3Achinese.md) | 1,508.62 | — | 39 / 168 | — | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1508.6238840175863 \| rating \| reported \| Higher is better \| ### Configuration category chinese config text ### Reported statistics lower 1498.9447074892084 rank 43 upper 1518.3030605459642 variance 24.388250047822034 votes 4367 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) Source Arena Original model label GPT-5.4 Observed 2026-10-22T06:45:03.380Z Evidence SHA-256 `8e027ef69b8de06c4b2a8b217bfe816b1f1536269bb257fd295b4ef1ba8246ac` Source locator `/rows/459/row` |  |  |  |  |  |  |  |
| [Arena vision / diagram (config: vision)](https://benchize.com/benchmarks/benchmark%3Avision%3Adiagram--config-vision.md) | 1,316.02 | — | 22 / 84 | — | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/vision/latest) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1316.0182040605155 \| rating \| reported \| Higher is better \| ### Configuration category diagram config vision ### Reported statistics lower 1306.891488420636 rank 22 upper 1325.144919700395 variance 21.683673380148306 votes 6221 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/vision/latest) Source Arena Original model label GPT-5.4 Observed 2026-10-22T06:45:03.380Z Evidence SHA-256 `06e61305486dce3fec5dc776ac2fd8321104e84c346cf9e08fa6f8e8a66ce0d7` Source locator `/rows/488/row` |  |  |  |  |  |  |  |
| [Arena text / industry entertainment and sports and media](https://benchize.com/benchmarks/lmarena%3Atext%3Aindustry_entertainment_and_sports_and_media.md) | 1,423.74 | — | 47 / 173 | — | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1423.7351778713482 \| rating \| reported \| Higher is better \| ### Configuration category industry_entertainment_and_sports_and_media config text ### Reported statistics lower 1417.538798859874 rank 56 upper 1429.9315568828224 variance 9.994930219478261 votes 14780 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) Source Arena Original model label GPT-5.4 Observed 2026-10-22T06:45:03.380Z Evidence SHA-256 `8e027ef69b8de06c4b2a8b217bfe816b1f1536269bb257fd295b4ef1ba8246ac` Source locator `/rows/4748/row` |  |  |  |  |  |  |  |
| [Arena text style control / coding](https://benchize.com/benchmarks/lmarena%3Atext_style_control%3Acoding.md) | 1,511.2 | — | 44 / 173 | — | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1511.1951942891149 \| rating \| reported \| Higher is better \| ### Configuration category coding config text_style_control ### Reported statistics lower 1505.4122485234784 rank 55 upper 1516.978140054751 variance 8.705667114830122 votes 18925 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label GPT-5.4 Observed 2026-10-22T06:45:03.380Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/864/row` |  |  |  |  |  |  |  |
| [Arena text / korean](https://benchize.com/benchmarks/lmarena%3Atext%3Akorean.md) | 1,438.6 | — | 28 / 144 | — | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1438.60444489253 \| rating \| reported \| Higher is better \| ### Configuration category korean config text ### Reported statistics lower 1419.643749881784 rank 30 upper 1457.5651399032756 variance 93.58630980340915 votes 1159 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) Source Arena Original model label GPT-5.4 Observed 2026-10-22T06:45:03.380Z Evidence SHA-256 `8e027ef69b8de06c4b2a8b217bfe816b1f1536269bb257fd295b4ef1ba8246ac` Source locator `/rows/8263/row` |  |  |  |  |  |  |  |
| [Arena vision / overall (config: vision)](https://benchize.com/benchmarks/benchmark%3Avision%3Aoverall--config-vision.md) | 1,292.03 | — | 26 / 92 | — | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/vision/latest) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1292.0285907748362 \| rating \| reported \| Higher is better \| ### Configuration category overall config vision ### Reported statistics lower 1285.5741361438882 rank 27 upper 1298.483045405784 variance 10.844834352652747 votes 22804 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/vision/latest) Source Arena Original model label GPT-5.4 Observed 2026-10-22T06:45:03.380Z Evidence SHA-256 `06e61305486dce3fec5dc776ac2fd8321104e84c346cf9e08fa6f8e8a66ce0d7` Source locator `/rows/26/row` |  |  |  |  |  |  |  |
| [Arena webdev / webdev](https://benchize.com/benchmarks/lmarena%3Awebdev%3Awebdev.md) | 1,400.54 | — | 72 / 107 | — | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/webdev/latest) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1400.5429943950562 \| rating \| reported \| Higher is better \| ### Configuration category webdev config webdev ### Reported statistics lower 1390.2450690912492 rank 96 upper 1410.8409196988634 variance 27.60598785844317 votes 4130 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/webdev/latest) Source Arena Original model label GPT-5.4 Observed 2026-10-22T06:45:03.380Z Evidence SHA-256 `f82507859808110820a4ab6df15561b8864137ddefc1f6fb0c552af2e58ea738` Source locator `/rows/307/row` |  |  |  |  |  |  |  |
| [Arena vision style control / overall](https://benchize.com/benchmarks/lmarena%3Avision_style_control%3Aoverall.md) | 1,278.64 | — | 30 / 92 | — | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/vision_style_control/latest) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1278.639320884338 \| rating \| reported \| Higher is better \| ### Configuration category overall config vision_style_control ### Reported statistics lower 1272.1327738042992 rank 31 upper 1285.1458679643767 variance 11.020593186291386 votes 22804 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/vision_style_control/latest) Source Arena Original model label GPT-5.4 Observed 2026-10-22T06:45:03.380Z Evidence SHA-256 `38568936995f36625aae49e9ea05557d55c1b1df9b2954f5c50cee523f26fe92` Source locator `/rows/30/row` |  |  |  |  |  |  |  |
| [Arena text style control / french](https://benchize.com/benchmarks/lmarena%3Atext_style_control%3Afrench.md) | 1,485.51 | — | 40 / 152 | — | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1485.5084367191243 \| rating \| reported \| Higher is better \| ### Configuration category french config text_style_control ### Reported statistics lower 1471.4109464965754 rank 49 upper 1499.6059269416733 variance 51.7353536381142 votes 2401 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label GPT-5.4 Observed 2026-10-22T06:45:03.380Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/2886/row` |  |  |  |  |  |  |  |
| [Arena text / industry legal and government](https://benchize.com/benchmarks/lmarena%3Atext%3Aindustry_legal_and_government.md) | 1,462.74 | — | 43 / 173 | — | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1462.7391453351845 \| rating \| reported \| Higher is better \| ### Configuration category industry_legal_and_government config text ### Reported statistics lower 1453.8501381528586 rank 48 upper 1471.6281525175107 variance 20.568865208651776 votes 5373 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) Source Arena Original model label GPT-5.4 Observed 2026-10-22T06:45:03.380Z Evidence SHA-256 `8e027ef69b8de06c4b2a8b217bfe816b1f1536269bb257fd295b4ef1ba8246ac` Source locator `/rows/5155/row` |  |  |  |  |  |  |  |
