# Arena text style control / polish

> Source: Benchize (https://benchize.com) — https://benchize.com/benchmarks/lmarena%3Atext_style_control%3Apolish. When citing or reusing this content, credit "Benchize" and link to https://benchize.com/benchmarks/lmarena%3Atext_style_control%3Apolish.

Human pairwise preferences on polish prompts in Arena’s text style control evaluation. The original organizer publishes model ratings and uncertainty, adjusting for response style; these are preference ratings rather than task accuracy.

Canonical URL: https://benchize.com/benchmarks/lmarena%3Atext_style_control%3Apolish
Last updated: Wed, 21 Oct 2026 18:52:20 GMT

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

Human pairwise preferences on polish prompts in Arena’s text style control evaluation. The original organizer publishes model ratings and uncertainty, adjusting for response style; these are preference ratings rather than task accuracy.

Language & multilingual · Models tested: 117 · Score publishers: [Arena](https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset)

## Model results

| # | Model | Score |  |
| --- | --- | --- | --- |
| 1 | [Claude Fable 5.1](https://benchize.com/models/claude-fable-5-1-max.md)Max | 1,514.16 |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1514.1614468427624 \| rating \| reported \| Higher is better \| ### Configuration category polish config text_style_control Reasoning effort max thinkingEnabled true ### Reported statistics lower 1477.363009234733 rank 1 upper 1550.9598844507918 variance 352.50280520964986 votes 240 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label Claude Fable 5.1 (Max) Observed 2026-10-21T18:45:05.190Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/10148/row` |  |  |  |
| 2 | [Claude Fable 5](https://benchize.com/models/claude-fable-5-high.md)High | 1,513.25 |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1513.2494994206327 \| rating \| reported \| Higher is better \| ### Configuration category polish config text_style_control Reasoning effort high thinkingEnabled true ### Reported statistics lower 1490.562285489193 rank 2 upper 1535.9367133520725 variance 133.9880758836052 votes 646 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label Claude Fable 5 (High) Observed 2026-10-21T18:45:05.190Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/10149/row` |  |  |  |
| 3 | [Muse Spark 1.1](https://benchize.com/models/muse-spark-1-1.md) | 1,510.83 |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1510.8337316536606 \| rating \| reported \| Higher is better \| ### Configuration category polish config text_style_control ### Reported statistics lower 1487.48652469062 rank 3 upper 1534.1809386167015 variance 141.89715376841275 votes 671 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label Muse Spark 1.1 Observed 2026-10-21T18:45:05.190Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/10150/row` |  |  |  |
| 4 | [Gemini 3.5 Flash](https://benchize.com/models/gemini-3-5-flash-high.md)High | 1,505.41 |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1505.409734851644 \| rating \| reported \| Higher is better \| ### Configuration category polish config text_style_control Reasoning effort high thinkingEnabled true ### Reported statistics lower 1483.751668405633 rank 4 upper 1527.0678012976553 variance 122.10773668923001 votes 797 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label Gemini 3.5 Flash (High) Observed 2026-10-21T18:45:05.190Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/10151/row` |  |  |  |
| 5 | [Gemini 3 Pro](https://benchize.com/models/gemini-3-pro.md) | 1,505.24 |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1505.2375645399566 \| rating \| reported \| Higher is better \| ### Configuration category polish config text_style_control ### Reported statistics lower 1488.6276971953855 rank 5 upper 1521.8474318845279 variance 71.81846951424653 votes 1356 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label Gemini 3 Pro Observed 2026-10-21T18:45:05.190Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/10152/row` |  |  |  |
| 6 | [Claude Opus 4.6](https://benchize.com/models/claude-opus-4-6-high.md)High | 1,503.36 |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1503.3583578981372 \| rating \| reported \| Higher is better \| ### Configuration category polish config text_style_control Reasoning effort high thinkingEnabled true ### Reported statistics lower 1488.0583019905291 rank 6 upper 1518.6584138057456 variance 60.93823250554553 votes 1561 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label Claude Opus 4.6 (High) Observed 2026-10-21T18:45:05.190Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/10153/row` |  |  |  |
| 7 | [Claude Opus 4.7](https://benchize.com/models/claude-opus-4-7.md) | 1,501.4 |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1501.4022553742304 \| rating \| reported \| Higher is better \| ### Configuration category polish config text_style_control ### Reported statistics lower 1483.4933356784604 rank 7 upper 1519.3111750700007 variance 83.49156391883125 votes 1122 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label Claude Opus 4.7 Observed 2026-10-21T18:45:05.190Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/10154/row` |  |  |  |
| 8 | [Claude Opus 5](https://benchize.com/models/claude-opus-5-max.md)Max | 1,500.54 |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1500.5448048923674 \| rating \| reported \| Higher is better \| ### Configuration category polish config text_style_control Reasoning effort max thinkingEnabled true ### Reported statistics lower 1475.1677182786627 rank 8 upper 1525.9218915060721 variance 167.64374032339708 votes 526 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label Claude Opus 5 (Max) Observed 2026-10-21T18:45:05.190Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/10155/row` |  |  |  |
| 9 | [Claude Opus 5](https://benchize.com/models/claude-opus-5-high.md)High | 1,500.15 |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1500.1509689298591 \| rating \| reported \| Higher is better \| ### Configuration category polish config text_style_control Reasoning effort high thinkingEnabled true ### Reported statistics lower 1480.7121726477226 rank 9 upper 1519.5897652119959 variance 98.3654435817 votes 1009 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label Claude Opus 5 (High) Observed 2026-10-21T18:45:05.190Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/10156/row` |  |  |  |
| 10 | [Gemini 3.7 Flash](https://benchize.com/models/gemini-3-7-flash-high.md)High | 1,499.38 |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1499.3759652937265 \| rating \| reported \| Higher is better \| ### Configuration category polish config text_style_control Reasoning effort high thinkingEnabled true ### Reported statistics lower 1471.4731485531336 rank 10 upper 1527.2787820343194 variance 202.67487389554566 votes 453 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label Gemini 3.7 Flash (High) Observed 2026-10-21T18:45:05.190Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/10157/row` |  |  |  |
