# Arena text style control / instruction following

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

Human pairwise preferences on instruction following 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%3Ainstruction_following
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 instruction following 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.

Instruction following · 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 | 1,525.35 |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1525.3537595597604 \| rating \| reported \| Higher is better \| ### Configuration category instruction_following config text_style_control Reasoning effort high thinkingEnabled true ### Reported statistics lower 1510.7269592139812 rank 1 upper 1539.9805599055396 variance 55.69324007920196 votes 1748 ### 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/7534/row` |  |  |  |
| 2 | [Claude Opus 5.5](https://benchize.com/models/claude-opus-5-5-high.md)High | 1,519.46 |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1519.4634681491418 \| rating \| reported \| Higher is better \| ### Configuration category instruction_following config text_style_control Reasoning effort high thinkingEnabled true ### Reported statistics lower 1508.3298624117929 rank 2 upper 1530.5970738864908 variance 32.26825601955324 votes 3298 ### 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/7535/row` |  |  |  |
| 3 | [Claude Opus 4.6](https://benchize.com/models/claude-opus-4-6-high.md)High | 1,511.21 |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1511.2123791350318 \| rating \| reported \| Higher is better \| ### Configuration category instruction_following config text_style_control Reasoning effort high thinkingEnabled true ### Reported statistics lower 1506.2126381009718 rank 3 upper 1516.2121201690916 variance 6.507270173768416 votes 26659 ### 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/7536/row` |  |  |  |
| 4 | [Claude Fable 5](https://benchize.com/models/claude-fable-5-high.md)High | 1,507.63 |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1507.6285010900642 \| rating \| reported \| Higher is better \| ### Configuration category instruction_following config text_style_control Reasoning effort high thinkingEnabled true ### Reported statistics lower 1501.7215713846876 rank 4 upper 1513.5354307954408 variance 9.082960451455625 votes 15293 ### 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/7537/row` |  |  |  |
| 5 | [Claude Opus 4.7](https://benchize.com/models/claude-opus-4-7-high.md)High | 1,502.13 |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1502.1253386871097 \| rating \| reported \| Higher is better \| ### Configuration category instruction_following config text_style_control Reasoning effort high thinkingEnabled true ### Reported statistics lower 1496.7038464884463 rank 5 upper 1507.5468308857733 variance 7.651410318868961 votes 22751 ### 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/7538/row` |  |  |  |
| 6 | [Claude Fable 5.1](https://benchize.com/models/claude-fable-5-1-max.md)Max | 1,499.79 |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1499.7880890016545 \| rating \| reported \| Higher is better \| ### Configuration category instruction_following config text_style_control Reasoning effort max thinkingEnabled true ### Reported statistics lower 1490.368463088894 rank 6 upper 1509.207714914415 variance 23.097827278105925 votes 4693 ### 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/7539/row` |  |  |  |
| 7 | [Claude Opus 4.6](https://benchize.com/models/claude-opus-4-6.md) | 1,498.2 |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1498.1973414332529 \| rating \| reported \| Higher is better \| ### Configuration category instruction_following config text_style_control ### Reported statistics lower 1493.4051234076858 rank 7 upper 1502.9895594588197 variance 5.978289674967698 votes 29280 ### 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/7540/row` |  |  |  |
| 8 | [Claude Opus 5](https://benchize.com/models/claude-opus-5-high.md)High | 1,495.07 |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1495.0681850849091 \| rating \| reported \| Higher is better \| ### Configuration category instruction_following config text_style_control Reasoning effort high thinkingEnabled true ### Reported statistics lower 1489.5551539172163 rank 8 upper 1500.5812162526022 variance 7.911971486515013 votes 24456 ### 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/7541/row` |  |  |  |
| 9 | [Muse Wonder](https://benchize.com/models/muse-wonder-max.md)Max | 1,494.99 |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1494.9939904801186 \| rating \| reported \| Higher is better \| ### Configuration category instruction_following config text_style_control Reasoning effort max thinkingEnabled true ### Reported statistics lower 1480.66363419599 rank 9 upper 1509.3243467642474 variance 53.4586262187129 votes 1797 ### 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/7542/row` |  |  |  |
| 10 | [Claude Opus 5](https://benchize.com/models/claude-opus-5-max.md)Max | 1,494.59 |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1494.5913932412752 \| rating \| reported \| Higher is better \| ### Configuration category instruction_following config text_style_control Reasoning effort max thinkingEnabled true ### Reported statistics lower 1487.8850626226856 rank 10 upper 1501.2977238598648 variance 11.707758032846892 votes 11699 ### 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/7543/row` |  |  |  |
| 11 | [Claude Opus 4.7](https://benchize.com/models/claude-opus-4-7.md) | 1,492.68 |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1492.6762318599035 \| rating \| reported \| Higher is better \| ### Configuration category instruction_following config text_style_control ### Reported statistics lower 1487.3306515497238 rank 11 upper 1498.0218121700832 variance 7.438639898635488 votes 23310 ### 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/7544/row` |  |  |  |
| 12 | [GPT-5.6 Sol](https://benchize.com/models/gpt-5-6-sol-xhigh.md)Extra high | 1,490.82 |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1490.8166692263094 \| rating \| reported \| Higher is better \| ### Configuration category instruction_following config text_style_control Reasoning effort xhigh thinkingEnabled true ### Reported statistics lower 1484.7224501570274 rank 12 upper 1496.9108882955911 variance 9.668073458011847 votes 14557 ### 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/7545/row` |  |  |  |