| [Arena text / industry mathematical](https://benchize.com/benchmarks/lmarena%3Atext%3Aindustry_mathematical.md) | 1,465.78 | — | 52 / 169 | — | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1465.7797772914007 \| rating \| reported \| Higher is better \| ### Configuration category industry_mathematical config text ### Reported statistics lower 1455.4239671514072 rank 58 upper 1476.1355874313942 variance 27.91720767065593 votes 3736 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) Source Arena Original model label GPT-5.4 Observed 2026-10-22T06:45:03.380Z Evidence SHA-256 `8e027ef69b8de06c4b2a8b217bfe816b1f1536269bb257fd295b4ef1ba8246ac` Source locator `/rows/5970/row` |  |  |  |  |  |  |  |
| [Judgemark v2.1](https://benchize.com/benchmarks/eq-bench%3Ajudgemark-v2.md) | 84.98% | — | 6 / 39 | — | — | [eq bench · judgemark-v2](https://eqbench.com/judgemark-v2.js) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `judgemark_score` \| 84.98 \| percent \| overall \| Higher is better \| \| `stability` \| 0.705 \| score_fraction \| overall \| Higher is better \| \| `separability` \| 0.898 \| score_fraction \| overall \| Higher is better \| \| `human_corr` \| 0.804 \| correlation \| overall \| Higher is better \| ### Configuration interactiveAdjustments none protocol judgemark-v2 sourceModelVersion gpt-5.4 ### Source [Original source](https://eqbench.com/judgemark-v2.js) Source eq bench Original model label gpt-5.4 Source version judgemark-v2 Observed 2026-10-22T05:10:06.632Z Evidence SHA-256 `070cc3fbd6f0333dde2b52bec4329ea3fba7eccbf016bbbbef95e0f8b2197781` Source locator `/leaderboardDataV2/41` |  |  |  |  |  |  |  |
| [Arena vision / humor (config: vision)](https://benchize.com/benchmarks/benchmark%3Avision%3Ahumor--config-vision.md) | 1,261.73 | — | 39 / 70 | — | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/vision/latest) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1261.7316883085387 \| rating \| reported \| Higher is better \| ### Configuration category humor config vision ### Reported statistics lower 1240.7342934749445 rank 43 upper 1282.7290831421333 variance 114.77165586749457 votes 844 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/vision/latest) Source Arena Original model label GPT-5.4 Observed 2026-10-22T06:45:03.380Z Evidence SHA-256 `06e61305486dce3fec5dc776ac2fd8321104e84c346cf9e08fa6f8e8a66ce0d7` Source locator `/rows/968/row` |  |  |  |  |  |  |  |
| [Arena text style control / exclude ties](https://benchize.com/benchmarks/lmarena%3Atext_style_control%3Aexclude_ties.md) | 1,470.6 | — | 44 / 173 | — | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1470.604845992086 \| rating \| reported \| Higher is better \| ### Configuration category exclude_ties config text_style_control ### Reported statistics lower 1465.7865623476218 rank 56 upper 1475.4231296365501 variance 6.043500233152245 votes 52149 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label GPT-5.4 Observed 2026-10-22T06:45:03.380Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/2109/row` |  |  |  |  |  |  |  |
| [Arena text style control / industry medicine and healthcare](https://benchize.com/benchmarks/lmarena%3Atext_style_control%3Aindustry_medicine_and_healthcare.md) | 1,465.25 | — | 60 / 173 | — | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1465.2504366680002 \| rating \| reported \| Higher is better \| ### Configuration category industry_medicine_and_healthcare config text_style_control ### Reported statistics lower 1455.943661130044 rank 85 upper 1474.5572122059566 variance 22.54770256739423 votes 5032 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label GPT-5.4 Observed 2026-10-22T06:45:03.380Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/6397/row` |  |  |  |  |  |  |  |
| [Arena webdev / overall](https://benchize.com/benchmarks/lmarena%3Awebdev%3Aoverall.md) | 1,400.54 | — | 72 / 107 | — | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/webdev/latest) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1400.5429943950562 \| rating \| reported \| Higher is better \| ### Configuration category overall config webdev ### Reported statistics lower 1390.2450690912492 rank 96 upper 1410.8409196988634 variance 27.60598785844317 votes 4130 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/webdev/latest) Source Arena Original model label GPT-5.4 Observed 2026-10-22T06:45:03.380Z Evidence SHA-256 `f82507859808110820a4ab6df15561b8864137ddefc1f6fb0c552af2e58ea738` Source locator `/rows/95/row` |  |  |  |  |  |  |  |
| [Arena text style control / industry writing and literature and language](https://benchize.com/benchmarks/lmarena%3Atext_style_control%3Aindustry_writing_and_literature_and_language.md) | 1,458.28 | — | 35 / 173 | — | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1458.2838728341435 \| rating \| reported \| Higher is better \| ### Configuration category industry_writing_and_literature_and_language config text_style_control ### Reported statistics lower 1452.378089145138 rank 39 upper 1464.1896565231493 variance 9.079436383239354 votes 16732 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label GPT-5.4 Observed 2026-10-22T06:45:03.380Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/7156/row` |  |  |  |  |  |  |  |
| [Arena text / industry software and it services](https://benchize.com/benchmarks/lmarena%3Atext%3Aindustry_software_and_it_services.md) | 1,474.84 | — | 44 / 173 | — | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1474.8354391739476 \| rating \| reported \| Higher is better \| ### Configuration category industry_software_and_it_services config text ### Reported statistics lower 1469.7502951218344 rank 51 upper 1479.9205832260614 variance 6.731476565996797 votes 26970 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) Source Arena Original model label GPT-5.4 Observed 2026-10-22T06:45:03.380Z Evidence SHA-256 `8e027ef69b8de06c4b2a8b217bfe816b1f1536269bb257fd295b4ef1ba8246ac` Source locator `/rows/6751/row` |  |  |  |  |  |  |  |