| 11 | [GPT-5.6 Sol](https://benchize.com/models/gpt-5-6-sol-xhigh.md)Extra high | 1,496.59 |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1496.5905376527385 \| rating \| reported \| Higher is better \| ### Configuration category polish config text_style_control Reasoning effort xhigh thinkingEnabled true ### Reported statistics lower 1472.8839216250597 rank 11 upper 1520.2971536804173 variance 146.2995361179603 votes 631 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label GPT-5.6 Sol (xHigh) Observed 2026-10-21T18:45:05.190Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/10158/row` |  |  |  |
| 12 | [Gemini 3 Flash](https://benchize.com/models/gemini-3-flash.md) | 1,496.3 |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1496.3006716225048 \| rating \| reported \| Higher is better \| ### Configuration category polish config text_style_control ### Reported statistics lower 1477.1270016373137 rank 12 upper 1515.4743416076958 variance 95.7005236449697 votes 972 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label Gemini 3 Flash Observed 2026-10-21T18:45:05.190Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/10159/row` |  |  |  |
| 13 | [Gemini 3.5 Flash](https://benchize.com/models/gemini-3-5-flash-medium.md)Medium | 1,496.24 |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1496.2406890989455 \| rating \| reported \| Higher is better \| ### Configuration category polish config text_style_control Reasoning effort medium thinkingEnabled true ### Reported statistics lower 1473.4317402029587 rank 13 upper 1519.0496379949325 variance 135.42983903332205 votes 682 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label Gemini 3.5 Flash (Medium) Observed 2026-10-21T18:45:05.190Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/10160/row` |  |  |  |
| 14 | [Gemini 3.1 Pro Preview](https://benchize.com/models/gemini-3-1-pro-preview.md) | 1,495.99 |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1495.9948183179138 \| rating \| reported \| Higher is better \| ### Configuration category polish config text_style_control ### Reported statistics lower 1483.6189910717258 rank 14 upper 1508.370645564102 variance 39.87055625909736 votes 2473 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label Gemini 3.1 Pro Preview Observed 2026-10-21T18:45:05.190Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/10161/row` |  |  |  |
| 15 | [Claude Opus 4.6](https://benchize.com/models/claude-opus-4-6.md) | 1,495.12 |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1495.1159746172993 \| rating \| reported \| Higher is better \| ### Configuration category polish config text_style_control ### Reported statistics lower 1479.6307381530198 rank 15 upper 1510.6012110815789 variance 62.42226184044334 votes 1614 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label Claude Opus 4.6 Observed 2026-10-21T18:45:05.190Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/10162/row` |  |  |  |
| 16 | [Gemini 3.8 Flash](https://benchize.com/models/gemini-3-8-flash-high.md)High | 1,494.8 |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1494.7995332596417 \| rating \| reported \| Higher is better \| ### Configuration category polish config text_style_control Reasoning effort high thinkingEnabled true ### Reported statistics lower 1470.2327607065142 rank 16 upper 1519.366305812769 variance 157.10862509468257 votes 596 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label Gemini 3.8 Flash (High) Observed 2026-10-21T18:45:05.190Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/10163/row` |  |  |  |
| 17 | [Claude Opus 4.7](https://benchize.com/models/claude-opus-4-7-high.md)High | 1,490.63 |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1490.6331103908071 \| rating \| reported \| Higher is better \| ### Configuration category polish config text_style_control Reasoning effort high thinkingEnabled true ### Reported statistics lower 1473.3772309045844 rank 17 upper 1507.8889898770296 variance 77.51361936745565 votes 1195 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label Claude Opus 4.7 (High) Observed 2026-10-21T18:45:05.190Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/10164/row` |  |  |  |
| 18 | [Muse Spark 1.3](https://benchize.com/models/muse-spark-1-3-max.md)Max | 1,488.22 |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1488.2198591837996 \| rating \| reported \| Higher is better \| ### Configuration category polish config text_style_control Reasoning effort max thinkingEnabled true ### Reported statistics lower 1452.6475379208252 rank 18 upper 1523.792180446774 variance 329.40351546124555 votes 281 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label Muse Spark 1.3 (Max) Observed 2026-10-21T18:45:05.190Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/10165/row` |  |  |  |
| 19 | [Claude Opus 4.8](https://benchize.com/models/claude-opus-4-8-high.md)High | 1,485.05 |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1485.0451954562166 \| rating \| reported \| Higher is better \| ### Configuration category polish config text_style_control Reasoning effort high thinkingEnabled true ### Reported statistics lower 1466.74829438975 rank 23 upper 1503.342096522683 variance 87.14829554663056 votes 1075 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label Claude Opus 4.8 (High) Observed 2026-10-21T18:45:05.190Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/10170/row` |  |  |  |
| 20 | [Claude Opus 4.8](https://benchize.com/models/claude-opus-4-8.md) | 1,484.41 |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1484.4074998853657 \| rating \| reported \| Higher is better \| ### Configuration category polish config text_style_control ### Reported statistics lower 1466.8803027394758 rank 24 upper 1501.9346970312556 variance 79.97030662829823 votes 1091 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label Claude Opus 4.8 Observed 2026-10-21T18:45:05.190Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/10171/row` |  |  |  |
| 21 | [GPT-5.4](https://benchize.com/models/gpt-5-4-high.md)High | 1,482.66 |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1482.6649787852148 \| rating \| reported \| Higher is better \| ### Configuration category polish config text_style_control Reasoning effort high thinkingEnabled true ### Reported statistics lower 1465.8361870194349 rank 25 upper 1499.4937705509947 variance 73.72413593771297 votes 1317 ### 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 (High) Observed 2026-10-21T18:45:05.190Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/10172/row` |  |  |  |
| 22 | [Gemini 3 Flash](https://benchize.com/models/gemini-3-flash-minimal.md)Minimal | 1,481.16 |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1481.1622350623313 \| rating \| reported \| Higher is better \| ### Configuration category polish config text_style_control Reasoning effort minimal thinkingEnabled true ### Reported statistics lower 1467.629174323691 rank 26 upper 1494.6952958009717 variance 47.675568450487674 votes 1910 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label Gemini 3 Flash (Minimal) Observed 2026-10-21T18:45:05.190Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/10173/row` |  |  |  |
| 23 | [GPT-5.5](https://benchize.com/models/gpt-5-5-high.md)High | 1,479.56 |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1479.5634553207024 \| rating \| reported \| Higher is better \| ### Configuration category polish config text_style_control Reasoning effort high thinkingEnabled true ### Reported statistics lower 1461.955955472767 rank 29 upper 1497.1709551686374 variance 80.70477007977365 votes 1168 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label GPT-5.5 (High) Observed 2026-10-21T18:45:05.190Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/10176/row` |  |  |  |