| 13 | [Claude Opus 4.8](https://benchize.com/models/claude-opus-4-8-high.md)High | 1,490.8 |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1490.8000221079171 \| rating \| reported \| Higher is better \| ### Configuration category instruction_following config text_style_control Reasoning effort high thinkingEnabled true ### Reported statistics lower 1485.4889748871838 rank 13 upper 1496.1110693286505 variance 7.34284132603614 votes 22656 ### 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/7546/row` |  |  |  |
| 14 | [Gemini 3.8 Flash](https://benchize.com/models/gemini-3-8-flash-high.md)High | 1,490.4 |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1490.3970109045779 \| rating \| reported \| Higher is better \| ### Configuration category instruction_following config text_style_control Reasoning effort high thinkingEnabled true ### Reported statistics lower 1484.079391648707 rank 14 upper 1496.7146301604487 variance 10.389884396818218 votes 14854 ### 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/7547/row` |  |  |  |
| 15 | [Claude Sonnet 5.5](https://benchize.com/models/claude-sonnet-5-5-xhigh.md)Extra high | 1,486.97 |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1486.9692445123287 \| rating \| reported \| Higher is better \| ### Configuration category instruction_following config text_style_control Reasoning effort xhigh thinkingEnabled true ### Reported statistics lower 1475.2504124105074 rank 16 upper 1498.68807661415 variance 35.749706619493445 votes 2756 ### 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/7549/row` |  |  |  |
| 16 | [Gemini 3.7 Flash](https://benchize.com/models/gemini-3-7-flash-high.md)High | 1,485.73 |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1485.7288229919889 \| rating \| reported \| Higher is better \| ### Configuration category instruction_following config text_style_control Reasoning effort high thinkingEnabled true ### Reported statistics lower 1478.813021054979 rank 17 upper 1492.6446249289988 variance 12.450560754236916 votes 10486 ### 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/7550/row` |  |  |  |
| 17 | [Muse Spark 1.3](https://benchize.com/models/muse-spark-1-3-max.md)Max | 1,484.36 |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1484.3594923410437 \| rating \| reported \| Higher is better \| ### Configuration category instruction_following config text_style_control Reasoning effort max thinkingEnabled true ### Reported statistics lower 1476.4856905141376 rank 18 upper 1492.23329416795 variance 16.13885716421389 votes 6905 ### 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/7551/row` |  |  |  |
| 18 | [GPT-6.1 Sol](https://benchize.com/models/gpt-6-1-sol-max.md)Max | 1,484.04 |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1484.0394470136798 \| rating \| reported \| Higher is better \| ### Configuration category instruction_following config text_style_control Reasoning effort max thinkingEnabled true ### Reported statistics lower 1470.9993415778672 rank 19 upper 1497.0795524494924 variance 44.265566211740186 votes 2278 ### 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/7552/row` |  |  |  |
| 19 | [Gemini 3.1 Pro Preview](https://benchize.com/models/gemini-3-1-pro-preview.md) | 1,480.07 |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1480.0703264564227 \| rating \| reported \| Higher is better \| ### Configuration category instruction_following config text_style_control ### Reported statistics lower 1475.8284789546988 rank 21 upper 1484.3121739581468 variance 4.683968010004799 votes 44333 ### 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/7554/row` |  |  |  |
| 20 | [Claude Opus 4.8](https://benchize.com/models/claude-opus-4-8.md) | 1,477.91 |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1477.9107844871676 \| rating \| reported \| Higher is better \| ### Configuration category instruction_following config text_style_control ### Reported statistics lower 1472.584116294241 rank 22 upper 1483.2374526800943 variance 7.38609870934618 votes 23252 ### 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/7555/row` |  |  |  |
| 21 | [GPT-5.5](https://benchize.com/models/gpt-5-5-high.md)High | 1,477.45 |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1477.4521677012367 \| rating \| reported \| Higher is better \| ### Configuration category instruction_following config text_style_control Reasoning effort high thinkingEnabled true ### Reported statistics lower 1472.1497032117868 rank 24 upper 1482.7546321906868 variance 7.319128220356146 votes 24002 ### 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/7557/row` |  |  |  |
| 22 | [DeepSeek V4.1 Flash](https://benchize.com/models/deepseek-v4-1-flash-max.md)Max | 1,475.72 |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1475.7159413776305 \| rating \| reported \| Higher is better \| ### Configuration category instruction_following config text_style_control Reasoning effort max thinkingEnabled true ### Reported statistics lower 1466.6160614392659 rank 25 upper 1484.8158213159952 variance 21.556345846157054 votes 4725 ### 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/7558/row` |  |  |  |
| 23 | [Qwen3.8 Max](https://benchize.com/models/qwen3-8-max.md) | 1,475.15 |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1475.149532065561 \| rating \| reported \| Higher is better \| ### Configuration category instruction_following config text_style_control ### Reported statistics lower 1468.3776871313994 rank 26 upper 1481.9213769997227 variance 11.93762212555584 votes 10450 ### 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/7559/row` |  |  |  |
| 24 | [GPT-5.5](https://benchize.com/models/gpt-5-5.md) | 1,475.03 |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1475.0264080619565 \| rating \| reported \| Higher is better \| ### Configuration category instruction_following config text_style_control ### Reported statistics lower 1469.7802844304315 rank 27 upper 1480.2725316934816 variance 7.164417072228917 votes 24814 ### 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/7560/row` |  |  |  |
