# Arena vision style control / ocr

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

Human pairwise preferences on ocr prompts in Arena’s vision 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%3Avision_style_control%3Aocr
Last updated: Wed, 21 Oct 2026 18:05:10 GMT

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

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

Multimodal · Models tested: 74 · Score publishers: [Arena](https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset)

## Model results

| # | Model | Score |  |
| --- | --- | --- | --- |
| 1 | [Claude Fable 5](https://benchize.com/models/claude-fable-5-high.md)High | 1,326.39 |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1326.390158119073 \| rating \| reported \| Higher is better \| ### Configuration category ocr config vision_style_control Reasoning effort high thinkingEnabled true ### Reported statistics lower 1319.0541903625644 rank 1 upper 1333.7261258755814 variance 14.009371292650693 votes 10497 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/vision_style_control/latest) Source Arena Original model label Claude Fable 5 (High) Observed 2026-10-21T16:40:19.533Z Evidence SHA-256 `38568936995f36625aae49e9ea05557d55c1b1df9b2954f5c50cee523f26fe92` Source locator `/rows/1019/row` |  |  |  |
| 2 | [Gemini 3.8 Flash](https://benchize.com/models/gemini-3-8-flash-high.md)High | 1,316.02 |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1316.0239835468183 \| rating \| reported \| Higher is better \| ### Configuration category ocr config vision_style_control Reasoning effort high thinkingEnabled true ### Reported statistics lower 1304.7849197536723 rank 2 upper 1327.2630473399643 variance 32.88244410324851 votes 3137 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/vision_style_control/latest) Source Arena Original model label Gemini 3.8 Flash (High) Observed 2026-10-21T16:40:19.533Z Evidence SHA-256 `38568936995f36625aae49e9ea05557d55c1b1df9b2954f5c50cee523f26fe92` Source locator `/rows/1020/row` |  |  |  |
| 3 | [Qwen3.8 Max](https://benchize.com/models/qwen3-8-max.md) | 1,315.92 |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1315.9189197251721 \| rating \| reported \| Higher is better \| ### Configuration category ocr config vision_style_control ### Reported statistics lower 1307.969499283218 rank 3 upper 1323.8683401671265 variance 16.450335227475012 votes 6896 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/vision_style_control/latest) Source Arena Original model label Qwen3.8-Max Observed 2026-10-21T16:40:19.533Z Evidence SHA-256 `38568936995f36625aae49e9ea05557d55c1b1df9b2954f5c50cee523f26fe92` Source locator `/rows/1021/row` |  |  |  |
| 4 | [Claude Opus 4.7](https://benchize.com/models/claude-opus-4-7.md) | 1,314.04 |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1314.0423675422626 \| rating \| reported \| Higher is better \| ### Configuration category ocr config vision_style_control ### Reported statistics lower 1307.376738442742 rank 4 upper 1320.707996641783 variance 11.566077723656614 votes 16736 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/vision_style_control/latest) Source Arena Original model label Claude Opus 4.7 Observed 2026-10-21T16:40:19.533Z Evidence SHA-256 `38568936995f36625aae49e9ea05557d55c1b1df9b2954f5c50cee523f26fe92` Source locator `/rows/1022/row` |  |  |  |
| 5 | [Claude Opus 4.6](https://benchize.com/models/claude-opus-4-6-high.md)High | 1,313.64 |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1313.6379956602605 \| rating \| reported \| Higher is better \| ### Configuration category ocr config vision_style_control Reasoning effort high thinkingEnabled true ### Reported statistics lower 1307.0691385945831 rank 5 upper 1320.206852725938 variance 11.232681427391682 votes 15908 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/vision_style_control/latest) Source Arena Original model label Claude Opus 4.6 (High) Observed 2026-10-21T16:40:19.533Z Evidence SHA-256 `38568936995f36625aae49e9ea05557d55c1b1df9b2954f5c50cee523f26fe92` Source locator `/rows/1023/row` |  |  |  |