| 24 | [GPT-5.3 Chat](https://benchize.com/models/gpt-5-3-chat.md) | 1,474.31 |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1474.3099408468734 \| rating \| reported \| Higher is better \| ### Configuration category polish config text_style_control ### Reported statistics lower 1452.5387577873203 rank 37 upper 1496.0811239064265 variance 123.38656586898514 votes 745 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label GPT-5.3 Chat Observed 2026-10-21T18:45:05.190Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/10184/row` |  |  |  |
| 25 | [Qwen3.8 Max](https://benchize.com/models/qwen3-8-max.md) | 1,473.99 |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1473.9872655529718 \| rating \| reported \| Higher is better \| ### Configuration category polish config text_style_control ### Reported statistics lower 1446.4803869203292 rank 38 upper 1501.4941441856147 variance 196.96381177768717 votes 432 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label Qwen3.8-Max Observed 2026-10-21T18:45:05.190Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/10185/row` |  |  |  |
| 26 | [DeepSeek V4.1 Flash](https://benchize.com/models/deepseek-v4-1-flash-max.md)Max | 1,472.2 |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1472.2005522845932 \| rating \| reported \| Higher is better \| ### Configuration category polish config text_style_control Reasoning effort max thinkingEnabled true ### Reported statistics lower 1434.3653433973989 rank 39 upper 1510.0357611717877 variance 372.6456792471809 votes 222 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label DeepSeek-V4.1-Flash-20260910 (Max) Observed 2026-10-21T18:45:05.190Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/10186/row` |  |  |  |
| 27 | [Claude Sonnet 4.6](https://benchize.com/models/claude-sonnet-4-6.md) | 1,472.11 |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1472.1083200344895 \| rating \| reported \| Higher is better \| ### Configuration category polish config text_style_control ### Reported statistics lower 1456.1905800093155 rank 40 upper 1488.0260600596635 variance 65.95787156277363 votes 1407 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label Claude Sonnet 4.6 Observed 2026-10-21T18:45:05.190Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/10187/row` |  |  |  |
| 28 | [GPT-5.4](https://benchize.com/models/gpt-5-4.md) | 1,472.04 |  |
| ### 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 2026-10-21T18:45:05.190Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/10188/row` |  |  |  |
| 29 | [Gemini 3.6 Flash](https://benchize.com/models/gemini-3-6-flash-high.md)High | 1,471.92 |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1471.918814145651 \| rating \| reported \| Higher is better \| ### Configuration category polish config text_style_control Reasoning effort high thinkingEnabled true ### Reported statistics lower 1446.6255028639089 rank 42 upper 1497.212125427393 variance 166.53870976013658 votes 529 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label Gemini 3.6 Flash (High) Observed 2026-10-21T18:45:05.190Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/10189/row` |  |  |  |
| 30 | [GPT-5.5](https://benchize.com/models/gpt-5-5.md) | 1,471.06 |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1471.064003952711 \| rating \| reported \| Higher is better \| ### Configuration category polish config text_style_control ### Reported statistics lower 1453.4345303445818 rank 43 upper 1488.69347756084 variance 80.90633121600459 votes 1196 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label GPT-5.5 Observed 2026-10-21T18:45:05.190Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/10190/row` |  |  |  |
| 31 | [MiMo-V2.5-Pro](https://benchize.com/models/mimo-v2-5-pro.md) | 1,467.83 |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1467.831816106554 \| rating \| reported \| Higher is better \| ### Configuration category polish config text_style_control ### Reported statistics lower 1451.5639726562385 rank 46 upper 1484.0996595568693 variance 68.89120588728565 votes 1376 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label MiMo-V2.5-Pro Observed 2026-10-21T18:45:05.190Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/10193/row` |  |  |  |
| 32 | [DeepSeek V4 Pro](https://benchize.com/models/deepseek-v4-pro.md) | 1,465.38 |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1465.384475711231 \| rating \| reported \| Higher is better \| ### Configuration category polish config text_style_control ### Reported statistics lower 1447.2990324760042 rank 47 upper 1483.469918946458 variance 85.14558460254838 votes 1125 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label DeepSeek-V4-Pro Observed 2026-10-21T18:45:05.190Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/10194/row` |  |  |  |
| 33 | [GPT-5.1](https://benchize.com/models/gpt-5-1.md) | 1,463.38 |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1463.376971995403 \| rating \| reported \| Higher is better \| ### Configuration category polish config text_style_control ### Reported statistics lower 1447.1633444463914 rank 49 upper 1479.5905995444148 variance 68.43278310883207 votes 1323 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label GPT-5.1 Observed 2026-10-21T18:45:05.190Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/10196/row` |  |  |  |
| 34 | [Hy3](https://benchize.com/models/hy3.md) | 1,463.13 |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1463.1285963352104 \| rating \| reported \| Higher is better \| ### Configuration category polish config text_style_control ### Reported statistics lower 1427.0334232221896 rank 50 upper 1499.2237694482312 variance 339.158008160951 votes 241 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label Hy3 Observed 2026-10-21T18:45:05.190Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/10197/row` |  |  |  |
| 35 | [GPT-5.6 Terra](https://benchize.com/models/gpt-5-6-terra-xhigh.md)Extra high | 1,462.72 |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1462.7220703392088 \| rating \| reported \| Higher is better \| ### Configuration category polish config text_style_control Reasoning effort xhigh thinkingEnabled true ### Reported statistics lower 1439.9747745888408 rank 51 upper 1485.469366089577 variance 134.6986882085643 votes 654 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label GPT-5.6 Terra (xHigh) Observed 2026-10-21T18:45:05.190Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/10198/row` |  |  |  |
| 36 | [GPT-5.4 Mini](https://benchize.com/models/gpt-5-4-mini-high.md)High | 1,461.88 |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1461.8839524135249 \| rating \| reported \| Higher is better \| ### Configuration category polish config text_style_control Reasoning effort high thinkingEnabled true ### Reported statistics lower 1443.9773128603501 rank 53 upper 1479.7905919666996 variance 83.47030517676663 votes 1189 ### 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 mini (High) Observed 2026-10-21T18:45:05.190Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/10200/row` |  |  |  |
