# Arena text style control / hard prompts > Source: Benchize (https://benchize.com) — https://benchize.com/benchmarks/lmarena%3Atext_style_control%3Ahard_prompts. When citing or reusing this content, credit "Benchize" and link to https://benchize.com/benchmarks/lmarena%3Atext_style_control%3Ahard_prompts. Human pairwise preferences on hard prompts 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%3Ahard_prompts 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 hard prompts 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. Human preference · Models tested: 151 · Score publishers: [Arena](https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset) ## Model results | # | Model | Score | | | --- | --- | --- | --- | | 1 | [Gemini 4 Argon](https://benchize.com/models/gemini-4-argon-high.md)High | 1,548.83 | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1548.8294110405436 \| rating \| reported \| Higher is better \| ### Configuration category hard_prompts config text_style_control Reasoning effort high thinkingEnabled true ### Reported statistics lower 1537.8652592734622 rank 1 upper 1559.793562807625 variance 31.29348239372019 votes 3131 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label Gemini 4 Argon (High) Observed 2026-10-21T18:45:05.190Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/3451/row` | | | | | 2 | [Claude Opus 5.5](https://benchize.com/models/claude-opus-5-5-high.md)High | 1,533.94 | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1533.9409880046433 \| rating \| reported \| Higher is better \| ### Configuration category hard_prompts config text_style_control Reasoning effort high thinkingEnabled true ### Reported statistics lower 1525.3993471811737 rank 2 upper 1542.482628828113 variance 18.992687768544187 votes 5917 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label Claude Opus 5.5 (High) Observed 2026-10-21T18:45:05.190Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/3452/row` | | | | | 3 | [Claude Opus 4.6](https://benchize.com/models/claude-opus-4-6-high.md)High | 1,530.48 | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1530.4827424231569 \| rating \| reported \| Higher is better \| ### Configuration category hard_prompts config text_style_control Reasoning effort high thinkingEnabled true ### Reported statistics lower 1526.4342240399876 rank 3 upper 1534.5312608063261 variance 4.2667387219050275 votes 52600 ### 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/3453/row` | | | | | 4 | [Claude Fable 5](https://benchize.com/models/claude-fable-5-high.md)High | 1,529.21 | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1529.2050820238678 \| rating \| reported \| Higher is better \| ### Configuration category hard_prompts config text_style_control Reasoning effort high thinkingEnabled true ### Reported statistics lower 1524.2999765082993 rank 4 upper 1534.1101875394363 variance 6.2632612353533625 votes 28193 ### 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/3454/row` | | | | | 5 | [Claude Opus 4.6](https://benchize.com/models/claude-opus-4-6.md) | 1,526.62 | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1526.6208151634146 \| rating \| reported \| Higher is better \| ### Configuration category hard_prompts config text_style_control ### Reported statistics lower 1522.6900829548342 rank 5 upper 1530.5515473719947 variance 4.022080260846947 votes 56652 ### 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/3455/row` | | | | | 6 | [Claude Opus 4.7](https://benchize.com/models/claude-opus-4-7-high.md)High | 1,525.17 | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1525.169593625853 \| rating \| reported \| Higher is better \| ### Configuration category hard_prompts config text_style_control Reasoning effort high thinkingEnabled true ### Reported statistics lower 1520.7082630170357 rank 6 upper 1529.6309242346701 variance 5.18122716660371 votes 43676 ### 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/3456/row` | | | | | 7 | [Claude Fable 5.1](https://benchize.com/models/claude-fable-5-1-max.md)Max | 1,522.83 | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1522.8291452003416 \| rating \| reported \| Higher is better \| ### Configuration category hard_prompts config text_style_control Reasoning effort max thinkingEnabled true ### Reported statistics lower 1515.7273458339832 rank 7 upper 1529.9309445667 variance 13.129271090531864 votes 9089 ### 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/3457/row` | | | | | 8 | [Muse Wonder](https://benchize.com/models/muse-wonder-max.md)Max | 1,522.83 | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1522.8286974766604 \| rating \| reported \| Higher is better \| ### Configuration category hard_prompts config text_style_control Reasoning effort max thinkingEnabled true ### Reported statistics lower 1512.0303759962221 rank 8 upper 1533.6270189570987 variance 30.35402752900661 votes 3187 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label Muse Wonder (Max) Observed 2026-10-21T18:45:05.190Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/3458/row` | | | | | 9 | [Claude Opus 4.7](https://benchize.com/models/claude-opus-4-7.md) | 1,518.94 | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1518.9441415990354 \| rating \| reported \| Higher is better \| ### Configuration category hard_prompts config text_style_control ### Reported statistics lower 1514.4701844910865 rank 9 upper 1523.4180987069842 variance 5.210596582719426 votes 44373 ### 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/3459/row` | | | | | 10 | [Gemini 3.8 Flash](https://benchize.com/models/gemini-3-8-flash-high.md)High | 1,517.42 | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1517.4194658247275 \| rating \| reported \| Higher is better \| ### Configuration category hard_prompts config text_style_control Reasoning effort high thinkingEnabled true ### Reported statistics lower 1512.0119085370275 rank 10 upper 1522.8270231124277 variance 7.612127888039073 votes 26670 ### 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/3460/row` | | | | | 11 | [Muse Spark 1.3](https://benchize.com/models/muse-spark-1-3-max.md)Max | 1,516.5 | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1516.504116879194 \| rating \| reported \| Higher is better \| ### Configuration category hard_prompts config text_style_control Reasoning