| [NC Bench](https://benchize.com/benchmarks/nc-bench%3Aoverall.md) | 84.31% | — | 105 / 144 | — | — | [nc bench](https://www.nc-bench.com/models) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `score` \| 84.31 \| percent \| reported \| Higher is better \| \| `tooling` \| 98.04 \| percent \| category \| Higher is better \| \| `creative_writing` \| 90.94 \| percent \| category \| Higher is better \| \| `language` \| 81.49 \| percent \| category \| Higher is better \| \| `utility` \| 81.95 \| percent \| category \| Higher is better \| \| `reasoning` \| 80.92 \| percent \| category \| Higher is better \| \| `text_editing` \| 96.73 \| percent \| category \| Higher is better \| \| `rule_following` \| 58.11 \| percent \| category \| Higher is better \| \| `hallucination` \| 86.32 \| percent \| category \| Higher is better \| ### Configuration Reasoning effort unknown Model configuration GPT-5.4 thinkingEnabled Not reported ### Source [Original source](https://www.nc-bench.com/models) Source nc bench Original model label GPT-5.4 Observed 2026-10-22T06:10:03.426Z Evidence SHA-256 `ec261022458543624b08a136d01f5a2f0666cd52ffb49c64d6ca983e8543d1b5` Source locator `/rows/135` |  |  |  |  |  |  |  |
| [Arena text / industry writing and literature and language](https://benchize.com/benchmarks/lmarena%3Atext%3Aindustry_writing_and_literature_and_language.md) | 1,448.68 | — | 39 / 173 | — | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1448.6803472259194 \| rating \| reported \| Higher is better \| ### Configuration category industry_writing_and_literature_and_language config text ### Reported statistics lower 1442.8120020267884 rank 44 upper 1454.5486924250506 variance 8.96468685038298 votes 16732 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) Source Arena Original model label GPT-5.4 Observed 2026-10-22T06:45:03.380Z Evidence SHA-256 `8e027ef69b8de06c4b2a8b217bfe816b1f1536269bb257fd295b4ef1ba8246ac` Source locator `/rows/7161/row` |  |  |  |  |  |  |  |
| [Judgemark v4](https://benchize.com/benchmarks/eq-bench%3Ajudgemark-v4.md) | 72.08% | CI 68.48–78.19% | 13 / 38 | — | — | [eq bench · judgemark-v4](https://eqbench.com/judgemark-v4.js) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `score` \| 0.720762 \| score_fraction \| overall \| Higher is better \| ### Configuration interactiveAdjustments none protocol judgemark-v4 sourceModelVersion gpt-5.4 ### Reported statistics Uncertainty Confidence interval: 68.48–78.19% confidenceIntervalHigh 0.781918 confidenceIntervalLow 0.684801 ### Source [Original source](https://eqbench.com/judgemark-v4.js) Source eq bench Original model label gpt-5.4 Source version judgemark-v4 Observed 2026-10-22T05:10:06.884Z Evidence SHA-256 `2b0d42aef4f614dd199dc38399be7b88075a919db52020c3759f190defc92a4d` Source locator `/leaderboardDataJudgemarkV4/13` |  |  |  |  |  |  |  |
| [Arena text / creative writing](https://benchize.com/benchmarks/lmarena%3Atext%3Acreative_writing.md) | 1,427.5 | — | 48 / 173 | — | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1427.4960833659122 \| rating \| reported \| Higher is better \| ### Configuration category creative_writing config text ### Reported statistics lower 1420.7264629810911 rank 60 upper 1434.265703750733 variance 11.929780402098359 votes 11332 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) Source Arena Original model label GPT-5.4 Observed 2026-10-22T06:45:03.380Z Evidence SHA-256 `8e027ef69b8de06c4b2a8b217bfe816b1f1536269bb257fd295b4ef1ba8246ac` Source locator `/rows/1281/row` |  |  |  |  |  |  |  |
| [Arena text / english](https://benchize.com/benchmarks/lmarena%3Atext%3Aenglish.md) | 1,451.14 | — | 51 / 173 | — | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1451.1408728565466 \| rating \| reported \| Higher is better \| ### Configuration category english config text ### Reported statistics lower 1446.29348576786 rank 63 upper 1455.9882599452333 variance 6.116728744035067 votes 30857 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) Source Arena Original model label GPT-5.4 Observed 2026-10-22T06:45:03.380Z Evidence SHA-256 `8e027ef69b8de06c4b2a8b217bfe816b1f1536269bb257fd295b4ef1ba8246ac` Source locator `/rows/1699/row` |  |  |  |  |  |  |  |
| [Arena text / exclude ties](https://benchize.com/benchmarks/lmarena%3Atext%3Aexclude_ties.md) | 1,450.8 | — | 43 / 173 | — | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1450.8020944395855 \| rating \| reported \| Higher is better \| ### Configuration category exclude_ties config text ### Reported statistics lower 1446.0815487819955 rank 48 upper 1455.5226400971753 variance 5.800804419755612 votes 52149 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) Source Arena Original model label GPT-5.4 Observed 2026-10-22T06:45:03.380Z Evidence SHA-256 `8e027ef69b8de06c4b2a8b217bfe816b1f1536269bb257fd295b4ef1ba8246ac` Source locator `/rows/2101/row` |  |  |  |  |  |  |  |
| [Arena vision style control / homework](https://benchize.com/benchmarks/lmarena%3Avision_style_control%3Ahomework.md) | 1,303.18 | — | 34 / 83 | — | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/vision_style_control/latest) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1303.1815404820143 \| rating \| reported \| Higher is better \| ### Configuration category homework config vision_style_control ### Reported statistics lower 1291.4820214458832 rank 34 upper 1314.8810595181453 variance 35.63197005768186 votes 3080 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/vision_style_control/latest) Source Arena Original model label GPT-5.4 Observed 2026-10-22T06:45:03.380Z Evidence SHA-256 `38568936995f36625aae49e9ea05557d55c1b1df9b2954f5c50cee523f26fe92` Source locator `/rows/841/row` |  |  |  |  |  |  |  |
| [Arena text / coding](https://benchize.com/benchmarks/lmarena%3Atext%3Acoding.md) | 1,478.45 | — | 46 / 173 | — | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1478.4479754432857 \| rating \| reported \| Higher is better \| ### Configuration category coding config text ### Reported statistics lower 1472.7259429324547 rank 57 upper 1484.170007954117 variance 8.5232349436175 votes 18925 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) Source Arena Original model label GPT-5.4 Observed 2026-10-22T06:45:03.380Z Evidence SHA-256 `8e027ef69b8de06c4b2a8b217bfe816b1f1536269bb257fd295b4ef1ba8246ac` Source locator `/rows/866/row` |  |  |  |  |  |  |  |
| [Arena text / german](https://benchize.com/benchmarks/lmarena%3Atext%3Agerman.md) | 1,441.72 | — | 51 / 149 | — | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1441.7234352912633 \| rating \| reported \| Higher is better \| ### Configuration category german config text ### Reported statistics lower 1422.102516515677 rank 68 upper 1461.34435406685 variance 100.21725380062725 votes 1000 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) Source Arena Original model label GPT-5.4 Observed 2026-10-22T06:45:03.380Z Evidence SHA-256 `8e027ef69b8de06c4b2a8b217bfe816b1f1536269bb257fd295b4ef1ba8246ac` Source locator `/rows/3204/row` |  |  |  |  |  |  |  |