| 6 | [Claude Opus 4.6](https://benchize.com/models/claude-opus-4-6.md) | 1,311.82 |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1311.8202587492563 \| rating \| reported \| Higher is better \| ### Configuration category ocr config vision_style_control ### Reported statistics lower 1305.4964072977968 rank 6 upper 1318.1441102007154 variance 10.410393302848622 votes 19407 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/vision_style_control/latest) Source Arena Original model label Claude Opus 4.6 Observed 2026-10-21T16:40:19.533Z Evidence SHA-256 `38568936995f36625aae49e9ea05557d55c1b1df9b2954f5c50cee523f26fe92` Source locator `/rows/1024/row` |  |  |  |
| 7 | [Claude Opus 4.7](https://benchize.com/models/claude-opus-4-7-high.md)High | 1,310.78 |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1310.7794334699593 \| rating \| reported \| Higher is better \| ### Configuration category ocr config vision_style_control Reasoning effort high thinkingEnabled true ### Reported statistics lower 1304.175266418251 rank 7 upper 1317.3836005216674 variance 11.353765452830118 votes 16364 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/vision_style_control/latest) Source Arena Original model label Claude Opus 4.7 (High) Observed 2026-10-21T16:40:19.533Z Evidence SHA-256 `38568936995f36625aae49e9ea05557d55c1b1df9b2954f5c50cee523f26fe92` Source locator `/rows/1025/row` |  |  |  |
| 8 | [Gemini 3.7 Flash](https://benchize.com/models/gemini-3-7-flash-high.md)High | 1,308.31 |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1308.3091395332024 \| rating \| reported \| Higher is better \| ### Configuration category ocr config vision_style_control Reasoning effort high thinkingEnabled true ### Reported statistics lower 1297.9346480032136 rank 8 upper 1318.6836310631913 variance 28.01802115540132 votes 3653 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/vision_style_control/latest) Source Arena Original model label Gemini 3.7 Flash (High) Observed 2026-10-21T16:40:19.533Z Evidence SHA-256 `38568936995f36625aae49e9ea05557d55c1b1df9b2954f5c50cee523f26fe92` Source locator `/rows/1026/row` |  |  |  |
| 9 | [Muse Spark 1.3](https://benchize.com/models/muse-spark-1-3-max.md)Max | 1,307.29 |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1307.2923011389 \| rating \| reported \| Higher is better \| ### Configuration category ocr config vision_style_control Reasoning effort max thinkingEnabled true ### Reported statistics lower 1296.894612856387 rank 9 upper 1317.6899894214127 variance 28.143454522510943 votes 3701 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/vision_style_control/latest) Source Arena Original model label Muse Spark 1.3 (Max) Observed 2026-10-21T16:40:19.533Z Evidence SHA-256 `38568936995f36625aae49e9ea05557d55c1b1df9b2954f5c50cee523f26fe92` Source locator `/rows/1027/row` |  |  |  |
| 10 | [Muse Spark 1.2](https://benchize.com/models/muse-spark-1-2-xhigh.md)Extra high | 1,306.63 |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1306.6306926135078 \| rating \| reported \| Higher is better \| ### Configuration category ocr config vision_style_control Reasoning effort xhigh thinkingEnabled true ### Reported statistics lower 1289.7232923249994 rank 10 upper 1323.5380929020162 variance 74.41448623005148 votes 1343 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/vision_style_control/latest) Source Arena Original model label Muse Spark 1.2 (xHigh) Observed 2026-10-21T16:40:19.533Z Evidence SHA-256 `38568936995f36625aae49e9ea05557d55c1b1df9b2954f5c50cee523f26fe92` Source locator `/rows/1028/row` |  |  |  |