| 25 | [Claude Sonnet 4.6](https://benchize.com/models/claude-sonnet-4-6.md) | 1,474.42 |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1474.421634368168 \| rating \| reported \| Higher is better \| ### Configuration category instruction_following config text_style_control ### Reported statistics lower 1469.2315120621492 rank 28 upper 1479.6117566741868 variance 7.012276015122464 votes 23706 ### 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/7561/row` |  |  |  |
| 26 | [GPT-6 Astra](https://benchize.com/models/gpt-6-astra-max.md)Max | 1,472.67 |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1472.6668760903697 \| rating \| reported \| Higher is better \| ### Configuration category instruction_following config text_style_control Reasoning effort max thinkingEnabled true ### Reported statistics lower 1463.0933493886935 rank 30 upper 1482.2404027920459 variance 23.85875204856329 votes 4190 ### 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/7563/row` |  |  |  |
| 27 | [Muse Spark 1.1](https://benchize.com/models/muse-spark-1-1.md) | 1,472.61 |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1472.6077820445537 \| rating \| reported \| Higher is better \| ### Configuration category instruction_following config text_style_control ### Reported statistics lower 1466.7917494607998 rank 31 upper 1478.4238146283076 variance 8.805570121711064 votes 16036 ### 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/7564/row` |  |  |  |
| 28 | [Gemini 3.6 Flash](https://benchize.com/models/gemini-3-6-flash-high.md)High | 1,472.51 |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1472.510653185851 \| rating \| reported \| Higher is better \| ### Configuration category instruction_following config text_style_control Reasoning effort high thinkingEnabled true ### Reported statistics lower 1466.203014823647 rank 32 upper 1478.818291548055 variance 10.357081401996538 votes 13098 ### 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/7565/row` |  |  |  |
| 29 | [Gemini 3 Pro](https://benchize.com/models/gemini-3-pro.md) | 1,472.48 |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1472.482937596884 \| rating \| reported \| Higher is better \| ### Configuration category instruction_following config text_style_control ### Reported statistics lower 1466.2208855169845 rank 33 upper 1478.7449896767837 variance 10.207917898307354 votes 11692 ### 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/7566/row` |  |  |  |
| 30 | [MiMo-V2.6-Pro](https://benchize.com/models/mimo-v2-6-pro.md) | 1,471.56 |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1471.5630847619022 \| rating \| reported \| Higher is better \| ### Configuration category instruction_following config text_style_control ### Reported statistics lower 1455.8471854269683 rank 34 upper 1487.2789840968362 variance 64.29575414819921 votes 1391 ### 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/7567/row` |  |  |  |
| 31 | [Muse Spark 1.2](https://benchize.com/models/muse-spark-1-2-xhigh.md)Extra high | 1,471.14 |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1471.1409286398275 \| rating \| reported \| Higher is better \| ### Configuration category instruction_following config text_style_control Reasoning effort xhigh thinkingEnabled true ### Reported statistics lower 1460.5127316823955 rank 36 upper 1481.7691255972597 variance 29.40512337590503 votes 3379 ### 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/7569/row` |  |  |  |
| 32 | [GPT-5.4](https://benchize.com/models/gpt-5-4-high.md)High | 1,470.91 |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1470.9099691839697 \| rating \| reported \| Higher is better \| ### Configuration category instruction_following config text_style_control Reasoning effort high thinkingEnabled true ### Reported statistics lower 1465.4568690091105 rank 37 upper 1476.3630693588289 variance 7.740887747347007 votes 21863 ### 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/7570/row` |  |  |  |
| 33 | [MiMo-V2.5-Pro](https://benchize.com/models/mimo-v2-5-pro.md) | 1,467.4 |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1467.404556645284 \| rating \| reported \| Higher is better \| ### Configuration category instruction_following config text_style_control ### Reported statistics lower 1462.4002255464595 rank 39 upper 1472.4088877441081 variance 6.519223793771008 votes 25875 ### 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/7572/row` |  |  |  |
| 34 | [Gemini 3.5 Flash](https://benchize.com/models/gemini-3-5-flash-medium.md)Medium | 1,465.92 |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1465.918902230671 \| rating \| reported \| Higher is better \| ### Configuration category instruction_following config text_style_control Reasoning effort medium thinkingEnabled true ### Reported statistics lower 1460.1780075952308 rank 41 upper 1471.6597968661108 variance 8.579519592316647 votes 17046 ### 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/7574/row` |  |  |  |
| 35 | [Claude Sonnet 5](https://benchize.com/models/claude-sonnet-5-high.md)High | 1,465.9 |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1465.8965237105438 \| rating \| reported \| Higher is better \| ### Configuration category instruction_following config text_style_control Reasoning effort high thinkingEnabled true ### Reported statistics lower 1460.3063410601878 rank 42 upper 1471.4867063608995 variance 8.134967345216147 votes 17926 ### 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/7575/row` |  |  |  |
| 36 | [Gemini 3.5 Flash](https://benchize.com/models/gemini-3-5-flash-high.md)High | 1,465 |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1464.995711161747 \| rating \| reported \| Higher is better \| ### Configuration category instruction_following config text_style_control Reasoning effort high thinkingEnabled true ### Reported statistics lower 1459.3999079800615 rank 44 upper 1470.591514343433 variance 8.151333831688838 votes 17393 ### 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/7577/row` |  |  |  |