effort max thinkingEnabled true ### Reported statistics lower 1510.0883858753896 rank 11 upper 1522.9198478829985 variance 10.715097111398968 votes 12510 ### 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/3461/row` | | | | | 12 | [Claude Opus 5](https://benchize.com/models/claude-opus-5-max.md)Max | 1,515.49 | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1515.4903049847705 \| rating \| reported \| Higher is better \| ### Configuration category hard_prompts config text_style_control Reasoning effort max thinkingEnabled true ### Reported statistics lower 1509.9353561261755 rank 13 upper 1521.0452538433656 variance 8.032744397877 votes 21745 ### 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/3463/row` | | | | | 13 | [Claude Opus 5](https://benchize.com/models/claude-opus-5-high.md)High | 1,514.64 | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1514.6431838157107 \| rating \| reported \| Higher is better \| ### Configuration category hard_prompts config text_style_control Reasoning effort high thinkingEnabled true ### Reported statistics lower 1510.1870783904103 rank 14 upper 1519.099289241011 variance 5.169097597616189 votes 45136 ### 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/3464/row` | | | | | 14 | [Claude Opus 4.8](https://benchize.com/models/claude-opus-4-8-high.md)High | 1,512.86 | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1512.8557232364133 \| rating \| reported \| Higher is better \| ### Configuration category hard_prompts config text_style_control Reasoning effort high thinkingEnabled true ### Reported statistics lower 1508.3083618190278 rank 15 upper 1517.4030846537987 variance 5.382979962958359 votes 42516 ### 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/3465/row` | | | | | 15 | [GPT-5.6 Sol](https://benchize.com/models/gpt-5-6-sol-xhigh.md)Extra high | 1,511.32 | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1511.3203566645398 \| rating \| reported \| Higher is better \| ### Configuration category hard_prompts config text_style_control Reasoning effort xhigh thinkingEnabled true ### Reported statistics lower 1506.2939940308709 rank 16 upper 1516.3467192982084 variance 6.576751829029548 votes 27137 ### 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/3466/row` | | | | | 16 | [Muse Spark 1.2](https://benchize.com/models/muse-spark-1-2-xhigh.md)Extra high | 1,511.01 | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1511.0069596643393 \| rating \| reported \| Higher is better \| ### Configuration category hard_prompts config text_style_control Reasoning effort xhigh thinkingEnabled true ### Reported statistics lower 1502.7490602184107 rank 17 upper 1519.264859110268 variance 17.751824617176784 votes 6116 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label Muse Spark 1.2 (xHigh) Observed 2026-10-21T18:45:05.190Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/3467/row` | | | | | 17 | [Muse Spark 1.1](https://benchize.com/models/muse-spark-1-1.md) | 1,510.29 | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1510.2870836354232 \| rating \| reported \| Higher is better \| ### Configuration category hard_prompts config text_style_control ### Reported statistics lower 1505.4431136368867 rank 18 upper 1515.1310536339597 variance 6.108107998013827 votes 29563 ### 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/3468/row` | | | | | 18 | [Gemini 3.1 Pro Preview](https://benchize.com/models/gemini-3-1-pro-preview.md) | 1,507.67 | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1507.6733893220871 \| rating \| reported \| Higher is better \| ### Configuration category hard_prompts config text_style_control ### Reported statistics lower 1504.1030840564104 rank 19 upper 1511.2436945877637 variance 3.31829137968337 votes 84197 ### 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/3469/row` | | | | | 19 | [Gemini 3.7 Flash](https://benchize.com/models/gemini-3-7-flash-high.md)High | 1,507.24 | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1507.2353572850466 \| rating \| reported \| Higher is better \| ### Configuration category hard_prompts config text_style_control Reasoning effort high thinkingEnabled true ### Reported statistics lower 1501.6202981861638 rank 20 upper 1512.8504163839293 variance 8.207530044080737 votes 19036 ### 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/3470/row` | | | | | 20 | [Claude Sonnet 5.5](https://benchize.com/models/claude-sonnet-5-5-xhigh.md)Extra high | 1,505.56 | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1505.5631910093887 \| rating \| reported \| Higher is better \| ### Configuration category hard_prompts config text_style_control Reasoning effort xhigh thinkingEnabled true ### Reported statistics lower 1496.6380132703562 rank 22 upper 1514.488368748421 variance 20.736600700804882 votes 5015 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label Claude Sonnet 5.5 (xHigh) Observed 2026-10-21T18:45:05.190Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/3472/row` | | | | | 21 | [Claude Opus 4.8](https://benchize.com/models/claude-opus-4-8.md) | 1,504.97 | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1504.9683040642162 \| rating \| reported \| Higher is better \| ### Configuration category hard_prompts config text_style_control ### Reported statistics lower 1500.4228902445807 rank 23 upper 1509.5137178838515 variance 5.378369977684274 votes 43360 ### 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/3473/row` | | | | | 22 | [MiMo-V2.6-Pro](https://benchize.com/models/mimo-v2-6-pro.md) | 1,503.93 | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1503.930627912539 \| rating \| reported \| Higher is better \| ### Configuration category hard_prompts config text_style_control ### Reported statistics lower 1492.3452868742097 rank 25 upper 1515.5159689508685 variance 34.93988436146911 votes 2619 ### 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-Pro Observed 2026-10-21T18:45:05.190Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/3475/row` | | | | | 23 | [Claude Sonnet 4.6](https://benchize.com/models/claude-sonnet-4-6.md) | 1,503.32 | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1503.32138237135 \| rating \| reported \| Higher is better \| ### Configuration category hard_prompts config text_style_control ### Reported statistics lower 1499.0378156190195 rank 26 upper 