| [Arena vision / chinese (config: vision)](https://benchize.com/benchmarks/benchmark%3Avision%3Achinese--config-vision.md) | 1,336.24 | — | 29 / 83 | — | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/vision/latest) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1336.2370687731266 \| rating \| reported \| Higher is better \| ### Configuration category chinese config vision ### Reported statistics lower 1317.694137185766 rank 31 upper 1354.780000360487 variance 89.50774377724557 votes 1356 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/vision/latest) Source Arena Original model label GPT-5.4 Observed 2026-10-22T06:45:03.380Z Evidence SHA-256 `06e61305486dce3fec5dc776ac2fd8321104e84c346cf9e08fa6f8e8a66ce0d7` Source locator `/rows/231/row` |  |  |  |  |  |  |  |
| [Arena text / japanese](https://benchize.com/benchmarks/lmarena%3Atext%3Ajapanese.md) | 1,449.94 | — | 30 / 138 | — | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1449.9439937602351 \| rating \| reported \| Higher is better \| ### Configuration category japanese config text ### Reported statistics lower 1426.1264789381435 rank 32 upper 1473.7615085823265 variance 147.6715067839893 votes 685 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) Source Arena Original model label GPT-5.4 Observed 2026-10-22T06:45:03.380Z Evidence SHA-256 `8e027ef69b8de06c4b2a8b217bfe816b1f1536269bb257fd295b4ef1ba8246ac` Source locator `/rows/7982/row` |  |  |  |  |  |  |  |
| [Arena text style control / longer query](https://benchize.com/benchmarks/lmarena%3Atext_style_control%3Alonger_query.md) | 1,477.29 | — | 44 / 172 | — | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1477.2912190745176 \| rating \| reported \| Higher is better \| ### Configuration category longer_query config text_style_control ### Reported statistics lower 1472.092200692677 rank 51 upper 1482.4902374563585 variance 7.036335256051333 votes 29935 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label GPT-5.4 Observed 2026-10-22T06:45:03.380Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/8568/row` |  |  |  |  |  |  |  |
| [Arena text / industry business and management and financial operations](https://benchize.com/benchmarks/lmarena%3Atext%3Aindustry_business_and_management_and_financial_operations.md) | 1,456.78 | — | 36 / 173 | — | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1456.7845409018162 \| rating \| reported \| Higher is better \| ### Configuration category industry_business_and_management_and_financial_operations config text ### Reported statistics lower 1450.5198357626582 rank 39 upper 1463.0492460409741 variance 10.21656935879922 votes 13839 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) Source Arena Original model label GPT-5.4 Observed 2026-10-22T06:45:03.380Z Evidence SHA-256 `8e027ef69b8de06c4b2a8b217bfe816b1f1536269bb257fd295b4ef1ba8246ac` Source locator `/rows/4321/row` |  |  |  |  |  |  |  |
| [Arena text style control / hard prompts english](https://benchize.com/benchmarks/lmarena%3Atext_style_control%3Ahard_prompts_english.md) | 1,486.42 | — | 52 / 173 | — | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1486.4239948177174 \| rating \| reported \| Higher is better \| ### Configuration category hard_prompts_english config text_style_control ### Reported statistics lower 1480.8282819346264 rank 65 upper 1492.0197077008083 variance 8.151070760230729 votes 21081 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label GPT-5.4 Observed 2026-10-22T06:45:03.380Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/3932/row` |  |  |  |  |  |  |  |
| [Arena text style control / korean](https://benchize.com/benchmarks/lmarena%3Atext_style_control%3Akorean.md) | 1,426.5 | — | 40 / 144 | — | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1426.5033032874212 \| rating \| reported \| Higher is better \| ### Configuration category korean config text_style_control ### Reported statistics lower 1407.369680708894 rank 48 upper 1445.6369258659483 variance 95.30116814095479 votes 1159 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label GPT-5.4 Observed 2026-10-22T06:45:03.380Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/8281/row` |  |  |  |  |  |  |  |
| [Arena text / multi turn](https://benchize.com/benchmarks/lmarena%3Atext%3Amulti_turn.md) | 1,463.18 | — | 39 / 173 | — | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1463.1836678862862 \| rating \| reported \| Higher is better \| ### Configuration category multi_turn config text ### Reported statistics lower 1456.675999064268 rank 45 upper 1469.6913367083046 variance 11.024393459310183 votes 12645 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) Source Arena Original model label GPT-5.4 Observed 2026-10-22T06:45:03.380Z Evidence SHA-256 `8e027ef69b8de06c4b2a8b217bfe816b1f1536269bb257fd295b4ef1ba8246ac` Source locator `/rows/9360/row` |  |  |  |  |  |  |  |
| [EQ-Bench 4](https://benchize.com/benchmarks/eq-bench%3Aeqbench4.md) | 1,271.8elo | CI 1,261.5–1,281.4 | 7 / 26 | — | — | [eq bench · eqbench4](https://eqbench.com/eqbench4/eqbench4_data.js) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `elo` \| 1271.8 \| elo \| overall \| Higher is better \| ### Configuration protocol eqbench4 ### Reported statistics Uncertainty Confidence interval: 1,261.5–1,281.4 confidenceIntervalHigh 1281.4 confidenceIntervalLow 1261.5 scenarios 120 ### Source [Original source](https://eqbench.com/eqbench4/eqbench4_data.js) Source eq bench Original model label gpt-5.4 Source version eqbench4 Observed 2026-10-22T05:10:04.699Z Evidence SHA-256 `188d8ea4a393978063a6c24dff6c92ce185169827038bfa558091212a68c29d8` Source locator `/models/6` |  |  |  |  |  |  |  |
| [Arena text / french](https://benchize.com/benchmarks/lmarena%3Atext%3Afrench.md) | 1,471.35 | — | 38 / 152 | — | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1471.347211120446 \| rating \| reported \| Higher is better \| ### Configuration category french config text ### Reported statistics lower 1457.4409013516101 rank 45 upper 1485.2535208892818 variance 50.34166977009876 votes 2401 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) Source Arena Original model label GPT-5.4 Observed 2026-10-22T06:45:03.380Z Evidence SHA-256 `8e027ef69b8de06c4b2a8b217bfe816b1f1536269bb257fd295b4ef1ba8246ac` Source locator `/rows/2882/row` |  |  |  |  |  |  |  |
| [Arena text style control / expert](https://benchize.com/benchmarks/lmarena%3Atext_style_control%3Aexpert.md) | 1,491.37 | — | 50 / 170 | — | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1491.3693796904058 \| rating \| reported \| Higher is better \| ### Configuration category expert config text_style_control ### Reported statistics lower 1483.1615624776946 rank 57 upper 1499.5771969031168 variance 17.537156205960283 votes 6736 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label GPT-5.4 Observed 2026-10-22T06:45:03.380Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/2527/row` |  |  |  |  |  |  |  |