| 37 | [GPT-6 Astra](https://benchize.com/models/gpt-6-astra-max.md)Max | 1,460.42 |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1460.4248118919365 \| rating \| reported \| Higher is better \| ### Configuration category polish config text_style_control Reasoning effort max thinkingEnabled true ### Reported statistics lower 1418.4613281319241 rank 56 upper 1502.388295651949 variance 458.40240686444173 votes 184 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label GPT-6 Astra (Max) Observed 2026-10-21T18:45:05.190Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/10203/row` |  |  |  |
| 38 | [Gemini 3.5 Flash-Lite](https://benchize.com/models/gemini-3-5-flash-lite.md) | 1,458.7 |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1458.6989049729495 \| rating \| reported \| Higher is better \| ### Configuration category polish config text_style_control ### Reported statistics lower 1433.2510464677644 rank 58 upper 1484.1467634781347 variance 168.58009749090795 votes 522 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label Gemini 3.5 Flash-Lite Observed 2026-10-21T18:45:05.190Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/10205/row` |  |  |  |
| 39 | [GPT-5 Chat](https://benchize.com/models/gpt-5-chat.md) | 1,458.17 |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1458.1654356245485 \| rating \| reported \| Higher is better \| ### Configuration category polish config text_style_control ### Reported statistics lower 1443.4739060366485 rank 60 upper 1472.8569652124484 variance 56.187258983330274 votes 1796 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label GPT-5 Chat Observed 2026-10-21T18:45:05.190Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/10207/row` |  |  |  |
| 40 | [GPT-5.1](https://benchize.com/models/gpt-5-1-high.md)High | 1,457.1 |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1457.0975541315904 \| rating \| reported \| Higher is better \| ### Configuration category polish config text_style_control Reasoning effort high thinkingEnabled true ### Reported statistics lower 1439.992801665413 rank 63 upper 1474.202306597768 variance 76.16183605902583 votes 1198 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label GPT-5.1 (High) Observed 2026-10-21T18:45:05.190Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/10210/row` |  |  |  |
| 41 | [Gemini 2.5 Pro](https://benchize.com/models/gemini-2-5-pro.md) | 1,456.26 |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1456.261610788875 \| rating \| reported \| Higher is better \| ### Configuration category polish config text_style_control ### Reported statistics lower 1447.7202353701186 rank 64 upper 1464.8029862076312 variance 18.991507510407548 votes 6495 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label Gemini 2.5 Pro Observed 2026-10-21T18:45:05.190Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/10211/row` |  |  |  |
| 42 | [MiMo-V2.6-Flash](https://benchize.com/models/mimo-v2-6-flash.md) | 1,456.24 |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1456.237866989056 \| rating \| reported \| Higher is better \| ### Configuration category polish config text_style_control ### Reported statistics lower 1415.0477871141966 rank 65 upper 1497.4279468639158 variance 441.66103537477187 votes 200 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label MiMo-V2.6-Flash Observed 2026-10-21T18:45:05.190Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/10212/row` |  |  |  |
| 43 | [Gemini 3.1 Flash Lite Preview](https://benchize.com/models/gemini-3-1-flash-lite-preview.md) | 1,453.35 |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1453.3466395034793 \| rating \| reported \| Higher is better \| ### Configuration category polish config text_style_control ### Reported statistics lower 1436.8274786690015 rank 67 upper 1469.8658003379571 variance 71.03620978710286 votes 1266 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label Gemini 3.1 Flash-Lite Preview Observed 2026-10-21T18:45:05.190Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/10214/row` |  |  |  |
| 44 | [GPT-5.2](https://benchize.com/models/gpt-5-2.md) | 1,453.34 |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1453.339442207522 \| rating \| reported \| Higher is better \| ### Configuration category polish config text_style_control ### Reported statistics lower 1438.1974761515878 rank 68 upper 1468.4814082634564 variance 59.68543377425457 votes 1633 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label GPT-5.2 Observed 2026-10-21T18:45:05.190Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/10215/row` |  |  |  |
| 45 | [GPT-6 Sol](https://benchize.com/models/gpt-6-sol-max.md)Max | 1,451.65 |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1451.6505749640135 \| rating \| reported \| Higher is better \| ### Configuration category polish config text_style_control Reasoning effort max thinkingEnabled true ### Reported statistics lower 1410.174155378732 rank 69 upper 1493.1269945492947 variance 447.82293964652484 votes 196 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label GPT-6 Sol (Max) Observed 2026-10-21T18:45:05.190Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/10216/row` |  |  |  |
| 46 | [GPT-5.2](https://benchize.com/models/gpt-5-2-high.md)High | 1,450.81 |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1450.8087342303809 \| rating \| reported \| Higher is better \| ### Configuration category polish config text_style_control Reasoning effort high thinkingEnabled true ### Reported statistics lower 1433.5484867088762 rank 71 upper 1468.0689817518855 variance 77.55286686888829 votes 1183 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label GPT-5.2 (High) Observed 2026-10-21T18:45:05.190Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/10218/row` |  |  |  |
| 47 | [MiMo-V2-Pro](https://benchize.com/models/mimo-v2-pro.md) | 1,448.88 |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1448.8784534293097 \| rating \| reported \| Higher is better \| ### Configuration category polish config text_style_control ### Reported statistics lower 1425.2962586492083 rank 73 upper 1472.4606482094114 variance 144.76789589694533 votes 588 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label MiMo-V2-Pro Observed 2026-10-21T18:45:05.190Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/10220/row` |  |  |  |
| 48 | [GPT-6 Luna](https://benchize.com/models/gpt-6-luna-max.md)Max | 1,448.74 |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1448.7374608772088 \| rating \| reported \| Higher is better \| ### Configuration category polish config text_style_control Reasoning effort max thinkingEnabled true ### Reported statistics lower 1427.934847072341 rank 74 upper 1469.5400746820767 variance 112.65218796131362 votes 883 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label GPT-6 Luna (Max) Observed 2026-10-21T18:45:05.190Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/10221/row` |  |  |  |
| 49 | [GPT-5](https://benchize.com/models/gpt-5-high.md)High | 1,448.16 |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1448.1551941273901 \| rating \| reported \| Higher is better \| ### Configuration category polish config text_style_control Reasoning effort high thinkingEnabled true ### Reported statistics lower 1433.1056180026 rank 77 upper 1463.2047702521802 variance 58.95930481298967 votes 1919 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label GPT-5 (High) Observed 2026-10-21T18:45:05.190Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/10224/row` |  |  |  |