| 11 | [Claude Opus 5.5](https://benchize.com/models/claude-opus-5-5-high.md)High | 1,305.99 |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1305.988248826146 \| rating \| reported \| Higher is better \| ### Configuration category ocr config vision_style_control Reasoning effort high thinkingEnabled true ### Reported statistics lower 1292.409206060833 rank 11 upper 1319.5672915914593 variance 48.00009866795541 votes 2118 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/vision_style_control/latest) Source Arena Original model label Claude Opus 5.5 (High) Observed 2026-10-21T16:40:19.533Z Evidence SHA-256 `38568936995f36625aae49e9ea05557d55c1b1df9b2954f5c50cee523f26fe92` Source locator `/rows/1029/row` |  |  |  |
| 12 | [Claude Opus 5](https://benchize.com/models/claude-opus-5-high.md)High | 1,304.05 |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1304.0534225638908 \| rating \| reported \| Higher is better \| ### Configuration category ocr config vision_style_control Reasoning effort high thinkingEnabled true ### Reported statistics lower 1297.1171308779558 rank 12 upper 1310.989714249826 variance 12.524445685371035 votes 12218 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/vision_style_control/latest) Source Arena Original model label Claude Opus 5 (High) Observed 2026-10-21T16:40:19.533Z Evidence SHA-256 `38568936995f36625aae49e9ea05557d55c1b1df9b2954f5c50cee523f26fe92` Source locator `/rows/1030/row` |  |  |  |
| 13 | [Claude Fable 5.1](https://benchize.com/models/claude-fable-5-1-max.md)Max | 1,303.14 |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1303.1400372691112 \| rating \| reported \| Higher is better \| ### Configuration category ocr config vision_style_control Reasoning effort max thinkingEnabled true ### Reported statistics lower 1292.6553969426488 rank 13 upper 1313.6246775955738 variance 28.616129420181373 votes 3456 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/vision_style_control/latest) Source Arena Original model label Claude Fable 5.1 (Max) Observed 2026-10-21T16:40:19.533Z Evidence SHA-256 `38568936995f36625aae49e9ea05557d55c1b1df9b2954f5c50cee523f26fe92` Source locator `/rows/1031/row` |  |  |  |
| 14 | [Gemini 3 Pro](https://benchize.com/models/gemini-3-pro.md) | 1,302.17 |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1302.174910886506 \| rating \| reported \| Higher is better \| ### Configuration category ocr config vision_style_control ### Reported statistics lower 1293.8834001310702 rank 15 upper 1310.4664216419417 variance 17.89662568739554 votes 8321 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/vision_style_control/latest) Source Arena Original model label Gemini 3 Pro Observed 2026-10-21T16:40:19.533Z Evidence SHA-256 `38568936995f36625aae49e9ea05557d55c1b1df9b2954f5c50cee523f26fe92` Source locator `/rows/1033/row` |  |  |  |
| 15 | [Gemini 3.6 Flash](https://benchize.com/models/gemini-3-6-flash-high.md)High | 1,300.74 |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1300.7393474092178 \| rating \| reported \| Higher is better \| ### Configuration category ocr config vision_style_control Reasoning effort high thinkingEnabled true ### Reported statistics lower 1292.267536992614 rank 16 upper 1309.2111578258216 variance 18.683415620190814 votes 6075 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/vision_style_control/latest) Source Arena Original model label Gemini 3.6 Flash (High) Observed 2026-10-21T16:40:19.533Z Evidence SHA-256 `38568936995f36625aae49e9ea05557d55c1b1df9b2954f5c50cee523f26fe92` Source locator `/rows/1034/row` |  |  |  |
| 16 | [Muse Spark 1.3](https://benchize.com/models/muse-spark-1-3-xhigh.md)Extra high | 1,300.34 |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1300.338750179862 \| rating \| reported \| Higher is better \| ### Configuration category ocr config vision_style_control Reasoning effort xhigh thinkingEnabled true ### Reported statistics lower 1289.3998327015083 rank 17 upper 1311.2776676582157 variance 31.149602581607407 votes 3280 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/vision_style_control/latest) Source Arena Original model label Muse Spark 1.3 (xHigh) Observed 2026-10-21T16:40:19.533Z Evidence SHA-256 `38568936995f36625aae49e9ea05557d55c1b1df9b2954f5c50cee523f26fe92` Source locator `/rows/1035/row` |  |  |  |