1507.6049491236804 variance 4.776556245461867 votes 46227 ### 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/3476/row` | | | | | 24 | [Qwen3.8 Max](https://benchize.com/models/qwen3-8-max.md) | 1,503.28 | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1503.2758342185348 \| rating \| reported \| Higher is better \| ### Configuration category hard_prompts config text_style_control ### Reported statistics lower 1497.692438783344 rank 27 upper 1508.8592296537254 variance 8.115225501772903 votes 19425 ### 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/3477/row` | | | | | 25 | [Gemini 3 Pro](https://benchize.com/models/gemini-3-pro.md) | 1,502.38 | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1502.378562504986 \| rating \| reported \| Higher is better \| ### Configuration category hard_prompts config text_style_control ### Reported statistics lower 1497.5002281973543 rank 28 upper 1507.2568968126172 variance 6.195080235876124 votes 23177 ### 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/3478/row` | | | | | 26 | [GPT-6.1 Sol](https://benchize.com/models/gpt-6-1-sol-max.md)Max | 1,502.17 | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1502.165304974315 \| rating \| reported \| Higher is better \| ### Configuration category hard_prompts config text_style_control Reasoning effort max thinkingEnabled true ### Reported statistics lower 1492.463545822878 rank 29 upper 1511.867064125752 variance 24.502183942580004 votes 4318 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label GPT-6.1 Sol (Max) Observed 2026-10-21T18:45:05.190Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/3479/row` | | | | | 27 | [Gemini 3.6 Flash](https://benchize.com/models/gemini-3-6-flash-high.md)High | 1,501.19 | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1501.1879009164843 \| rating \| reported \| Higher is better \| ### Configuration category hard_prompts config text_style_control Reasoning effort high thinkingEnabled true ### Reported statistics lower 1496.0033636814028 rank 30 upper 1506.3724381515656 variance 6.997192367947506 votes 24133 ### 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/3480/row` | | | | | 28 | [GPT-5.5](https://benchize.com/models/gpt-5-5-high.md)High | 1,501.17 | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1501.1717990828358 \| rating \| reported \| Higher is better \| ### Configuration category hard_prompts config text_style_control Reasoning effort high thinkingEnabled true ### Reported statistics lower 1496.790785264933 rank 31 upper 1505.5528129007384 variance 4.996352419362027 votes 45527 ### 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/3481/row` | | | | | 29 | [GPT-6 Astra](https://benchize.com/models/gpt-6-astra-max.md)Max | 1,500.81 | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1500.8135028720108 \| rating \| reported \| Higher is better \| ### Configuration category hard_prompts config text_style_control Reasoning effort max thinkingEnabled true ### Reported statistics lower 1493.463426393566 rank 32 upper 1508.1635793504558 variance 14.0633094771088 votes 8080 ### 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/3482/row` | | | | | 30 | [GPT-5.5](https://benchize.com/models/gpt-5-5.md) | 1,498.96 | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1498.9630096508893 \| rating \| reported \| Higher is better \| ### Configuration category hard_prompts config text_style_control ### Reported statistics lower 1494.6117513217846 rank 35 upper 1503.314267979994 variance 4.928713265025134 votes 47276 ### 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/3485/row` | | | | | 31 | [DeepSeek V4.1 Flash](https://benchize.com/models/deepseek-v4-1-flash-max.md)Max | 1,498.87 | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1498.8694936813984 \| rating \| reported \| Higher is better \| ### Configuration category hard_prompts config text_style_control Reasoning effort max thinkingEnabled true ### Reported statistics lower 1491.7317768080788 rank 36 upper 1506.007210554718 variance 13.262410074323276 votes 8655 ### 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/3486/row` | | | | | 32 | [GPT-5.4](https://benchize.com/models/gpt-5-4-high.md)High | 1,496.46 | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1496.4586652206178 \| rating \| reported \| Higher is better \| ### Configuration category hard_prompts config text_style_control Reasoning effort high thinkingEnabled true ### Reported statistics lower 1491.9528791108146 rank 38 upper 1500.9644513304208 variance 5.284999635535914 votes 42124 ### 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/3488/row` | | | | | 33 | [Gemini 3.5 Flash](https://benchize.com/models/gemini-3-5-flash-medium.md)Medium | 1,495.03 | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1495.0329233690768 \| rating \| reported \| Higher is better \| ### Configuration category hard_prompts config text_style_control Reasoning effort medium thinkingEnabled true ### Reported statistics lower 1490.1941949838422 rank 41 upper 1499.8716517543114 variance 6.094896100394598 votes 31491 ### 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/3491/row` | | | | | 34 | [Gemini 3.5 Flash](https://benchize.com/models/gemini-3-5-flash-high.md)High | 1,495.03 | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1495.0295144659285 \| rating \| reported \| Higher is better \| ### Configuration category hard_prompts config text_style_control Reasoning effort high thinkingEnabled true ### Reported statistics lower 1490.4430597648138 rank 42 upper 1499.6159691670432 variance 5.475931854861394 votes 32389 ### 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/3492/row` | | | | | 35 | [MiMo-V2.5-Pro](https://benchize.com/models/mimo-v2-5-pro.md) | 1,493.84 | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1493.8398804751332 \| rating \| reported \| Higher is better \| ### Configuration category hard_prompts config text_style_control ### Reported statistics lower 1489.6924696337696 rank 44 upper 1497.987291316497 variance 4.477730333694634 votes 50452 ### 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/3494/row` | | | | | 36 | [Gemini 3 Flash](https://benchize.com/models/gemini-3-flash.md) | 1,492.68 | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1492.6774536104144 \| rating \| reported \| Higher is better \| ### Configuration