| 37 | [GPT-5.6 Terra](https://benchize.com/models/gpt-5-6-terra-xhigh.md)Extra high | 1,463.99 |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1463.9889428350946 \| rating \| reported \| Higher is better \| ### Configuration category instruction_following config text_style_control Reasoning effort xhigh thinkingEnabled true ### Reported statistics lower 1458.1126742824006 rank 46 upper 1469.8652113877886 variance 8.98891117024676 votes 16102 ### 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/7579/row` |  |  |  |
| 38 | [DeepSeek V4 Pro](https://benchize.com/models/deepseek-v4-pro-high-budget-20260813.md)High · 20260813 tokens | 1,461.47 |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1461.4701453825917 \| rating \| reported \| Higher is better \| ### Configuration category instruction_following config text_style_control reasoningBudget 20260813 Reasoning effort high thinkingEnabled true ### Reported statistics lower 1451.1901596719235 rank 50 upper 1471.7501310932596 variance 27.50988911874966 votes 3482 ### 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/7583/row` |  |  |  |
| 39 | [GPT-5.4](https://benchize.com/models/gpt-5-4.md) | 1,460.28 |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1460.2842524669582 \| rating \| reported \| Higher is better \| ### Configuration category instruction_following config text_style_control ### Reported statistics lower 1454.9155439865237 rank 52 upper 1465.6529609473926 variance 7.503147135827042 votes 23383 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label GPT-5.4 Observed 2026-10-21T18:45:05.190Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/7585/row` |  |  |  |
| 40 | [Gemini 3 Flash](https://benchize.com/models/gemini-3-flash.md) | 1,457.61 |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1457.609991390976 \| rating \| reported \| Higher is better \| ### Configuration category instruction_following config text_style_control ### Reported statistics lower 1450.489580459852 rank 54 upper 1464.7304023220997 variance 13.198176576810408 votes 8502 ### 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/7587/row` |  |  |  |
| 41 | [Gemma 4 31B](https://benchize.com/models/gemma-4-31b-it.md) | 1,453.57 |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1453.5740076663503 \| rating \| reported \| Higher is better \| ### Configuration category instruction_following config text_style_control ### Reported statistics lower 1439.9530087036112 rank 59 upper 1467.1950066290894 variance 48.297175995606324 votes 1798 ### 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/7592/row` |  |  |  |
| 42 | [DeepSeek V4 Pro](https://benchize.com/models/deepseek-v4-pro.md) | 1,452.73 |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1452.731140148001 \| rating \| reported \| Higher is better \| ### Configuration category instruction_following config text_style_control ### Reported statistics lower 1447.1579173652374 rank 60 upper 1458.3043629307647 variance 8.085681413266911 votes 20026 ### 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/7593/row` |  |  |  |
| 43 | [GPT-6 Sol](https://benchize.com/models/gpt-6-sol-max.md)Max | 1,451.9 |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1451.8961988114033 \| rating \| reported \| Higher is better \| ### Configuration category instruction_following config text_style_control Reasoning effort max thinkingEnabled true ### Reported statistics lower 1442.629913628748 rank 62 upper 1461.1624839940587 variance 22.351935838474894 votes 4626 ### 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/7595/row` |  |  |  |
| 44 | [Qwen3.6 Max Preview](https://benchize.com/models/qwen3-6-max-preview.md) | 1,451.15 |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1451.154957158159 \| rating \| reported \| Higher is better \| ### Configuration category instruction_following config text_style_control ### Reported statistics lower 1437.4319797809535 rank 64 upper 1464.8779345353646 variance 49.02307089192422 votes 1896 ### 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/7597/row` |  |  |  |
| 45 | [GPT-5.1](https://benchize.com/models/gpt-5-1-high.md)High | 1,450.26 |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1450.2594404818249 \| rating \| reported \| Higher is better \| ### Configuration category instruction_following config text_style_control Reasoning effort high thinkingEnabled true ### Reported statistics lower 1443.9142158283823 rank 65 upper 1456.6046651352674 variance 10.480881816502189 votes 11162 ### 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/7598/row` |  |  |  |
| 46 | [Hy3](https://benchize.com/models/hy3.md) | 1,447.29 |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1447.2880882657869 \| rating \| reported \| Higher is better \| ### Configuration category instruction_following config text_style_control ### Reported statistics lower 1438.2189013489178 rank 68 upper 1456.3572751826562 variance 21.411176111019373 votes 4617 ### 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/7601/row` |  |  |  |
| 47 | [MiMo-V2-Pro](https://benchize.com/models/mimo-v2-pro.md) | 1,445.02 |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1445.023385641013 \| rating \| reported \| Higher is better \| ### Configuration category instruction_following config text_style_control ### Reported statistics lower 1437.969327713734 rank 72 upper 1452.077443568292 variance 12.95334287415773 votes 8458 ### 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/7605/row` |  |  |  |
| 48 | [GPT-5.6 Luna](https://benchize.com/models/gpt-5-6-luna-xhigh.md)Extra high | 1,443.35 |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1443.3456268752213 \| rating \| reported \| Higher is better \| ### Configuration category instruction_following config text_style_control Reasoning effort xhigh thinkingEnabled true ### Reported statistics lower 1437.2601762390118 rank 75 upper 1449.4310775114309 variance 9.640272400226412 votes 14603 ### 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/7608/row` |  |  |  |
| 49 | [Step 5 Preview](https://benchize.com/models/step-5-preview.md) | 1,443.12 |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1443.1237317322682 \| rating \| reported \| Higher is better \| ### Configuration category instruction_following config text_style_control ### Reported statistics lower 1432.1503278418536 rank 76 upper 1454.0971356226828 variance 31.346318823849106 votes 3099 ### 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/7609/row` |  |  |  |