| [Arena text / russian](https://benchize.com/benchmarks/lmarena%3Atext%3Arussian.md) | 1,458.05 | — | 38 / 172 | — | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1458.0521797786755 \| rating \| reported \| Higher is better \| ### Configuration category russian config text ### Reported statistics lower 1450.4245673653093 rank 42 upper 1465.6797921920415 variance 15.145410596390361 votes 7663 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) Source Arena Original model label GPT-5.4 Observed 2026-10-22T06:45:03.380Z Evidence SHA-256 `8e027ef69b8de06c4b2a8b217bfe816b1f1536269bb257fd295b4ef1ba8246ac` Source locator `/rows/10425/row` |  |  |  |  |  |  |  |
| [Arena text style control / chinese](https://benchize.com/benchmarks/lmarena%3Atext_style_control%3Achinese.md) | 1,493.62 | — | 62 / 168 | — | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1493.6195434117328 \| rating \| reported \| Higher is better \| ### Configuration category chinese config text_style_control ### Reported statistics lower 1483.8194766007034 rank 76 upper 1503.4196102227622 variance 25.00125967334657 votes 4367 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label GPT-5.4 Observed 2026-10-22T06:45:03.380Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/492/row` |  |  |  |  |  |  |  |
| [Arena text style control / industry business and management and financial operations](https://benchize.com/benchmarks/lmarena%3Atext_style_control%3Aindustry_business_and_management_and_financial_operations.md) | 1,473.8 | — | 32 / 173 | — | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1473.7959530298012 \| rating \| reported \| Higher is better \| ### Configuration category industry_business_and_management_and_financial_operations config text_style_control ### Reported statistics lower 1467.4399043382127 rank 36 upper 1480.15200172139 variance 10.516670060918736 votes 13839 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label GPT-5.4 Observed 2026-10-22T06:45:03.380Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/4318/row` |  |  |  |  |  |  |  |
| [Arena text style control / instruction following](https://benchize.com/benchmarks/lmarena%3Atext_style_control%3Ainstruction_following.md) | 1,460.28 | — | 45 / 173 | — | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1460.2842524669582 \| rating \| reported \| Higher is better \| ### Configuration category instruction_following config text_style_control ### Reported statistics lower 1454.9155439865237 rank 52 upper 1465.6529609473926 variance 7.503147135827042 votes 23383 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label GPT-5.4 Observed 2026-10-22T06:45:03.380Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/7585/row` |  |  |  |  |  |  |  |
| [Arena webdev / image to webdev](https://benchize.com/benchmarks/lmarena%3Awebdev%3Aimage_to_webdev.md) | 1,436.46 | — | 44 / 52 | — | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/webdev/latest) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1436.4605011545846 \| rating \| reported \| Higher is better \| ### Configuration category image_to_webdev config webdev ### Reported statistics lower 1424.736486524324 rank 53 upper 1448.1845157848452 variance 35.781333463762095 votes 3201 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/webdev/latest) Source Arena Original model label GPT-5.4 Observed 2026-10-22T06:45:03.380Z Evidence SHA-256 `f82507859808110820a4ab6df15561b8864137ddefc1f6fb0c552af2e58ea738` Source locator `/rows/200/row` |  |  |  |  |  |  |  |
| [Arena vision style control / humor](https://benchize.com/benchmarks/lmarena%3Avision_style_control%3Ahumor.md) | 1,245.02 | — | 39 / 70 | — | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/vision_style_control/latest) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1245.0232091636976 \| rating \| reported \| Higher is better \| ### Configuration category humor config vision_style_control ### Reported statistics lower 1224.004526481174 rank 44 upper 1266.0418918462215 variance 115.00449238937706 votes 844 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/vision_style_control/latest) Source Arena Original model label GPT-5.4 Observed 2026-10-22T06:45:03.380Z Evidence SHA-256 `38568936995f36625aae49e9ea05557d55c1b1df9b2954f5c50cee523f26fe92` Source locator `/rows/969/row` |  |  |  |  |  |  |  |
| [Arena vision style control / entity recognition](https://benchize.com/benchmarks/lmarena%3Avision_style_control%3Aentity_recognition.md) | 1,215.38 | — | 16 / 37 | — | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/vision_style_control/latest) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1215.3759835843214 \| rating \| reported \| Higher is better \| ### Configuration category entity_recognition config vision_style_control ### Reported statistics lower 1169.1099259378382 rank 24 upper 1261.6420412308046 variance 557.2227088876925 votes 137 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/vision_style_control/latest) Source Arena Original model label GPT-5.4 Observed 2026-10-22T06:45:03.380Z Evidence SHA-256 `38568936995f36625aae49e9ea05557d55c1b1df9b2954f5c50cee523f26fe92` Source locator `/rows/780/row` |  |  |  |  |  |  |  |
| [EQ-Bench 3](https://benchize.com/benchmarks/eq-bench%3Aeqbench3.md) | 1,562.9elo | CI 1,529.3–1,596.5 | 8 / 50 | — | — | [eq bench · eqbench3](https://eqbench.com/eqbench3.js) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `elo_norm` \| 1562.9 \| elo \| overall \| Higher is better \| \| `rubric_0_100` \| 82.4 \| percent \| overall \| Higher is better \| ### Configuration interactiveAdjustments none protocol eqbench3 sourceModelVersion gpt-5.4 ### Reported statistics Uncertainty Confidence interval: 1,529.3–1,596.5 confidenceIntervalHigh 1596.5 confidenceIntervalLow 1529.3 ### Source [Original source](https://eqbench.com/eqbench3.js) Source eq bench Original model label gpt-5.4 Source version eqbench3 Observed 2026-10-22T05:10:04.922Z Evidence SHA-256 `3672ff093e739f07ff664a2e6013bc38a6977a146e4092b4cef80ba1780542b2` Source locator `/leaderboardDataEQBench3/10` |  |  |  |  |  |  |  |
| [Arena vision style control / ocr](https://benchize.com/benchmarks/lmarena%3Avision_style_control%3Aocr.md) | 1,290.35 | — | 30 / 84 | — | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/vision_style_control/latest) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1290.3459332347802 \| rating \| reported \| Higher is better \| ### Configuration category ocr config vision_style_control ### Reported statistics lower 1283.704823214727 rank 31 upper 1296.9870432548337 variance 11.481144106208058 votes 16434 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/vision_style_control/latest) Source Arena Original model label GPT-5.4 Observed 2026-10-22T06:45:03.380Z Evidence SHA-256 `38568936995f36625aae49e9ea05557d55c1b1df9b2954f5c50cee523f26fe92` Source locator `/rows/1049/row` |  |  |  |  |  |  |  |