category hard_prompts config text_style_control ### Reported statistics lower 1487.155551409299 rank 45 upper 1498.19935581153 variance 7.937454321890724 votes 17156 ### 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/3495/row` | | | | | 37 | [GPT-5.6 Terra](https://benchize.com/models/gpt-5-6-terra-xhigh.md)Extra high | 1,489.97 | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1489.9730592920523 \| rating \| reported \| Higher is better \| ### Configuration category hard_prompts config text_style_control Reasoning effort xhigh thinkingEnabled true ### Reported statistics lower 1485.0651201283224 rank 48 upper 1494.880998455782 variance 6.270499817702092 votes 29450 ### 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/3498/row` | | | | | 38 | [Claude Sonnet 5](https://benchize.com/models/claude-sonnet-5-high.md)High | 1,489.28 | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1489.2837179017388 \| rating \| reported \| Higher is better \| ### Configuration category hard_prompts config text_style_control Reasoning effort high thinkingEnabled true ### Reported statistics lower 1484.5477659057979 rank 49 upper 1494.01966989768 variance 5.838730116545867 votes 33444 ### 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/3499/row` | | | | | 39 | [GPT-5.4](https://benchize.com/models/gpt-5-4.md) | 1,486.78 | | | ### 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 2026-10-21T18:45:05.190Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/3506/row` | | | | | 40 | [GPT-6 Sol](https://benchize.com/models/gpt-6-sol-max.md)Max | 1,485.88 | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1485.87623360358 \| rating \| reported \| Higher is better \| ### Configuration category hard_prompts config text_style_control Reasoning effort max thinkingEnabled true ### Reported statistics lower 1478.5292162591213 rank 57 upper 1493.2232509480386 variance 14.051605491380263 votes 8512 ### 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/3507/row` | | | | | 41 | [DeepSeek V4 Pro](https://benchize.com/models/deepseek-v4-pro-high-budget-20260813.md)High · 20260813 tokens | 1,482.66 | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1482.663790199744 \| rating \| reported \| Higher is better \| ### Configuration category hard_prompts config text_style_control reasoningBudget 20260813 Reasoning effort high thinkingEnabled true ### Reported statistics lower 1474.8906827485287 rank 61 upper 1490.4368976509593 variance 15.728711999370551 votes 6526 ### 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 (High, 20260813) Observed 2026-10-21T18:45:05.190Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/3511/row` | | | | | 42 | [Qwen3.6 Max Preview](https://benchize.com/models/qwen3-6-max-preview.md) | 1,482.02 | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1482.016907134058 \| rating \| reported \| Higher is better \| ### Configuration category hard_prompts config text_style_control ### Reported statistics lower 1471.8349246451378 rank 62 upper 1492.1988896229784 variance 26.98786378919105 votes 3576 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label Qwen3.6-Max-Preview Observed 2026-10-21T18:45:05.190Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/3512/row` | | | | | 43 | [DeepSeek V4 Pro](https://benchize.com/models/deepseek-v4-pro.md) | 1,480.17 | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1480.1746192495339 \| rating \| reported \| Higher is better \| ### Configuration category hard_prompts config text_style_control ### Reported statistics lower 1475.5981140150443 rank 65 upper 1484.7511244840234 variance 5.452199578056473 votes 38504 ### 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/3515/row` | | | | | 44 | [MiMo-V2.6-Flash](https://benchize.com/models/mimo-v2-6-flash.md) | 1,476.78 | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1476.7833575282675 \| rating \| reported \| Higher is better \| ### Configuration category hard_prompts config text_style_control ### Reported statistics lower 1469.3239225917282 rank 70 upper 1484.242792464807 variance 14.484905909368027 votes 7817 ### 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/3520/row` | | | | | 45 | [GPT-5.1](https://benchize.com/models/gpt-5-1-high.md)High | 1,476.6 | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1476.5995005013526 \| rating \| reported \| Higher is better \| ### Configuration category hard_prompts config text_style_control Reasoning effort high thinkingEnabled true ### Reported statistics lower 1471.7447649735875 rank 71 upper 1481.4542360291177 variance 6.135288218522628 votes 22416 ### 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/3521/row` | | | | | 46 | [Step 5 Preview](https://benchize.com/models/step-5-preview.md) | 1,475.68 | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1475.6782805748246 \| rating \| reported \| Higher is better \| ### Configuration category hard_prompts config text_style_control ### Reported statistics lower 1467.2416976809027 rank 72 upper 1484.1148634687465 variance 18.52835973213783 votes 5502 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label Step 5 Preview Observed 2026-10-21T18:45:05.190Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/3522/row` | | | | | 47 | [Gemma 4 31B](https://benchize.com/models/gemma-4-31b-it.md) | 1,475.62 | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1475.6169628956495 \| rating \| reported \| Higher is better \| ### Configuration category hard_prompts config text_style_control ### Reported statistics lower 1465.9685929480897 rank 73 upper 1485.2653328432093 variance 24.2332527797746 votes 3565 ### 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/3523/row` | | | | | 48 | [Hy3](https://benchize.com/models/hy3.md) | 1,475.35 | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1475.3477742830135 \| rating \| reported \| Higher is better \| ### Configuration category hard_prompts config text_style_control ### Reported statistics lower 1468.2277281683305 rank 74 upper 1482.4678203976964 variance 13.196824186196114 votes 8479 ### 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/3524/row` | | | | | 49 | [MiMo-V2-Pro](https://benchize.com/models/mimo-v2-pro.md) | 1,475.03 | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1475.0301919783835 \| rating \| reported \| Higher is better \| ### Configuration