| 50 | [Gemini 3.5 Flash-Lite](https://benchize.com/models/gemini-3-5-flash-lite.md) | 1,443.06 |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1443.0622263517566 \| rating \| reported \| Higher is better \| ### Configuration category instruction_following config text_style_control ### Reported statistics lower 1436.7225899473167 rank 77 upper 1449.4018627561966 variance 10.462428888730619 votes 12907 ### 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/7610/row` |  |  |  |
| 51 | [Gemini 3 Flash](https://benchize.com/models/gemini-3-flash-minimal.md)Minimal | 1,443.05 |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1443.050641593839 \| rating \| reported \| Higher is better \| ### Configuration category instruction_following config text_style_control Reasoning effort minimal thinkingEnabled true ### Reported statistics lower 1438.4539393193252 rank 78 upper 1447.6473438683524 variance 5.500429078321194 votes 29797 ### 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/7611/row` |  |  |  |
| 52 | [MiMo-V2.6-Flash](https://benchize.com/models/mimo-v2-6-flash.md) | 1,440.77 |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1440.765925906116 \| rating \| reported \| Higher is better \| ### Configuration category instruction_following config text_style_control ### Reported statistics lower 1431.0860906495423 rank 79 upper 1450.4457611626901 variance 24.391569705146843 votes 4184 ### 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/7612/row` |  |  |  |
| 53 | [GPT-6 Luna](https://benchize.com/models/gpt-6-luna-max.md)Max | 1,439.94 |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1439.9444066532783 \| rating \| reported \| Higher is better \| ### Configuration category instruction_following config text_style_control Reasoning effort max thinkingEnabled true ### Reported statistics lower 1434.1577299086753 rank 80 upper 1445.7310833978813 variance 8.716903996507977 votes 21675 ### 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/7613/row` |  |  |  |
| 54 | [Beam 1.0 501B A23B](https://benchize.com/models/beam-1-0-501b-a23b.md) | 1,439 |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1439.0006197383677 \| rating \| reported \| Higher is better \| ### Configuration category instruction_following config text_style_control ### Reported statistics lower 1423.9630358403294 rank 82 upper 1454.0382036364063 variance 58.865379025378815 votes 1557 ### 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/7615/row` |  |  |  |
| 55 | [Gemini 2.5 Pro](https://benchize.com/models/gemini-2-5-pro.md) | 1,438.06 |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1438.055054286761 \| rating \| reported \| Higher is better \| ### Configuration category instruction_following config text_style_control ### Reported statistics lower 1434.2072891924327 rank 84 upper 1441.9028193810898 variance 3.854081720563142 votes 35196 ### 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/7617/row` |  |  |  |
| 56 | [Gemma 4 26B A4B](https://benchize.com/models/gemma-4-26b-a4b-it.md) | 1,437.35 |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1437.349721486601 \| rating \| reported \| Higher is better \| ### Configuration category instruction_following config text_style_control ### Reported statistics lower 1423.855573453357 rank 85 upper 1450.8438695198452 variance 47.401791778208434 votes 1736 ### 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/7618/row` |  |  |  |
| 57 | [GPT-5.3 Chat](https://benchize.com/models/gpt-5-3-chat.md) | 1,435.84 |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1435.8413134511552 \| rating \| reported \| Higher is better \| ### Configuration category instruction_following config text_style_control ### Reported statistics lower 1429.350811666194 rank 87 upper 1442.3318152361164 variance 10.966306131839067 votes 11216 ### 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/7620/row` |  |  |  |
| 58 | [MiniMax M3](https://benchize.com/models/minimax-m3.md) | 1,434.67 |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1434.6680938079085 \| rating \| reported \| Higher is better \| ### Configuration category instruction_following config text_style_control ### Reported statistics lower 1429.4335982649504 rank 90 upper 1439.9025893508663 variance 7.1326922578581495 votes 22903 ### 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/7623/row` |  |  |  |
| 59 | [GPT-5.4 Mini](https://benchize.com/models/gpt-5-4-mini-high.md)High | 1,434.39 |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1434.389313577486 \| rating \| reported \| Higher is better \| ### Configuration category instruction_following config text_style_control Reasoning effort high thinkingEnabled true ### Reported statistics lower 1428.9584259164312 rank 91 upper 1439.8202012385407 variance 7.677953132832655 votes 21732 ### 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/7624/row` |  |  |  |
| 60 | [Qwen3.5 397B A17B](https://benchize.com/models/qwen3-5-397b-a17b.md) | 1,433.79 |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1433.788664215889 \| rating \| reported \| Higher is better \| ### Configuration category instruction_following config text_style_control ### Reported statistics lower 1429.3850053427577 rank 92 upper 1438.1923230890204 variance 5.0481372770266 votes 32566 ### 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/7625/row` |  |  |  |
| 61 | [MiMo-V2.5](https://benchize.com/models/mimo-v2-5.md) | 1,431.67 |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1431.6661133493399 \| rating \| reported \| Higher is better \| ### Configuration category instruction_following config text_style_control ### Reported statistics lower 1425.5589279299309 rank 95 upper 1437.7732987687486 variance 9.709257729411613 votes 16053 ### 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/7628/row` |  |  |  |
| 62 | [DeepSeek V4 Flash](https://benchize.com/models/deepseek-v4-flash.md) | 1,427.94 |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1427.9436863073252 \| rating \| reported \| Higher is better \| ### Configuration category instruction_following config text_style_control ### Reported statistics lower 1422.1512212160997 rank 98 upper 1433.7361513985509 variance 8.734351557360998 votes 17950 ### 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/7631/row` |  |  |  |