| [SVGBench Arena](https://benchize.com/benchmarks/svgbench%3Aarena.md) | 1,795 | — | 4 / 191 | — | — | [svgbench](https://svgbench.ai/api/leaderboard?shape=2) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1795 \| rating \| reported \| Higher is better \| ### Configuration Reasoning effort unknown sourceModelId model_gpt54 ### Reported statistics coverageCount 27 draws 7 judged 211 losses 78 rank 5 ratingDeviation 28 wins 126 ### Source [Original source](https://svgbench.ai/api/leaderboard?shape=2) Source svgbench Original model label GPT-5.4 Observed 2026-10-22T04:30:04.538Z Evidence SHA-256 `5c0a9c869593820d57d2c05f6d416e1b44a740b4835e66c66e9ad8b8edc59e2c` Source locator `/rows/4` |  |  |  |  |  |  |  |
| [Arena vision / homework (config: vision)](https://benchize.com/benchmarks/benchmark%3Avision%3Ahomework--config-vision.md) | 1,309.23 | — | 32 / 83 | — | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/vision/latest) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1309.2301450244765 \| rating \| reported \| Higher is better \| ### Configuration category homework config vision ### Reported statistics lower 1297.6058833845602 rank 32 upper 1320.8544066643929 variance 35.17503765634905 votes 3080 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/vision/latest) Source Arena Original model label GPT-5.4 Observed 2026-10-22T06:45:03.380Z Evidence SHA-256 `06e61305486dce3fec5dc776ac2fd8321104e84c346cf9e08fa6f8e8a66ce0d7` Source locator `/rows/839/row` |  |  |  |  |  |  |  |
| [Arena text style control / japanese](https://benchize.com/benchmarks/lmarena%3Atext_style_control%3Ajapanese.md) | 1,446.27 | — | 36 / 138 | — | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1446.2651861705397 \| rating \| reported \| Higher is better \| ### Configuration category japanese config text_style_control ### Reported statistics lower 1422.2374701989318 rank 41 upper 1470.2929021421473 variance 150.28955450521727 votes 685 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label GPT-5.4 Observed 2026-10-22T06:45:03.380Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/7991/row` |  |  |  |  |  |  |  |
| [Arena vision style control / diagram](https://benchize.com/benchmarks/lmarena%3Avision_style_control%3Adiagram.md) | 1,313.83 | — | 22 / 84 | — | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/vision_style_control/latest) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1313.8299188501546 \| rating \| reported \| Higher is better \| ### Configuration category diagram config vision_style_control ### Reported statistics lower 1304.5633324655462 rank 22 upper 1323.0965052347628 variance 22.353388967968083 votes 6221 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/vision_style_control/latest) Source Arena Original model label GPT-5.4 Observed 2026-10-22T06:45:03.380Z Evidence SHA-256 `38568936995f36625aae49e9ea05557d55c1b1df9b2954f5c50cee523f26fe92` Source locator `/rows/488/row` |  |  |  |  |  |  |  |
| [Arena text / math](https://benchize.com/benchmarks/lmarena%3Atext%3Amath.md) | 1,457.46 | — | 55 / 170 | — | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1457.4619227860153 \| rating \| reported \| Higher is better \| ### Configuration category math config text ### Reported statistics lower 1447.1688738504492 rank 64 upper 1467.7549717215813 variance 27.579849566320082 votes 3557 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) Source Arena Original model label GPT-5.4 Observed 2026-10-22T06:45:03.380Z Evidence SHA-256 `8e027ef69b8de06c4b2a8b217bfe816b1f1536269bb257fd295b4ef1ba8246ac` Source locator `/rows/8976/row` |  |  |  |  |  |  |  |
| [Arena text style control / industry life and physical and social science](https://benchize.com/benchmarks/lmarena%3Atext_style_control%3Aindustry_life_and_physical_and_social_science.md) | 1,478.35 | — | 52 / 173 | — | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1478.3454908640506 \| rating \| reported \| Higher is better \| ### Configuration category industry_life_and_physical_and_social_science config text_style_control ### Reported statistics lower 1471.6423969621133 rank 65 upper 1485.0485847659877 variance 11.696459588773719 votes 11099 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label GPT-5.4 Observed 2026-10-22T06:45:03.380Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/5562/row` |  |  |  |  |  |  |  |
| [Arena text style control / math](https://benchize.com/benchmarks/lmarena%3Atext_style_control%3Amath.md) | 1,459.94 | — | 55 / 170 | — | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1459.9367554397631 \| rating \| reported \| Higher is better \| ### Configuration category math config text_style_control ### Reported statistics lower 1449.6302451193962 rank 67 upper 1470.24326576013 variance 27.65203531835241 votes 3557 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label GPT-5.4 Observed 2026-10-22T06:45:03.380Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/8979/row` |  |  |  |  |  |  |  |
| [Arena text style control / overall](https://benchize.com/benchmarks/lmarena%3Atext_style_control%3Aoverall.md) | 1,464.68 | — | 44 / 173 | — | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1464.680183320086 \| rating \| reported \| Higher is better \| ### Configuration category overall config text_style_control ### Reported statistics lower 1460.992041639329 rank 55 upper 1468.3683250008428 variance 3.5409436082092083 votes 67829 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label GPT-5.4 Observed 2026-10-22T06:45:03.380Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/54/row` |  |  |  |  |  |  |  |
| [Arena vision style control / chinese](https://benchize.com/benchmarks/lmarena%3Avision_style_control%3Achinese.md) | 1,297.36 | — | 40 / 83 | — | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/vision_style_control/latest) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1297.3632838300186 \| rating \| reported \| Higher is better \| ### Configuration category chinese config vision_style_control ### Reported statistics lower 1278.4689144846247 rank 44 upper 1316.2576531754125 variance 92.93271374848484 votes 1356 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/vision_style_control/latest) Source Arena Original model label GPT-5.4 Observed 2026-10-22T06:45:03.380Z Evidence SHA-256 `38568936995f36625aae49e9ea05557d55c1b1df9b2954f5c50cee523f26fe92` Source locator `/rows/244/row` |  |  |  |  |  |  |  |
| [Arena text style control / creative writing](https://benchize.com/benchmarks/lmarena%3Atext_style_control%3Acreative_writing.md) | 1,434.32 | — | 51 / 173 | — | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1434.3201040782606 \| rating \| reported \| Higher is better \| ### Configuration category creative_writing config text_style_control ### Reported statistics lower 1427.5271956012302 rank 66 upper 1441.1130125552904 variance 12.012000578720013 votes 11332 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label GPT-5.4 Observed 2026-10-22T06:45:03.380Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/1287/row` |  |  |  |  |  |  |  |