category hard_prompts config text_style_control ### Reported statistics lower 1469.4190385389447 rank 75 upper 1480.641345417822 variance 8.1961162127558 votes 16513 ### 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/3525/row` | | | | | 50 | [Gemini 3.5 Flash-Lite](https://benchize.com/models/gemini-3-5-flash-lite.md) | 1,475.03 | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1475.0256396502293 \| rating \| reported \| Higher is better \| ### Configuration category hard_prompts config text_style_control ### Reported statistics lower 1469.7751301222925 rank 76 upper 1480.276149178166 variance 7.176401359411977 votes 23808 ### 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/3526/row` | | | | | 51 | [GPT-5.6 Luna](https://benchize.com/models/gpt-5-6-luna-xhigh.md)Extra high | 1,474.38 | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1474.3787905728652 \| rating \| reported \| Higher is better \| ### Configuration category hard_prompts config text_style_control Reasoning effort xhigh thinkingEnabled true ### Reported statistics lower 1469.3414269106747 rank 77 upper 1479.416154235056 variance 6.605571958356513 votes 26984 ### 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/3527/row` | | | | | 52 | [Gemini 3 Flash](https://benchize.com/models/gemini-3-flash-minimal.md)Minimal | 1,474.37 | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1474.3685090468562 \| rating \| reported \| Higher is better \| ### Configuration category hard_prompts config text_style_control Reasoning effort minimal thinkingEnabled true ### Reported statistics lower 1470.6217315485228 rank 78 upper 1478.1152865451895 variance 3.654429808382116 votes 57557 ### 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/3528/row` | | | | | 53 | [GPT-5.3 Chat](https://benchize.com/models/gpt-5-3-chat.md) | 1,472.77 | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1472.770277329242 \| rating \| reported \| Higher is better \| ### Configuration category hard_prompts config text_style_control ### Reported statistics lower 1467.570357561858 rank 82 upper 1477.970197096626 variance 7.038775332321824 votes 21659 ### 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/3532/row` | | | | | 54 | [GPT-5.4 Mini](https://benchize.com/models/gpt-5-4-mini-high.md)High | 1,468.84 | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1468.840658637715 \| rating \| reported \| Higher is better \| ### Configuration category hard_prompts config text_style_control Reasoning effort high thinkingEnabled true ### Reported statistics lower 1464.3549343523982 rank 84 upper 1473.3263829230318 variance 5.238041927062976 votes 41648 ### 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/3534/row` | | | | | 55 | [GPT-6 Luna](https://benchize.com/models/gpt-6-luna-max.md)Max | 1,464.67 | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1464.6736466257375 \| rating \| reported \| Higher is better \| ### Configuration category hard_prompts config text_style_control Reasoning effort max thinkingEnabled true ### Reported statistics lower 1459.582492159408 rank 87 upper 1469.764801092067 variance 6.747398582120769 votes 39234 ### 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/3537/row` | | | | | 56 | [Qwen3.5 397B A17B](https://benchize.com/models/qwen3-5-397b-a17b.md) | 1,463.39 | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1463.3907002875771 \| rating \| reported \| Higher is better \| ### Configuration category hard_prompts config text_style_control ### Reported statistics lower 1459.7216892501199 rank 90 upper 1467.0597113250346 variance 3.504304646054082 votes 62653 ### 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/3540/row` | | | | | 57 | [MiniMax M3](https://benchize.com/models/minimax-m3.md) | 1,463.17 | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1463.1699595695293 \| rating \| reported \| Higher is better \| ### Configuration category hard_prompts config text_style_control ### Reported statistics lower 1458.7199589445047 rank 91 upper 1467.619960194554 variance 5.154944120718652 votes 43582 ### 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/3541/row` | | | | | 58 | [MiMo-V2.5](https://benchize.com/models/mimo-v2-5.md) | 1,462.27 | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1462.2731477564676 \| rating \| reported \| Higher is better \| ### Configuration category hard_prompts config text_style_control ### Reported statistics lower 1457.3126642254178 rank 92 upper 1467.233631287517 variance 6.405482398837209 votes 31827 ### 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/3542/row` | | | | | 59 | [Qwen3.8 27B](https://benchize.com/models/qwen3-8-27b.md) | 1,461.25 | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1461.2496443710327 \| rating \| reported \| Higher is better \| ### Configuration category hard_prompts config text_style_control ### Reported statistics lower 1455.386491723588 rank 94 upper 1467.1127970184775 variance 8.948829226555723 votes 16357 ### 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/3544/row` | | | | | 60 | [Gemma 4 26B A4B](https://benchize.com/models/gemma-4-26b-a4b-it.md) | 1,461.05 | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1461.0485002858863 \| rating \| reported \| Higher is better \| ### Configuration category hard_prompts config text_style_control ### Reported statistics lower 1451.2803813412906 rank 96 upper 1470.816619230482 variance 24.83851895060247 votes 3471 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label Gemma 4 26B A4B Observed 2026-10-21T18:45:05.190Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/3546/row` | | | | | 61 | [Beam 1.0 501B A23B](https://benchize.com/models/beam-1-0-501b-a23b.md) | 1,460.95 | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1460.947945249938 \| rating \| reported \| Higher is better \| ### Configuration category hard_prompts config text_style_control ### Reported statistics lower 1449.2831958903873 rank 97 upper 1472.6126946094887 variance 35.42049621569306 votes 2676 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label Beam 1.0 501B A23B Observed 2026-10-21T18:45:05.190Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/3547/row` | | | | | 62 | [GPT-5.2](https://benchize.com/models/gpt-5-2.md) | 1,460.52 | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1460.5157789845935 \| rating \| reported \| Higher is better \| ### Configuration category hard_prompts config text_style_control ### Reported statistics lower 1456.6155785401736 rank 99 upper 1464.4159794290135 variance 3.9598403150147607 votes 53237 ### 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/3549/row` | | | | | 63 | [GPT-5.2](https://benchize.com/models/gpt-5-2-high.md)High | 1,459.67 | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1459.6741454349278 \| rating \| reported \| Higher is better \| ### Configuration category hard_prompts config text_style_control Reasoning effort high thinkingEnabled true ### Reported statistics lower 1455.2569581016812 rank 101 upper 1464.0913327681744 variance 5.07920163868062 votes 29881 ### 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/3551/row` | | | | | 64 | [DeepSeek V4 Flash](https://benchize.com/models/deepseek-v4-flash.md) | 1,459.06 | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1459.0556798846048 \| rating \| reported \| Higher is better \| ### Configuration category hard_prompts config text_style_control ### Reported statistics lower 1454.302809775571 rank 102 upper 1463.8085499936387 variance 5.8805197003949825 votes 34751 ### 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/3552/row` | | | | | 65 | [MiMo-V2-Omni](https://benchize.com/models/mimo-v2-omni.md) | 1,458.35 | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1458.3516095676089 \| rating \| reported \| Higher is better \| ### Configuration category hard_prompts config text_style_control ### Reported statistics lower 1451.7166635843362 rank 104 upper 1464.9865555508816 variance 11.459841236301923 votes 13804 ### 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/3554/row` | | | | | 66 | [Gemini 2.5 Pro](https://benchize.com/models/gemini-2-5-pro.md) | 1,458.13 | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1458.1295751206758 \| rating \| reported \| Higher is better \| ### Configuration category hard_prompts config text_style_control ### Reported statistics lower 1454.9946644387717 rank 105 upper 1461.2644858025799 variance 2.558315848805765 votes 65892 ### 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/3555/row` | | | | | 67 | [GPT-5.1](https://benchize.com/models/gpt-5-1.md) | 1,455.73 | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1455.7336114958664 \| rating \| reported \| Higher is better \| ### Configuration category hard_prompts config text_style_control ### Reported statistics lower 1451.106923713582 rank 109 upper 1460.3602992781507 variance 5.572424652692472 votes 24332 ### 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/3559/row` | | | | | 68 | [GPT-5 Chat](https://benchize.com/models/gpt-5-chat.md) | 1,448.38 | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1448.3834263326978 \| rating \| reported \| Higher is better \| ### Configuration category hard_prompts config text_style_control ### Reported statistics lower 1442.8349491584188 rank 115 upper 1453.9319035069768 variance 8.014038517776633 votes 15198 ### 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/3565/row` | | | | | 69 | [GPT-5](https://benchize.com/models/gpt-5-high.md)High | 1,448.15 | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1448.1503157519346 \| rating \| reported \| Higher is better \| ### Configuration category hard_prompts config text_style_control Reasoning effort high thinkingEnabled true ### Reported statistics lower 1442.2982677378689 rank 116 upper 1454.0023637660006 variance 8.914963704529384 votes 15055 ### 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/3566/row` | | | | | 70 | [DeepSeek V3.2](https://benchize.com/models/deepseek-v3-2.md) | 1,447.27 | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1447.2686069376955 \| rating \| reported \| Higher is better \| ### Configuration category hard_prompts config text_style_control ### Reported statistics lower 1442.813300960376 rank 117 upper 1451.723912915015 variance 5.167243039182764 votes 27069 ### 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/3567/row` | | | | | 71 | [Qwen3 235B A22B Instruct 2507](https://benchize.com/models/qwen3-235b-a22b-2507.md) | 1,447.2 | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1447.2030629867372 \| rating \| reported \| Higher is better \| ### Configuration category hard_prompts config text_style_control ### Reported statistics lower 1443.9361616210958 rank 118 upper 1450.4699643523786 variance 2.7782790421533012 votes 53535 ### 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/3568/row` | | | | | 72 | [DeepSeek V3.2 Exp](https://benchize.com/models/deepseek-v3-2-exp.md) | 1,446.42 | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1446.418604793731 \| rating \| reported \| Higher is better \| ### Configuration category hard_prompts config text_style_control ### Reported statistics lower 1438.4929603380833 rank 120 upper 1454.3442492493787 variance 16.352079501398386 votes 6580 ### 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/3570/row` | | | | | 73 | [DeepSeek V3.2 Exp](https://benchize.com/models/deepseek-v3-2-exp-thinking.md)Thinking | 1,446.41 | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1446.4142739852555 \| rating \| reported \| Higher is better \| ### Configuration category hard_prompts config text_style_control thinkingEnabled true ### Reported statistics lower 1437.854975179927 rank 121 upper 1454.973572790584 variance 19.07129542668435 votes 4717 ### 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/3571/row` | | | | | 74 | [DeepSeek V3.2](https://benchize.com/models/deepseek-v3-2-thinking.md)Thinking | 1,445.89 | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1445.8897405900339 \| rating \| reported \| Higher is better \| ### Configuration category hard_prompts config text_style_control thinkingEnabled true ### Reported statistics lower 1441.2925449203497 rank 123 upper 1450.4869362597183 variance 5.501609938264247 votes 23323 ### 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/3573/row` | | | | | 75 | [Gemini 3.1 Flash Lite Preview](https://benchize.com/models/gemini-3-1-flash-lite-preview.md) | 1,445.26 | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1445.2620689809887 \| rating \| reported \| Higher is better \| ### Configuration category hard_prompts config text_style_control ### Reported statistics lower 1440.8185536347771 rank 124 upper 