| 63 | [MiMo-V2-Omni](https://benchize.com/models/mimo-v2-omni.md) | 1,427.56 |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1427.5610870718979 \| rating \| reported \| Higher is better \| ### Configuration category instruction_following config text_style_control ### Reported statistics lower 1419.5536720454638 rank 99 upper 1435.5685020983321 variance 16.691235907607147 votes 7039 ### 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/7632/row` |  |  |  |
| 64 | [GPT-5.2](https://benchize.com/models/gpt-5-2-high.md)High | 1,426.91 |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1426.91245189355 \| rating \| reported \| Higher is better \| ### Configuration category instruction_following config text_style_control Reasoning effort high thinkingEnabled true ### Reported statistics lower 1421.337863276828 rank 100 upper 1432.487040510272 variance 8.089645027112354 votes 15296 ### 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/7633/row` |  |  |  |
| 65 | [GPT-5.1](https://benchize.com/models/gpt-5-1.md) | 1,426.39 |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1426.387461667525 \| rating \| reported \| Higher is better \| ### Configuration category instruction_following config text_style_control ### Reported statistics lower 1420.4119172050155 rank 101 upper 1432.3630061300346 variance 9.295200935403114 votes 12323 ### 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/7634/row` |  |  |  |
| 66 | [GPT-5.2](https://benchize.com/models/gpt-5-2.md) | 1,423.71 |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1423.7050740579587 \| rating \| reported \| Higher is better \| ### Configuration category instruction_following config text_style_control ### Reported statistics lower 1418.9534902780351 rank 109 upper 1428.4566578378822 variance 5.877337092878852 votes 27793 ### 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/7642/row` |  |  |  |
| 67 | [Qwen3.8 27B](https://benchize.com/models/qwen3-8-27b.md) | 1,423.57 |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1423.5741413681505 \| rating \| reported \| Higher is better \| ### Configuration category instruction_following config text_style_control ### Reported statistics lower 1416.4049365750434 rank 110 upper 1430.743346161258 variance 13.379681981395118 votes 8906 ### 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/7643/row` |  |  |  |
| 68 | [Mistral Medium 3.5](https://benchize.com/models/mistral-medium-3-5.md) | 1,421.37 |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1421.3664149935353 \| rating \| reported \| Higher is better \| ### Configuration category instruction_following config text_style_control ### Reported statistics lower 1411.3748495194811 rank 111 upper 1431.3579804675894 variance 25.987882542047316 votes 3832 ### 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/7644/row` |  |  |  |
| 69 | [DeepSeek V3.2](https://benchize.com/models/deepseek-v3-2.md) | 1,420.3 |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1420.3049158188471 \| rating \| reported \| Higher is better \| ### Configuration category instruction_following config text_style_control ### Reported statistics lower 1414.5984622461744 rank 112 upper 1426.0113693915196 variance 8.476887010123873 votes 13557 ### 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/7645/row` |  |  |  |
| 70 | [DeepSeek V3.2](https://benchize.com/models/deepseek-v3-2-thinking.md)Thinking | 1,419.17 |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1419.1744065901437 \| rating \| reported \| Higher is better \| ### Configuration category instruction_following config text_style_control thinkingEnabled true ### Reported statistics lower 1413.278015529509 rank 113 upper 1425.070797650778 variance 9.05057926239797 votes 11719 ### 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/7646/row` |  |  |  |
| 71 | [DeepSeek V3.1 Terminus](https://benchize.com/models/deepseek-v3-1-terminus-thinking.md)Thinking | 1,417.81 |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1417.8087587143364 \| rating \| reported \| Higher is better \| ### Configuration category instruction_following config text_style_control thinkingEnabled true ### Reported statistics lower 1397.6850241381535 rank 116 upper 1437.9324932905195 variance 105.41950654555944 votes 858 ### 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/7649/row` |  |  |  |
| 72 | [DeepSeek V3.1](https://benchize.com/models/deepseek-v3-1-thinking.md)Thinking | 1,416.16 |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1416.1642671528373 \| rating \| reported \| Higher is better \| ### Configuration category instruction_following config text_style_control thinkingEnabled true ### Reported statistics lower 1405.0919881728257 rank 117 upper 1427.2365461328488 variance 31.913751398499794 votes 2833 ### 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/7650/row` |  |  |  |
| 73 | [DeepSeek V3.2 Exp](https://benchize.com/models/deepseek-v3-2-exp-thinking.md)Thinking | 1,415.72 |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1415.7160266422811 \| rating \| reported \| Higher is better \| ### Configuration category instruction_following config text_style_control thinkingEnabled true ### Reported statistics lower 1404.2381652426516 rank 120 upper 1427.1938880419107 variance 34.29460224834567 votes 2561 ### 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/7653/row` |  |  |  |
| 74 | [GPT-5 Chat](https://benchize.com/models/gpt-5-chat.md) | 1,414.82 |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1414.8210326080302 \| rating \| reported \| Higher is better \| ### Configuration category instruction_following config text_style_control ### Reported statistics lower 1407.8823204260248 rank 123 upper 1421.7597447900357 variance 12.533188299546122 votes 8236 ### 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/7656/row` |  |  |  |
| 75 | [Qwen3 235B A22B Instruct 2507](https://benchize.com/models/qwen3-235b-a22b-2507.md) | 1,414.3 |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1414.3018807016538 \| rating \| reported \| Higher is better \| ### Configuration category instruction_following config text_style_control ### Reported statistics lower 1410.2199927613904 rank 126 upper 1418.3837686419172 variance 4.337365030990261 votes 27848 ### 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/7659/row` |  |  |  |