| 50 | [Qwen3.5 397B A17B](https://benchize.com/models/qwen3-5-397b-a17b.md) | 1,445.41 |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1445.4098953952202 \| rating \| reported \| Higher is better \| ### Configuration category polish config text_style_control ### Reported statistics lower 1430.7690833281663 rank 81 upper 1460.050707462274 variance 55.79999369720044 votes 1687 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label Qwen3.5-397B-A17B Observed 2026-10-21T18:45:05.190Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/10228/row` |  |  |  |
| 51 | [Claude Sonnet 5](https://benchize.com/models/claude-sonnet-5-high.md)High | 1,445.4 |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1445.4042961856533 \| rating \| reported \| Higher is better \| ### Configuration category polish config text_style_control Reasoning effort high thinkingEnabled true ### Reported statistics lower 1423.4488927583611 rank 82 upper 1467.3596996129456 variance 125.48351086269325 votes 732 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label Claude Sonnet 5 (High) Observed 2026-10-21T18:45:05.190Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/10229/row` |  |  |  |
| 52 | [Qwen3.8 27B](https://benchize.com/models/qwen3-8-27b.md) | 1,439.05 |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1439.0545262458638 \| rating \| reported \| Higher is better \| ### Configuration category polish config text_style_control ### Reported statistics lower 1409.3478343551978 rank 89 upper 1468.7612181365298 variance 229.7271907049892 votes 389 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label Qwen3.8-27B Observed 2026-10-21T18:45:05.190Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/10236/row` |  |  |  |
| 53 | [Gemma 4 31B](https://benchize.com/models/gemma-4-31b-it.md) | 1,437.7 |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1437.6951113944267 \| rating \| reported \| Higher is better \| ### Configuration category polish config text_style_control ### Reported statistics lower 1399.6804723165108 rank 91 upper 1475.7097504723426 variance 376.188539738945 votes 202 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label Gemma 4 31B Observed 2026-10-21T18:45:05.190Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/10238/row` |  |  |  |
| 54 | [DeepSeek V4 Flash](https://benchize.com/models/deepseek-v4-flash.md) | 1,436.94 |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1436.9424332306005 \| rating \| reported \| Higher is better \| ### Configuration category polish config text_style_control ### Reported statistics lower 1418.2173287880444 rank 92 upper 1455.6675376731569 variance 91.2750995782597 votes 1026 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label DeepSeek-V4-Flash Observed 2026-10-21T18:45:05.190Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/10239/row` |  |  |  |
| 55 | [GPT-5.6 Luna](https://benchize.com/models/gpt-5-6-luna-xhigh.md)Extra high | 1,436.13 |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1436.1305507308848 \| rating \| reported \| Higher is better \| ### Configuration category polish config text_style_control Reasoning effort xhigh thinkingEnabled true ### Reported statistics lower 1412.3524483614574 rank 93 upper 1459.9086531003124 variance 147.18318708641414 votes 611 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label GPT-5.6 Luna (xHigh) Observed 2026-10-21T18:45:05.190Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/10240/row` |  |  |  |
| 56 | [MiniMax M3](https://benchize.com/models/minimax-m3.md) | 1,432.78 |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1432.7809689398803 \| rating \| reported \| Higher is better \| ### Configuration category polish config text_style_control ### Reported statistics lower 1415.0205077813696 rank 96 upper 1450.541430098391 variance 82.11307091558766 votes 1138 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label MiniMax-M3 Observed 2026-10-21T18:45:05.190Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/10243/row` |  |  |  |
| 57 | [DeepSeek V3.2 Exp](https://benchize.com/models/deepseek-v3-2-exp-thinking.md)Thinking | 1,429.46 |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1429.4596084329698 \| rating \| reported \| Higher is better \| ### Configuration category polish config text_style_control thinkingEnabled true ### Reported statistics lower 1399.954957568028 rank 98 upper 1458.964259297912 variance 226.61297785428897 votes 397 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label DeepSeek-V3.2-Exp (Thinking) Observed 2026-10-21T18:45:05.190Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/10245/row` |  |  |  |
| 58 | [GPT-4o (2024-05-13)](https://benchize.com/models/gpt-4o-2024-05-13.md) | 1,424.5 |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1424.4950796563962 \| rating \| reported \| Higher is better \| ### Configuration category polish config text_style_control ### Reported statistics lower 1367.2236895711699 rank 103 upper 1481.7664697416226 variance 853.845446585181 votes 166 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label GPT-4o (2024-05-13) Observed 2026-10-21T18:45:05.190Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/10250/row` |  |  |  |
| 59 | [Mistral Medium 3.5](https://benchize.com/models/mistral-medium-3-5.md) | 1,422.28 |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1422.2813516940612 \| rating \| reported \| Higher is better \| ### Configuration category polish config text_style_control ### Reported statistics lower 1384.0619482502361 rank 106 upper 1460.5007551378865 variance 380.25210415712314 votes 233 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label Mistral Medium 3.5 Observed 2026-10-21T18:45:05.190Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/10253/row` |  |  |  |
| 60 | [MiMo-V2-Omni](https://benchize.com/models/mimo-v2-omni.md) | 1,421.71 |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1421.7149051375677 \| rating \| reported \| Higher is better \| ### Configuration category polish config text_style_control ### Reported statistics lower 1395.0209651493399 rank 107 upper 1448.4088451257956 variance 185.49370573920552 votes 428 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label MiMo-V2-Omni Observed 2026-10-21T18:45:05.190Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/10254/row` |  |  |  |
| 61 | [MiMo-V2.5](https://benchize.com/models/mimo-v2-5.md) | 1,420.05 |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1420.0464603373139 \| rating \| reported \| Higher is better \| ### Configuration category polish config text_style_control ### Reported statistics lower 1400.920761131638 rank 108 upper 1439.17215954299 variance 95.22225466415276 votes 945 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label MiMo-V2.5 Observed 2026-10-21T18:45:05.190Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/10255/row` |  |  |  |
| 62 | [DeepSeek V3.2](https://benchize.com/models/deepseek-v3-2-thinking.md)Thinking | 1,418.52 |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1418.5184329545648 \| rating \| reported \| Higher is better \| ### Configuration category polish config text_style_control thinkingEnabled true ### Reported statistics lower 1401.124911305064 rank 112 upper 1435.9119546040656 variance 78.75513170722776 votes 1119 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label DeepSeek-V3.2 (Thinking) Observed 2026-10-21T18:45:05.190Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/10259/row` |  |  |  |