1449.7055843272 variance 5.139929790643746 votes 41605 ### 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/3574/row` | | | | | 76 | [Mistral Medium 3.5](https://benchize.com/models/mistral-medium-3-5.md) | 1,444.88 | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1444.87966332773 \| rating \| reported \| Higher is better \| ### Configuration category hard_prompts config text_style_control ### Reported statistics lower 1437.2028782289722 rank 125 upper 1452.5564484264876 variance 15.341314902305529 votes 7650 ### 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/3575/row` | | | | | 77 | [DeepSeek V3.1 Terminus](https://benchize.com/models/deepseek-v3-1-terminus-thinking.md)Thinking | 1,444.27 | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1444.2670045335399 \| rating \| reported \| Higher is better \| ### Configuration category hard_prompts config text_style_control thinkingEnabled true ### Reported statistics lower 1429.8684549206441 rank 126 upper 1458.6655541464359 variance 53.96861989986465 votes 1659 ### 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/3576/row` | | | | | 78 | [MiniMax M2.7](https://benchize.com/models/minimax-m2-7.md) | 1,441.28 | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1441.2777779303633 \| rating \| reported \| Higher is better \| ### Configuration category hard_prompts config text_style_control ### Reported statistics lower 1437.341443030193 rank 133 upper 1445.2141128305336 variance 4.033554222377226 votes 56288 ### 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/3583/row` | | | | | 79 | [Qwen3 VL 235B A22B Instruct](https://benchize.com/models/qwen3-vl-235b-a22b-instruct.md) | 1,437.95 | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1437.950797005073 \| rating \| reported \| Higher is better \| ### Configuration category hard_prompts config text_style_control ### Reported statistics lower 1429.350933926419 rank 136 upper 1446.5506600837266 variance 19.25248933378629 votes 5704 ### 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/3586/row` | | | | | 80 | [DeepSeek V3.1](https://benchize.com/models/deepseek-v3-1-thinking.md)Thinking | 1,436.84 | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1436.8350960835537 \| rating \| reported \| Higher is better \| ### Configuration category hard_prompts config text_style_control thinkingEnabled true ### Reported statistics lower 1428.2060073285948 rank 137 upper 1445.464184838513 variance 19.38356656066042 votes 5085 ### 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/3587/row` | | | | | 81 | [Hy3 preview](https://benchize.com/models/hy3-preview.md) | 1,433.26 | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1433.2607502096082 \| rating \| reported \| Higher is better \| ### Configuration category hard_prompts config text_style_control ### Reported statistics lower 1424.2349263750668 rank 139 upper 1442.2865740441498 variance 21.206916355140542 votes 4589 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label Hy3 preview Observed 2026-10-21T18:45:05.190Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/3589/row` | | | | | 82 | [R1 0528](https://benchize.com/models/deepseek-r1-0528.md) | 1,433.11 | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1433.1077973579374 \| rating \| reported \| Higher is better \| ### Configuration category hard_prompts config text_style_control ### Reported statistics lower 1425.4081219805075 rank 140 upper 1440.8074727353671 variance 15.432939329826223 votes 6879 ### 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/3590/row` | | | | | 83 | [Mistral Large 3](https://benchize.com/models/mistral-large-3.md) | 1,432.73 | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1432.731470309886 \| rating \| reported \| Higher is better \| ### Configuration category hard_prompts config text_style_control ### Reported statistics lower 1429.1963917365686 rank 143 upper 1436.266548883203 variance 3.2531340573549 votes 52468 ### 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/3593/row` | | | | | 84 | [Qwen3.5-122B-A10B](https://benchize.com/models/qwen3-5-122b-a10b.md) | 1,432.63 | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1432.6301519829763 \| rating \| reported \| Higher is better \| ### Configuration category hard_prompts config text_style_control ### Reported statistics lower 1427.4076268085994 rank 144 upper 1437.8526771573534 variance 7.100107139004504 votes 18809 ### 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/3594/row` | | | | | 85 | [DeepSeek V3.1](https://benchize.com/models/deepseek-v3-1.md) | 1,432.3 | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1432.3004259048723 \| rating \| reported \| Higher is better \| ### Configuration category hard_prompts config text_style_control ### Reported statistics lower 1424.511028938449 rank 148 upper 1440.0898228712956 variance 15.794704025894509 votes 6712 ### 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/3598/row` | | | | | 86 | [Qwen3.5-27B](https://benchize.com/models/qwen3-5-27b.md) | 1,427.82 | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1427.8227901683713 \| rating \| reported \| Higher is better \| ### Configuration category hard_prompts config text_style_control ### Reported statistics lower 1422.5905433018513 rank 150 upper 1433.0550370348913 variance 7.1265653362548 votes 18079 ### 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/3600/row` | | | | | 87 | [DeepSeek V3.1 Terminus](https://benchize.com/models/deepseek-v3-1-terminus.md) | 1,423.79 | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1423.7858083388633 \| rating \| reported \| Higher is better \| ### Configuration category hard_prompts config text_style_control ### Reported statistics lower 1410.563132750895 rank 156 upper 1437.0084839268316 variance 45.51373784427607 votes 1902 ### 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/3606/row` | | | | | 88 | [GPT-5.4 Nano](https://benchize.com/models/gpt-5-4-nano-high.md)High | 1,421.23 | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1421.231729950533 \| rating \| reported \| Higher is better \| ### Configuration category hard_prompts config text_style_control Reasoning effort high thinkingEnabled true ### Reported statistics lower 1416.6880432911246 rank 157 upper 1425.7754166099417 variance 5.374283422659913 votes 41305 ### 