| 76 | [DeepSeek V3.2 Exp](https://benchize.com/models/deepseek-v3-2-exp.md) | 1,413.98 |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1413.9822117137853 \| rating \| reported \| Higher is better \| ### Configuration category instruction_following config text_style_control ### Reported statistics lower 1403.7530081467182 rank 128 upper 1424.2114152808522 variance 27.23876800469957 votes 3389 ### 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/7661/row` |  |  |  |
| 77 | [GPT-5](https://benchize.com/models/gpt-5-high.md)High | 1,410.12 |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1410.118333993512 \| rating \| reported \| Higher is better \| ### Configuration category instruction_following config text_style_control Reasoning effort high thinkingEnabled true ### Reported statistics lower 1402.9585780240413 rank 133 upper 1417.2780899629827 variance 13.344437083698269 votes 8372 ### 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/7666/row` |  |  |  |
| 78 | [Qwen3 VL 235B A22B Instruct](https://benchize.com/models/qwen3-vl-235b-a22b-instruct.md) | 1,408.93 |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1408.9313807666304 \| rating \| reported \| Higher is better \| ### Configuration category instruction_following config text_style_control ### Reported statistics lower 1397.7132891243518 rank 134 upper 1420.1494724089089 variance 32.75984097932353 votes 2946 ### 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/7667/row` |  |  |  |
| 79 | [Gemini 3.1 Flash Lite Preview](https://benchize.com/models/gemini-3-1-flash-lite-preview.md) | 1,408.37 |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1408.3729473367837 \| rating \| reported \| Higher is better \| ### Configuration category instruction_following config text_style_control ### Reported statistics lower 1403.0570680505673 rank 135 upper 1413.6888266229998 variance 7.356208644849517 votes 21488 ### 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/7668/row` |  |  |  |
| 80 | [MiniMax M2.7](https://benchize.com/models/minimax-m2-7.md) | 1,408.12 |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1408.1220877997414 \| rating \| reported \| Higher is better \| ### Configuration category instruction_following config text_style_control ### Reported statistics lower 1403.3975106933412 rank 136 upper 1412.8466649061413 variance 5.810716677235203 votes 29021 ### 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/7669/row` |  |  |  |
| 81 | [Qwen3.5-122B-A10B](https://benchize.com/models/qwen3-5-122b-a10b.md) | 1,405.81 |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1405.8100408807175 \| rating \| reported \| Higher is better \| ### Configuration category instruction_following config text_style_control ### Reported statistics lower 1399.2191568235783 rank 138 upper 1412.4009249378564 variance 11.308139611086753 votes 9572 ### 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/7671/row` |  |  |  |
| 82 | [DeepSeek V3.1](https://benchize.com/models/deepseek-v3-1.md) | 1,402.37 |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1402.370644227312 \| rating \| reported \| Higher is better \| ### Configuration category instruction_following config text_style_control ### Reported statistics lower 1392.5433742327918 rank 144 upper 1412.1979142218322 variance 25.14025011147903 votes 3680 ### 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/7677/row` |  |  |  |
| 83 | [Mistral Large 3](https://benchize.com/models/mistral-large-3.md) | 1,402.29 |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1402.2886811138555 \| rating \| reported \| Higher is better \| ### Configuration category instruction_following config text_style_control ### Reported statistics lower 1397.9495675393914 rank 145 upper 1406.6277946883197 variance 4.901238693662907 votes 27793 ### 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/7678/row` |  |  |  |
| 84 | [Qwen3.5-27B](https://benchize.com/models/qwen3-5-27b.md) | 1,400.86 |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1400.8590777475001 \| rating \| reported \| Higher is better \| ### Configuration category instruction_following config text_style_control ### Reported statistics lower 1394.2424966026413 rank 147 upper 1407.4756588923588 variance 11.396489742558085 votes 9231 ### 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/7680/row` |  |  |  |
| 85 | [Gemini 2.5 Flash](https://benchize.com/models/gemini-2-5-flash.md) | 1,399.39 |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1399.3875414905804 \| rating \| reported \| Higher is better \| ### Configuration category instruction_following config text_style_control ### Reported statistics lower 1395.5823662441164 rank 149 upper 1403.1927167370445 variance 3.7692343799969246 votes 34833 ### 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/7682/row` |  |  |  |
| 86 | [DeepSeek R1](https://benchize.com/models/deepseek-r1.md) | 1,397.2 |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1397.2048675930769 \| rating \| reported \| Higher is better \| ### Configuration category instruction_following config text_style_control ### Reported statistics lower 1389.6809981231197 rank 151 upper 1404.7287370630343 variance 14.736227678922633 votes 6426 ### 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/7684/row` |  |  |  |
| 87 | [Hy3 preview](https://benchize.com/models/hy3-preview.md) | 1,395.99 |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1395.9900271783524 \| rating \| reported \| Higher is better \| ### Configuration category instruction_following config text_style_control ### Reported statistics lower 1383.5478129265894 rank 154 upper 1408.4322414301153 variance 40.29945463760025 votes 2336 ### 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/7687/row` |  |  |  |
| 88 | [DeepSeek V3.1 Terminus](https://benchize.com/models/deepseek-v3-1-terminus.md) | 1,393.84 |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1393.8366788692108 \| rating \| reported \| Higher is better \| ### Configuration category instruction_following config text_style_control ### Reported statistics lower 1376.0327188112185 rank 160 upper 1411.6406389272029 variance 82.51578594022385 votes 1019 ### 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/7693/row` |  |  |  |