| 63 | [DeepSeek V3.1 Terminus](https://benchize.com/models/deepseek-v3-1-terminus-thinking.md)Thinking | 1,417.47 |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1417.4739850887138 \| rating \| reported \| Higher is better \| ### Configuration category polish config text_style_control thinkingEnabled true ### Reported statistics lower 1378.6819436065055 rank 114 upper 1456.2660265709221 variance 391.7320353014905 votes 205 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label DeepSeek-V3.1-Terminus (Thinking) Observed 2026-10-21T18:45:05.190Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/10261/row` |  |  |  |
| 64 | [Mistral Large 3](https://benchize.com/models/mistral-large-3.md) | 1,414.61 |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1414.6072918550187 \| rating \| reported \| Higher is better \| ### Configuration category polish config text_style_control ### Reported statistics lower 1400.7795378331937 rank 115 upper 1428.4350458768438 variance 49.77452322489019 votes 1883 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label Mistral Large 3 Observed 2026-10-21T18:45:05.190Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/10262/row` |  |  |  |
| 65 | [DeepSeek V3.2 Exp](https://benchize.com/models/deepseek-v3-2-exp.md) | 1,414.56 |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1414.560041627136 \| rating \| reported \| Higher is better \| ### Configuration category polish config text_style_control ### Reported statistics lower 1386.852454117235 rank 116 upper 1442.2676291370367 variance 199.84866204555476 votes 440 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label DeepSeek-V3.2-Exp Observed 2026-10-21T18:45:05.190Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/10263/row` |  |  |  |
| 66 | [R1 0528](https://benchize.com/models/deepseek-r1-0528.md) | 1,411.82 |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1411.8209928700458 \| rating \| reported \| Higher is better \| ### Configuration category polish config text_style_control ### Reported statistics lower 1397.4493364432365 rank 119 upper 1426.192649296855 variance 53.76720618156422 votes 1980 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label DeepSeek-R1 (0528) Observed 2026-10-21T18:45:05.190Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/10266/row` |  |  |  |
| 67 | [Qwen3 VL 235B A22B Instruct](https://benchize.com/models/qwen3-vl-235b-a22b-instruct.md) | 1,404.07 |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1404.072323497317 \| rating \| reported \| Higher is better \| ### Configuration category polish config text_style_control ### Reported statistics lower 1377.5765982642404 rank 123 upper 1430.5680487303935 variance 182.74918159863074 votes 540 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label Qwen3-VL-235B-A22B-Instruct Observed 2026-10-21T18:45:05.190Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/10270/row` |  |  |  |
| 68 | [DeepSeek V3.2](https://benchize.com/models/deepseek-v3-2.md) | 1,403.5 |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1403.4974043310087 \| rating \| reported \| Higher is better \| ### Configuration category polish config text_style_control ### Reported statistics lower 1387.0765074860144 rank 124 upper 1419.9183011760028 variance 70.19360763190936 votes 1338 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label DeepSeek-V3.2 Observed 2026-10-21T18:45:05.190Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/10271/row` |  |  |  |
| 69 | [Qwen3 235B A22B Instruct 2507](https://benchize.com/models/qwen3-235b-a22b-2507.md) | 1,403.41 |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1403.4145826796482 \| rating \| reported \| Higher is better \| ### Configuration category polish config text_style_control ### Reported statistics lower 1393.6797137960664 rank 125 upper 1413.14945156323 variance 24.669709244314134 votes 3942 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label Qwen3-235B-A22B-Instruct (2507) Observed 2026-10-21T18:45:05.190Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/10272/row` |  |  |  |
| 70 | [GPT-5.4 Nano](https://benchize.com/models/gpt-5-4-nano-high.md)High | 1,401.76 |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1401.7632541319765 \| rating \| reported \| Higher is better \| ### Configuration category polish config text_style_control Reasoning effort high thinkingEnabled true ### Reported statistics lower 1383.282416003712 rank 127 upper 1420.2440922602414 variance 88.90929041936498 votes 1129 ### 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 nano (High) Observed 2026-10-21T18:45:05.190Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/10274/row` |  |  |  |
| 71 | [DeepSeek V3.1](https://benchize.com/models/deepseek-v3-1.md) | 1,401.23 |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1401.2311756990907 \| rating \| reported \| Higher is better \| ### Configuration category polish config text_style_control ### Reported statistics lower 1382.0185227965198 rank 128 upper 1420.4438286016614 variance 96.09006598382894 votes 1007 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label DeepSeek-V3.1 Observed 2026-10-21T18:45:05.190Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/10275/row` |  |  |  |
| 72 | [MiniMax M2.7](https://benchize.com/models/minimax-m2-7.md) | 1,401.18 |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1401.1841457225771 \| rating \| reported \| Higher is better \| ### Configuration category polish config text_style_control ### Reported statistics lower 1386.168246627563 rank 129 upper 1416.2000448175913 variance 58.69572892907039 votes 1680 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label MiniMax-M2.7 Observed 2026-10-21T18:45:05.190Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/10276/row` |  |  |  |
| 73 | [Gemini 2.5 Flash](https://benchize.com/models/gemini-2-5-flash.md) | 1,399.66 |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1399.6583854376088 \| rating \| reported \| Higher is better \| ### Configuration category polish config text_style_control ### Reported statistics lower 1391.1432599205552 rank 131 upper 1408.1735109546623 variance 18.87495505107994 votes 6188 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label Gemini 2.5 Flash Observed 2026-10-21T18:45:05.190Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/10278/row` |  |  |  |
| 74 | [DeepSeek V3.1](https://benchize.com/models/deepseek-v3-1-thinking.md)Thinking | 1,399.18 |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1399.181160384599 \| rating \| reported \| Higher is better \| ### Configuration category polish config text_style_control thinkingEnabled true ### Reported statistics lower 1378.5904325418658 rank 132 upper 1419.7718882273323 variance 110.3690272064152 votes 787 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label DeepSeek-V3.1 (Thinking) Observed 2026-10-21T18:45:05.190Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/10279/row` |  |  |  |
| 75 | [GPT-5 Mini](https://benchize.com/models/gpt-5-mini-high.md)High | 1,399.04 |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1399.0391756268627 \| rating \| reported \| Higher is better \| ### Configuration category polish config text_style_control Reasoning effort high thinkingEnabled true ### Reported statistics lower 1382.846594262235 rank 134 upper 1415.2317569914906 variance 68.25523934751291 votes 1562 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label GPT-5 mini (High) Observed 2026-10-21T18:45:05.190Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/10281/row` |  |  |  |