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/3607/row` | | | | | 89 | [Qwen3 235B A22B](https://benchize.com/models/qwen3-235b-a22b-off.md)Non-thinking | 1,420.1 | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1420.1036844966366 \| rating \| reported \| Higher is better \| ### Configuration category hard_prompts config text_style_control thinkingEnabled false ### Reported statistics lower 1414.4418862968748 rank 159 upper 1425.7654826963983 variance 8.344735776455002 votes 16395 ### 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/3609/row` | | | | | 90 | [Qwen3 Next 80B A3B Instruct](https://benchize.com/models/qwen3-next-80b-a3b-instruct.md) | 1,419.4 | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1419.3977094586105 \| rating \| reported \| Higher is better \| ### Configuration category hard_prompts config text_style_control ### Reported statistics lower 1413.3575918681745 rank 161 upper 1425.4378270490467 variance 9.497178600421284 votes 11998 ### 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/3611/row` | | | | | 91 | [Gemini 2.5 Flash](https://benchize.com/models/gemini-2-5-flash.md) | 1,419.23 | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1419.2299120372827 \| rating \| reported \| Higher is better \| ### Configuration category hard_prompts config text_style_control ### Reported statistics lower 1416.0973443754876 rank 162 upper 1422.3624796990778 variance 2.5544931271581293 votes 65128 ### 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/3612/row` | | | | | 92 | [DeepSeek R1](https://benchize.com/models/deepseek-r1.md) | 1,418.76 | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1418.755750157414 \| rating \| reported \| Higher is better \| ### Configuration category hard_prompts config text_style_control ### Reported statistics lower 1409.7387737067006 rank 165 upper 1427.7727266081276 variance 21.165361418095646 votes 4116 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label DeepSeek-R1 Observed 2026-10-21T18:45:05.190Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/3615/row` | | | | | 93 | [Qwen3 235B A22B Thinking 2507](https://benchize.com/models/qwen3-235b-a22b-thinking-2507.md) | 1,417.8 | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1417.8003161136385 \| rating \| reported \| Higher is better \| ### Configuration category hard_prompts config text_style_control ### Reported statistics lower 1408.323474438514 rank 168 upper 1427.277157788763 variance 23.379276552845056 votes 3806 ### 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/3618/row` | | | | | 94 | [MiniMax M2.5](https://benchize.com/models/minimax-m2-5.md) | 1,417.72 | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1417.7159587913693 \| rating \| reported \| Higher is better \| ### Configuration category hard_prompts config text_style_control ### Reported statistics lower 1412.912638898711 rank 169 upper 1422.5192786840275 variance 6.006020907192145 votes 26855 ### 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/3619/row` | | | | | 95 | [Qwen3 VL 235B A22B Thinking](https://benchize.com/models/qwen3-vl-235b-a22b-thinking.md) | 1,417.43 | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1417.4293471953094 \| rating \| reported \| Higher is better \| ### Configuration category hard_prompts config text_style_control ### Reported statistics lower 1408.2740550044173 rank 170 upper 1426.5846393862018 variance 21.819672945359592 votes 4046 ### 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/3620/row` | | | | | 96 | [MiMo-V2-Flash](https://benchize.com/models/mimo-v2-flash-off.md)Non-thinking | 1,413.27 | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1413.2669209533583 \| rating \| reported \| Higher is better \| ### Configuration category hard_prompts config text_style_control thinkingEnabled false ### Reported statistics lower 1408.9079963070355 rank 175 upper 1417.6258455996813 variance 4.9460959909203925 votes 29150 ### 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/3625/row` | | | | | 97 | [Step 3.5 Flash](https://benchize.com/models/step-3-5-flash.md) | 1,412.46 | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1412.4550580909863 \| rating \| reported \| Higher is better \| ### Configuration category hard_prompts config text_style_control ### Reported statistics lower 1408.1528149497346 rank 176 upper 1416.7573012322382 variance 4.818298701195817 votes 37536 ### 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/3626/row` | | | | | 98 | [Qwen3.5-35B-A3B](https://benchize.com/models/qwen3-5-35b-a3b.md) | 1,412.19 | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1412.1901703696672 \| rating \| reported \| Higher is better \| ### Configuration category hard_prompts config text_style_control ### Reported statistics lower 1407.036297308334 rank 177 upper 1417.3440434309998 variance 6.914666737865294 votes 19346 ### 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/3627/row` | | | | | 99 | [MiMo-V2-Flash](https://benchize.com/models/mimo-v2-flash-thinking.md)Thinking | 1,411.06 | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1411.0604525973822 \| rating \| reported \| Higher is better \| ### Configuration category hard_prompts config text_style_control thinkingEnabled true ### Reported statistics lower 1403.2928841978141 rank 178 upper 1418.8280209969503 variance 15.70630368779151 votes 6185 ### 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/3628/row` | | | | | 100 | [Solar Pro 4](https://benchize.com/models/solar-pro4.md) | 1,409.39 | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1409.3930190194137 \| rating \| reported \| Higher is better \| ### Configuration category hard_prompts config text_style_control ### Reported statistics lower 1403.3184144038491 rank 179 upper 1415.467623634978 variance 9.605939555215036 votes 15023 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label Solar Pro 4 Observed 2026-10-21T18:45:05.190Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/3629/row` | | | | [Next page](https://benchize.com/benchmarks/lmarena%3Atext_style_control%3Ahard_prompts.md?cursor=%7B%22score%22%3A1409.3930190194137%2C%22id%22%3A%2216914b58eb63a410dbd3b0e6665114afb86f9d9f9ed91863cdb30c50fc61dcee%22%7D) --- Cite as: Arena text style control / hard prompts — Benchize, https://benchize.com/benchmarks/lmarena%3Atext_style_control%3Ahard_prompts (retrieved 2026-10-21)