| 89 | [R1 0528](https://benchize.com/models/deepseek-r1-0528.md) | 1,391.05 |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1391.0522864098332 \| rating \| reported \| Higher is better \| ### Configuration category instruction_following config text_style_control ### Reported statistics lower 1381.5123477489262 rank 161 upper 1400.59222507074 variance 23.69163224230986 votes 4015 ### 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/7694/row` |  |  |  |
| 90 | [GPT-5.4 Nano](https://benchize.com/models/gpt-5-4-nano-high.md)High | 1,386.75 |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1386.7461255151288 \| rating \| reported \| Higher is better \| ### Configuration category instruction_following config text_style_control Reasoning effort high thinkingEnabled true ### Reported statistics lower 1381.2263837907826 rank 165 upper 1392.2658672394748 variance 7.931244385428999 votes 21465 ### 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/7698/row` |  |  |  |
| 91 | [Qwen3.5-35B-A3B](https://benchize.com/models/qwen3-5-35b-a3b.md) | 1,386.56 |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1386.560668482073 \| rating \| reported \| Higher is better \| ### Configuration category instruction_following config text_style_control ### Reported statistics lower 1380.0953650204706 rank 166 upper 1393.0259719436754 variance 10.881321602467237 votes 9945 ### 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/7699/row` |  |  |  |
| 92 | [Qwen3 235B A22B Thinking 2507](https://benchize.com/models/qwen3-235b-a22b-thinking-2507.md) | 1,385.48 |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1385.4769767672176 \| rating \| reported \| Higher is better \| ### Configuration category instruction_following config text_style_control ### Reported statistics lower 1372.9963615167578 rank 167 upper 1397.9575920176774 variance 40.54859476584558 votes 2094 ### 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/7700/row` |  |  |  |
| 93 | [Step 3.5 Flash](https://benchize.com/models/step-3-5-flash.md) | 1,384.1 |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1384.0957008422617 \| rating \| reported \| Higher is better \| ### Configuration category instruction_following config text_style_control ### Reported statistics lower 1378.84425783324 rank 170 upper 1389.3471438512836 variance 7.178953351898765 votes 19314 ### 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/7703/row` |  |  |  |
| 94 | [MiMo-V2-Flash](https://benchize.com/models/mimo-v2-flash-off.md)Non-thinking | 1,382.19 |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1382.1859088852266 \| rating \| reported \| Higher is better \| ### Configuration category instruction_following config text_style_control thinkingEnabled false ### Reported statistics lower 1376.6636571679237 rank 172 upper 1387.7081606025295 variance 7.938459177272951 votes 14749 ### 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/7705/row` |  |  |  |
| 95 | [Qwen3 VL 235B A22B Thinking](https://benchize.com/models/qwen3-vl-235b-a22b-thinking.md) | 1,382.07 |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1382.0670994158627 \| rating \| reported \| Higher is better \| ### Configuration category instruction_following config text_style_control ### Reported statistics lower 1369.82644088078 rank 173 upper 1394.3077579509454 variance 39.00438046226956 votes 2156 ### 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/7706/row` |  |  |  |
| 96 | [MiniMax M2.5](https://benchize.com/models/minimax-m2-5.md) | 1,381.16 |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1381.1576498634195 \| rating \| reported \| Higher is better \| ### Configuration category instruction_following config text_style_control ### Reported statistics lower 1375.2769450526948 rank 175 upper 1387.0383546741443 variance 9.00248855580156 votes 13767 ### 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/7708/row` |  |  |  |
| 97 | [Qwen3 235B A22B](https://benchize.com/models/qwen3-235b-a22b-off.md)Non-thinking | 1,380.87 |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1380.867953481401 \| rating \| reported \| Higher is better \| ### Configuration category instruction_following config text_style_control thinkingEnabled false ### Reported statistics lower 1374.0488020101102 rank 177 upper 1387.6871049526917 variance 12.10499160837113 votes 9220 ### 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/7710/row` |  |  |  |
| 98 | [Solar Pro 4](https://benchize.com/models/solar-pro4.md) | 1,378.27 |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1378.2719039572771 \| rating \| reported \| Higher is better \| ### Configuration category instruction_following config text_style_control ### Reported statistics lower 1370.9154326135945 rank 179 upper 1385.62837530096 variance 14.087791424156435 votes 8359 ### 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/7712/row` |  |  |  |
| 99 | [DeepSeek V3 0324](https://benchize.com/models/deepseek-chat-v3-0324.md) | 1,377.69 |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1377.6908839716273 \| rating \| reported \| Higher is better \| ### Configuration category instruction_following config text_style_control ### Reported statistics lower 1371.798958481195 rank 180 upper 1383.5828094620592 variance 9.036875730072317 votes 12413 ### 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/7713/row` |  |  |  |
| 100 | [Qwen3 Next 80B A3B Instruct](https://benchize.com/models/qwen3-next-80b-a3b-instruct.md) | 1,376.09 |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1376.0915571989735 \| rating \| reported \| Higher is better \| ### Configuration category instruction_following config text_style_control ### Reported statistics lower 1368.5303228110297 rank 181 upper 1383.6527915869174 variance 14.88295674586823 votes 6416 ### 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/7714/row` |  |  |  |

[Next page](https://benchize.com/benchmarks/lmarena%3Atext_style_control%3Ainstruction_following.md?cursor=%7B%22score%22%3A1376.0915571989735%2C%22id%22%3A%22724ef6ab7d63babfe9532a6c02c0dc9c409eb4d9e1e1075c4d61e1c83662efae%22%7D)

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