| [Arena text / longer query](https://benchize.com/benchmarks/lmarena%3Atext%3Alonger_query.md) | 1,463.91 | — | 39 / 172 | — | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1463.9051576290042 \| rating \| reported \| Higher is better \| ### Configuration category longer_query config text ### Reported statistics lower 1458.7479089375174 rank 45 upper 1469.062406320491 variance 6.923727497106384 votes 29935 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) Source Arena Original model label GPT-5.4 Observed 2026-10-22T06:45:03.380Z Evidence SHA-256 `8e027ef69b8de06c4b2a8b217bfe816b1f1536269bb257fd295b4ef1ba8246ac` Source locator `/rows/8562/row` |  |  |  |  |  |  |  |
| [Arena text / polish](https://benchize.com/benchmarks/lmarena%3Atext%3Apolish.md) | 1,454.17 | — | 35 / 137 | — | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1454.1704613611678 \| rating \| reported \| Higher is better \| ### Configuration category polish config text ### Reported statistics lower 1437.57696411997 rank 42 upper 1470.7639586023656 variance 71.67697573909933 votes 1302 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) Source Arena Original model label GPT-5.4 Observed 2026-10-22T06:45:03.380Z Evidence SHA-256 `8e027ef69b8de06c4b2a8b217bfe816b1f1536269bb257fd295b4ef1ba8246ac` Source locator `/rows/10189/row` |  |  |  |  |  |  |  |
| [Arena vision / creative writing vision (config: vision)](https://benchize.com/benchmarks/benchmark%3Avision%3Acreative_writing_vision--config-vision.md) | 1,272.06 | — | 34 / 79 | — | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/vision/latest) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1272.0582502487298 \| rating \| reported \| Higher is better \| ### Configuration category creative_writing_vision config vision ### Reported statistics lower 1255.6562729907614 rank 37 upper 1288.4602275066984 variance 70.0319515392598 votes 1446 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/vision/latest) Source Arena Original model label GPT-5.4 Observed 2026-10-22T06:45:03.380Z Evidence SHA-256 `06e61305486dce3fec5dc776ac2fd8321104e84c346cf9e08fa6f8e8a66ce0d7` Source locator `/rows/399/row` |  |  |  |  |  |  |  |
| [Arena text / overall](https://benchize.com/benchmarks/lmarena%3Atext.md) | 1,452.15 | — | 43 / 173 | — | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1452.1549449444144 \| rating \| reported \| Higher is better \| ### Configuration category overall config text ### Reported statistics lower 1448.4962071608957 rank 48 upper 1455.813682727933 variance 3.484707969908124 votes 67829 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) Source Arena Original model label GPT-5.4 Observed 2026-10-22T06:45:03.380Z Evidence SHA-256 `8e027ef69b8de06c4b2a8b217bfe816b1f1536269bb257fd295b4ef1ba8246ac` Source locator `/rows/47/row` |  |  |  |  |  |  |  |
| [Arena vision / english (config: vision)](https://benchize.com/benchmarks/benchmark%3Avision%3Aenglish--config-vision.md) | 1,290.36 | — | 28 / 92 | — | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/vision/latest) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1290.360200114876 \| rating \| reported \| Higher is better \| ### Configuration category english config vision ### Reported statistics lower 1281.59487938775 rank 30 upper 1299.125520842002 variance 20.000435000238184 votes 9595 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/vision/latest) Source Arena Original model label GPT-5.4 Observed 2026-10-22T06:45:03.380Z Evidence SHA-256 `06e61305486dce3fec5dc776ac2fd8321104e84c346cf9e08fa6f8e8a66ce0d7` Source locator `/rows/619/row` |  |  |  |  |  |  |  |
| [Arena vision style control / creative writing vision](https://benchize.com/benchmarks/lmarena%3Avision_style_control%3Acreative_writing_vision.md) | 1,256.61 | — | 36 / 79 | — | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/vision_style_control/latest) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1256.6081768337945 \| rating \| reported \| Higher is better \| ### Configuration category creative_writing_vision config vision_style_control ### Reported statistics lower 1240.12119090655 rank 40 upper 1273.095162761039 variance 70.75976019861108 votes 1446 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/vision_style_control/latest) Source Arena Original model label GPT-5.4 Observed 2026-10-22T06:45:03.380Z Evidence SHA-256 `38568936995f36625aae49e9ea05557d55c1b1df9b2954f5c50cee523f26fe92` Source locator `/rows/402/row` |  |  |  |  |  |  |  |
| [Arena text / hard prompts english](https://benchize.com/benchmarks/lmarena%3Atext%3Ahard_prompts_english.md) | 1,463.73 | — | 48 / 173 | — | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1463.726838242144 \| rating \| reported \| Higher is better \| ### Configuration category hard_prompts_english config text ### Reported statistics lower 1458.2005865729643 rank 56 upper 1469.2530899113235 variance 7.949963525990202 votes 21081 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) Source Arena Original model label GPT-5.4 Observed 2026-10-22T06:45:03.380Z Evidence SHA-256 `8e027ef69b8de06c4b2a8b217bfe816b1f1536269bb257fd295b4ef1ba8246ac` Source locator `/rows/3923/row` |  |  |  |  |  |  |  |
| [Arena text / industry medicine and healthcare](https://benchize.com/benchmarks/lmarena%3Atext%3Aindustry_medicine_and_healthcare.md) | 1,439.66 | — | 69 / 173 | — | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1439.6623991106903 \| rating \| reported \| Higher is better \| ### Configuration category industry_medicine_and_healthcare config text ### Reported statistics lower 1430.5051948346568 rank 98 upper 1448.8196033867234 variance 21.828787985770536 votes 5032 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) Source Arena Original model label GPT-5.4 Observed 2026-10-22T06:45:03.380Z Evidence SHA-256 `8e027ef69b8de06c4b2a8b217bfe816b1f1536269bb257fd295b4ef1ba8246ac` Source locator `/rows/6410/row` |  |  |  |  |  |  |  |
| [Arena text / non english](https://benchize.com/benchmarks/lmarena%3Atext%3Anon_english.md) | 1,447.77 | — | 39 / 173 | — | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1447.7749851628741 \| rating \| reported \| Higher is better \| ### Configuration category non_english config text ### Reported statistics lower 1443.2297529830564 rank 43 upper 1452.3202173426919 variance 5.377940134919258 votes 36970 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) Source Arena Original model label GPT-5.4 Observed 2026-10-22T06:45:03.380Z Evidence SHA-256 `8e027ef69b8de06c4b2a8b217bfe816b1f1536269bb257fd295b4ef1ba8246ac` Source locator `/rows/9773/row` |  |  |  |  |  |  |  |