| 76 | [DeepSeek V3.1 Terminus](https://benchize.com/models/deepseek-v3-1-terminus.md) | 1,397.22 |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1397.2191346567756 \| rating \| reported \| Higher is better \| ### Configuration category polish config text_style_control ### Reported statistics lower 1359.3291621261656 rank 136 upper 1435.1091071873857 variance 373.72521361845077 votes 229 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label DeepSeek-V3.1-Terminus Observed 2026-10-21T18:45:05.190Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/10283/row` |  |  |  |
| 77 | [DeepSeek V3 0324](https://benchize.com/models/deepseek-chat-v3-0324.md) | 1,396.15 |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1396.148074014864 \| rating \| reported \| Higher is better \| ### Configuration category polish config text_style_control ### Reported statistics lower 1384.0528692878765 rank 137 upper 1408.2432787418516 variance 38.082922196027845 votes 2736 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label DeepSeek-V3 (0324) Observed 2026-10-21T18:45:05.190Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/10284/row` |  |  |  |
| 78 | [Qwen3 235B A22B](https://benchize.com/models/qwen3-235b-a22b-off.md)Non-thinking | 1,391.31 |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1391.3145140675913 \| rating \| reported \| Higher is better \| ### Configuration category polish config text_style_control thinkingEnabled false ### Reported statistics lower 1380.2073039457523 rank 140 upper 1402.4217241894305 variance 32.11543386228253 votes 3629 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label Qwen3-235B-A22B (Non-Thinking) Observed 2026-10-21T18:45:05.190Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/10287/row` |  |  |  |
| 79 | [Qwen3.5-122B-A10B](https://benchize.com/models/qwen3-5-122b-a10b.md) | 1,386.18 |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1386.17511752762 \| rating \| reported \| Higher is better \| ### Configuration category polish config text_style_control ### Reported statistics lower 1362.5419073580215 rank 144 upper 1409.8083276972184 variance 145.3949265085425 votes 601 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label Qwen3.5-122B-A10B Observed 2026-10-21T18:45:05.190Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/10291/row` |  |  |  |
| 80 | [MiMo-V2-Flash](https://benchize.com/models/mimo-v2-flash-thinking.md)Thinking | 1,385.82 |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1385.8174290486345 \| rating \| reported \| Higher is better \| ### Configuration category polish config text_style_control thinkingEnabled true ### Reported statistics lower 1357.8718531998547 rank 145 upper 1413.7630048974142 variance 203.296519882722 votes 418 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label MiMo-V2-Flash (Thinking) Observed 2026-10-21T18:45:05.190Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/10292/row` |  |  |  |
| 81 | [Qwen3 235B A22B Thinking 2507](https://benchize.com/models/qwen3-235b-a22b-thinking-2507.md) | 1,379.8 |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1379.7950824718077 \| rating \| reported \| Higher is better \| ### Configuration category polish config text_style_control ### Reported statistics lower 1359.1782727674943 rank 149 upper 1400.4118921761215 variance 110.64880875309625 votes 783 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label Qwen3-235B-A22B-Thinking (2507) Observed 2026-10-21T18:45:05.190Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/10296/row` |  |  |  |
| 82 | [MiMo-V2-Flash](https://benchize.com/models/mimo-v2-flash-off.md)Non-thinking | 1,378.6 |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1378.5990896284802 \| rating \| reported \| Higher is better \| ### Configuration category polish config text_style_control thinkingEnabled false ### Reported statistics lower 1361.4784960598372 rank 152 upper 1395.7196831971232 variance 76.3029718198818 votes 1204 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label MiMo-V2-Flash (Non-Thinking) Observed 2026-10-21T18:45:05.190Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/10299/row` |  |  |  |
| 83 | [Qwen3.5-35B-A3B](https://benchize.com/models/qwen3-5-35b-a3b.md) | 1,373.88 |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1373.8842604911265 \| rating \| reported \| Higher is better \| ### Configuration category polish config text_style_control ### Reported statistics lower 1350.443382618438 rank 154 upper 1397.3251383638153 variance 143.03804390203553 votes 587 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label Qwen3.5-35B-A3B Observed 2026-10-21T18:45:05.190Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/10301/row` |  |  |  |
| 84 | [MiniMax M2.5](https://benchize.com/models/minimax-m2-5.md) | 1,371.38 |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1371.3793162999661 \| rating \| reported \| Higher is better \| ### Configuration category polish config text_style_control ### Reported statistics lower 1351.8427023375998 rank 155 upper 1390.9159302623325 variance 99.3579009772025 votes 928 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label MiniMax-M2.5 Observed 2026-10-21T18:45:05.190Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/10302/row` |  |  |  |
| 85 | [Gemini 2.0 Flash 001](https://benchize.com/models/gemini-2-0-flash-001.md) | 1,370.45 |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1370.4538444429747 \| rating \| reported \| Higher is better \| ### Configuration category polish config text_style_control ### Reported statistics lower 1354.1683364489677 rank 157 upper 1386.7393524369818 variance 69.0408990444277 votes 1349 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label Gemini 2.0 Flash (001) Observed 2026-10-21T18:45:05.190Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/10304/row` |  |  |  |
| 86 | [Step 3.5 Flash](https://benchize.com/models/step-3-5-flash.md) | 1,369.24 |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1369.2438254468311 \| rating \| reported \| Higher is better \| ### Configuration category polish config text_style_control ### Reported statistics lower 1352.9202666092835 rank 160 upper 1385.5673842843787 variance 69.363901986259 votes 1365 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label Step-3.5-Flash Observed 2026-10-21T18:45:05.190Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/10307/row` |  |  |  |
| 87 | [Qwen3 Next 80B A3B Instruct](https://benchize.com/models/qwen3-next-80b-a3b-instruct.md) | 1,369.2 |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1369.2034476992226 \| rating \| reported \| Higher is better \| ### Configuration category polish config text_style_control ### Reported statistics lower 1350.5615038640594 rank 161 upper 1387.8453915343855 variance 90.46617084146646 votes 1023 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label Qwen3-Next-80B-A3B-Instruct Observed 2026-10-21T18:45:05.190Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/10308/row` |  |  |  |
| 88 | [Gemma 3 27B](https://benchize.com/models/gemma-3-27b-it.md) | 1,369.01 |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1369.0066445875555 \| rating \| reported \| Higher is better \| ### Configuration category polish config text_style_control ### Reported statistics lower 1356.9656345435944 rank 162 upper 1381.0476546315163 variance 37.74241236108565 votes 2829 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label Gemma 3 27B IT Observed 2026-10-21T18:45:05.190Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/10309/row` |  |  |  |