| [Arena text style control / industry legal and government](https://benchize.com/benchmarks/lmarena%3Atext_style_control%3Aindustry_legal_and_government.md) | 1,475.01 | — | 38 / 173 | — | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1475.0132631005654 \| rating \| reported \| Higher is better \| ### Configuration category industry_legal_and_government config text_style_control ### Reported statistics lower 1466.0214452173043 rank 45 upper 1484.0050809838262 variance 21.047417822149647 votes 5373 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label GPT-5.4 Observed 2026-10-22T06:45:03.380Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/5152/row` |  |  |  |  |  |  |  |
| [Arena text / hard prompts](https://benchize.com/benchmarks/lmarena%3Atext%3Ahard_prompts.md) | 1,468.35 | — | 42 / 173 | — | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1468.3518156307468 \| rating \| reported \| Higher is better \| ### Configuration category hard_prompts config text ### Reported statistics lower 1463.9382235830667 rank 48 upper 1472.765407678427 variance 5.070936764545606 votes 44723 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) Source Arena Original model label GPT-5.4 Observed 2026-10-22T06:45:03.380Z Evidence SHA-256 `8e027ef69b8de06c4b2a8b217bfe816b1f1536269bb257fd295b4ef1ba8246ac` Source locator `/rows/3498/row` |  |  |  |  |  |  |  |
| [Arena webdev / webdev-html](https://benchize.com/benchmarks/lmarena%3Awebdev%3Awebdev-html.md) | 1,434.87 | — | 65 / 106 | — | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/webdev/latest) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1434.8735184064024 \| rating \| reported \| Higher is better \| ### Configuration category webdev-html config webdev ### Reported statistics lower 1408.2564059436647 rank 83 upper 1461.4906308691402 variance 184.42750760139847 votes 553 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/webdev/latest) Source Arena Original model label GPT-5.4 Observed 2026-10-22T06:45:03.380Z Evidence SHA-256 `f82507859808110820a4ab6df15561b8864137ddefc1f6fb0c552af2e58ea738` Source locator `/rows/442/row` |  |  |  |  |  |  |  |
| [Arena text style control / non english](https://benchize.com/benchmarks/lmarena%3Atext_style_control%3Anon_english.md) | 1,456.39 | — | 40 / 173 | — | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1456.388162881038 \| rating \| reported \| Higher is better \| ### Configuration category non_english config text_style_control ### Reported statistics lower 1451.8110644590486 rank 50 upper 1460.9652613030273 variance 5.453613052343403 votes 36970 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label GPT-5.4 Observed 2026-10-22T06:45:03.380Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/9780/row` |  |  |  |  |  |  |  |
| [Arena text / industry life and physical and social science](https://benchize.com/benchmarks/lmarena%3Atext%3Aindustry_life_and_physical_and_social_science.md) | 1,462.39 | — | 45 / 173 | — | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1462.39341921994 \| rating \| reported \| Higher is better \| ### Configuration category industry_life_and_physical_and_social_science config text ### Reported statistics lower 1455.7674442263785 rank 54 upper 1469.0193942135015 variance 11.42887290078204 votes 11099 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) Source Arena Original model label GPT-5.4 Observed 2026-10-22T06:45:03.380Z Evidence SHA-256 `8e027ef69b8de06c4b2a8b217bfe816b1f1536269bb257fd295b4ef1ba8246ac` Source locator `/rows/5551/row` |  |  |  |  |  |  |  |
| [Arena text / expert](https://benchize.com/benchmarks/lmarena%3Atext%3Aexpert.md) | 1,481.65 | — | 42 / 170 | — | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1481.651752893006 \| rating \| reported \| Higher is better \| ### Configuration category expert config text ### Reported statistics lower 1473.522399092988 rank 48 upper 1489.7811066930242 variance 17.203462614217383 votes 6736 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) Source Arena Original model label GPT-5.4 Observed 2026-10-22T06:45:03.380Z Evidence SHA-256 `8e027ef69b8de06c4b2a8b217bfe816b1f1536269bb257fd295b4ef1ba8246ac` Source locator `/rows/2518/row` |  |  |  |  |  |  |  |
| [Arena text style control / spanish](https://benchize.com/benchmarks/lmarena%3Atext_style_control%3Aspanish.md) | 1,460.93 | — | 38 / 155 | — | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1460.929568601227 \| rating \| reported \| Higher is better \| ### Configuration category spanish config text_style_control ### Reported statistics lower 1446.6352828527347 rank 51 upper 1475.2238543497197 variance 53.18984651321522 votes 2036 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label GPT-5.4 Observed 2026-10-22T06:45:03.380Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/10815/row` |  |  |  |  |  |  |  |
| [Arena vision / entity recognition (config: vision)](https://benchize.com/benchmarks/benchmark%3Avision%3Aentity_recognition--config-vision.md) | 1,251.13 | — | 14 / 37 | — | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/vision/latest) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1251.1294095628514 \| rating \| reported \| Higher is better \| ### Configuration category entity_recognition config vision ### Reported statistics lower 1205.2335349609211 rank 18 upper 1297.0252841647819 variance 548.3415035269074 votes 137 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/vision/latest) Source Arena Original model label GPT-5.4 Observed 2026-10-22T06:45:03.380Z Evidence SHA-256 `06e61305486dce3fec5dc776ac2fd8321104e84c346cf9e08fa6f8e8a66ce0d7` Source locator `/rows/774/row` |  |  |  |  |  |  |  |
| [Arena text style control / hard prompts](https://benchize.com/benchmarks/lmarena%3Atext_style_control%3Ahard_prompts.md) | 1,486.78 | — | 45 / 173 | — | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1486.7786871051612 \| rating \| reported \| Higher is better \| ### Configuration category hard_prompts config text_style_control ### Reported statistics lower 1482.3218905760837 rank 56 upper 1491.2354836342388 variance 5.1707010874606985 votes 44723 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label GPT-5.4 Observed 2026-10-22T06:45:03.380Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/3506/row` |  |  |  |  |  |  |  |
| [Arena text style control / russian](https://benchize.com/benchmarks/lmarena%3Atext_style_control%3Arussian.md) | 1,469.49 | — | 37 / 172 | — | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1469.492068578255 \| rating \| reported \| Higher is better \| ### Configuration category russian config text_style_control ### Reported statistics lower 1461.8446262874982 rank 45 upper 1477.1395108690122 variance 15.22426149029761 votes 7663 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label GPT-5.4 Observed 2026-10-22T06:45:03.380Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/10428/row` |  |  |  |  |  |  |  |

---
Cite as: GPT-5.4 — Benchize, https://benchize.com/models/gpt-5-4 (retrieved 2026-10-22)