| 89 | [Qwen3.5-27B](https://benchize.com/models/qwen3-5-27b.md) | 1,365.5 |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1365.4994076596183 \| rating \| reported \| Higher is better \| ### Configuration category polish config text_style_control ### Reported statistics lower 1340.00039771821 rank 166 upper 1390.9984176010266 variance 169.25848703346375 votes 537 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label Qwen3.5-27B Observed 2026-10-21T18:45:05.190Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/10313/row` |  |  |  |
| 90 | [Qwen3 VL 235B A22B Thinking](https://benchize.com/models/qwen3-vl-235b-a22b-thinking.md) | 1,364.51 |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1364.5051251668397 \| rating \| reported \| Higher is better \| ### Configuration category polish config text_style_control ### Reported statistics lower 1336.775224307622 rank 167 upper 1392.235026026057 variance 200.1706740990367 votes 399 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label Qwen3-VL-235B-A22B-Thinking Observed 2026-10-21T18:45:05.190Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/10314/row` |  |  |  |
| 91 | [Qwen3 235B A22B](https://benchize.com/models/qwen3-235b-a22b.md) | 1,361.41 |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1361.413959146476 \| rating \| reported \| Higher is better \| ### Configuration category polish config text_style_control ### Reported statistics lower 1347.322573080283 rank 173 upper 1375.505345212669 variance 51.69056093919494 votes 1885 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label Qwen3-235B-A22B Observed 2026-10-21T18:45:05.190Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/10320/row` |  |  |  |
| 92 | [Qwen3 Next 80B A3B Thinking](https://benchize.com/models/qwen3-next-80b-a3b-thinking.md) | 1,358.49 |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1358.4910808096847 \| rating \| reported \| Higher is better \| ### Configuration category polish config text_style_control ### Reported statistics lower 1336.1220421242376 rank 175 upper 1380.860119495132 variance 130.25621647054965 votes 709 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label Qwen3-Next-80B-A3B-Thinking Observed 2026-10-21T18:45:05.190Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/10322/row` |  |  |  |
| 93 | [Gemini 1.5 Pro 001](https://benchize.com/models/gemini-1-5-pro-001.md) | 1,357.71 |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1357.7062511775582 \| rating \| reported \| Higher is better \| ### Configuration category polish config text_style_control ### Reported statistics lower 1297.451306133675 rank 177 upper 1417.9611962214415 variance 945.1249048103454 votes 148 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label Gemini 1.5 Pro (001) Observed 2026-10-21T18:45:05.190Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/10324/row` |  |  |  |
| 94 | [MiniMax M1](https://benchize.com/models/minimax-m1.md) | 1,352.68 |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1352.6817281519518 \| rating \| reported \| Higher is better \| ### Configuration category polish config text_style_control ### Reported statistics lower 1341.8128550587116 rank 178 upper 1363.550601245192 variance 30.75196372809614 votes 3528 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label MiniMax-M1 Observed 2026-10-21T18:45:05.190Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/10325/row` |  |  |  |
| 95 | [Gemma 2 27B](https://benchize.com/models/gemma-2-27b-it.md) | 1,351.16 |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1351.1579565258326 \| rating \| reported \| Higher is better \| ### Configuration category polish config text_style_control ### Reported statistics lower 1274.0383112251684 rank 179 upper 1428.2776018264967 variance 1548.2242473252875 votes 58 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label Gemma 2 27B IT Observed 2026-10-21T18:45:05.190Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/10326/row` |  |  |  |
| 96 | [Command A](https://benchize.com/models/command-a.md) | 1,349.84 |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1349.843313097182 \| rating \| reported \| Higher is better \| ### Configuration category polish config text_style_control ### Reported statistics lower 1338.448033588928 rank 180 upper 1361.2385926054362 variance 33.80288612537361 votes 3071 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label Command A (03-2025) Observed 2026-10-21T18:45:05.190Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/10327/row` |  |  |  |
| 97 | [Qwen3 30B A3B Instruct 2507](https://benchize.com/models/qwen3-30b-a3b-instruct-2507.md) | 1,344.2 |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1344.2022107950381 \| rating \| reported \| Higher is better \| ### Configuration category polish config text_style_control ### Reported statistics lower 1328.8725512833082 rank 182 upper 1359.5318703067678 variance 61.174275637062614 votes 1541 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label Qwen3-30B-A3B-Instruct (2507) Observed 2026-10-21T18:45:05.190Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/10329/row` |  |  |  |
| 98 | [Grok 3 Mini](https://benchize.com/models/grok-3-mini-high.md)High | 1,343.79 |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1343.7881198649486 \| rating \| reported \| Higher is better \| ### Configuration category polish config text_style_control Reasoning effort high thinkingEnabled true ### Reported statistics lower 1328.28123627299 rank 183 upper 1359.295003456907 variance 62.596906529144675 votes 1571 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label Grok 3 Mini (High) Observed 2026-10-21T18:45:05.190Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/10330/row` |  |  |  |
| 99 | [Trinity Large Thinking](https://benchize.com/models/trinity-large-thinking.md) | 1,342.68 |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1342.6799829198394 \| rating \| reported \| Higher is better \| ### Configuration category polish config text_style_control ### Reported statistics lower 1316.512854202691 rank 185 upper 1368.8471116369878 variance 178.2444267295555 votes 568 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label Trinity Large Thinking Observed 2026-10-21T18:45:05.190Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/10332/row` |  |  |  |
| 100 | [GPT-5 Nano](https://benchize.com/models/gpt-5-nano-high.md)High | 1,337.61 |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1337.6112087599927 \| rating \| reported \| Higher is better \| ### Configuration category polish config text_style_control Reasoning effort high thinkingEnabled true ### Reported statistics lower 1311.9287100421957 rank 189 upper 1363.2937074777894 variance 171.70319172403808 votes 571 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label GPT-5 nano (High) Observed 2026-10-21T18:45:05.190Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/10336/row` |  |  |  |

[Next page](https://benchize.com/benchmarks/lmarena%3Atext_style_control%3Apolish.md?cursor=%7B%22score%22%3A1337.6112087599927%2C%22id%22%3A%220a4799cd64db9a7b422a4d3a48fc6cc472c3c6fd8f791971af30e8ae98778550%22%7D)

---
Cite as: Arena text style control / polish — Benchize, https://benchize.com/benchmarks/lmarena%3Atext_style_control%3Apolish (retrieved 2026-10-21)