| 17 | [GPT-6 Astra](https://benchize.com/models/gpt-6-astra-max.md)Max | 1,299.24 |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1299.2373217320571 \| rating \| reported \| Higher is better \| ### Configuration category ocr config vision_style_control Reasoning effort max thinkingEnabled true ### Reported statistics lower 1287.3790147371444 rank 18 upper 1311.09562872697 variance 36.605740514013696 votes 2740 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/vision_style_control/latest) Source Arena Original model label GPT-6 Astra (Max) Observed 2026-10-21T16:40:19.533Z Evidence SHA-256 `38568936995f36625aae49e9ea05557d55c1b1df9b2954f5c50cee523f26fe92` Source locator `/rows/1036/row` |  |  |  |
| 18 | [Gemini 3.5 Flash](https://benchize.com/models/gemini-3-5-flash-medium.md)Medium | 1,299.15 |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1299.1499500407633 \| rating \| reported \| Higher is better \| ### Configuration category ocr config vision_style_control Reasoning effort medium thinkingEnabled true ### Reported statistics lower 1292.0357162126713 rank 19 upper 1306.2641838688553 variance 13.175287130013698 votes 9712 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/vision_style_control/latest) Source Arena Original model label Gemini 3.5 Flash (Medium) Observed 2026-10-21T16:40:19.533Z Evidence SHA-256 `38568936995f36625aae49e9ea05557d55c1b1df9b2954f5c50cee523f26fe92` Source locator `/rows/1037/row` |  |  |  |
| 19 | [GPT-5.5](https://benchize.com/models/gpt-5-5.md) | 1,298.96 |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1298.961421074777 \| rating \| reported \| Higher is better \| ### Configuration category ocr config vision_style_control ### Reported statistics lower 1293.1588057477943 rank 20 upper 1304.7640364017598 variance 8.764989084758925 votes 20286 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/vision_style_control/latest) Source Arena Original model label GPT-5.5 Observed 2026-10-21T16:40:19.533Z Evidence SHA-256 `38568936995f36625aae49e9ea05557d55c1b1df9b2954f5c50cee523f26fe92` Source locator `/rows/1038/row` |  |  |  |
| 20 | [Claude Opus 4.8](https://benchize.com/models/claude-opus-4-8-high.md)High | 1,298.95 |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1298.948760225173 \| rating \| reported \| Higher is better \| ### Configuration category ocr config vision_style_control Reasoning effort high thinkingEnabled true ### Reported statistics lower 1292.2877797825377 rank 21 upper 1305.6097406678084 variance 11.549950820286163 votes 12994 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/vision_style_control/latest) Source Arena Original model label Claude Opus 4.8 (High) Observed 2026-10-21T16:40:19.533Z Evidence SHA-256 `38568936995f36625aae49e9ea05557d55c1b1df9b2954f5c50cee523f26fe92` Source locator `/rows/1039/row` |  |  |  |
| 21 | [GPT-5.4](https://benchize.com/models/gpt-5-4-high.md)High | 1,298.81 |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1298.8084929495358 \| rating \| reported \| Higher is better \| ### Configuration category ocr config vision_style_control Reasoning effort high thinkingEnabled true ### Reported statistics lower 1293.0691728046452 rank 22 upper 1304.5478130944261 variance 8.574814221122653 votes 21790 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/vision_style_control/latest) Source Arena Original model label GPT-5.4 (High) Observed 2026-10-21T16:40:19.533Z Evidence SHA-256 `38568936995f36625aae49e9ea05557d55c1b1df9b2954f5c50cee523f26fe92` Source locator `/rows/1040/row` |  |  |  |
| 22 | [GPT-5.6 Sol](https://benchize.com/models/gpt-5-6-sol-xhigh.md)Extra high | 1,297.44 |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1297.4432123941049 \| rating \| reported \| Higher is better \| ### Configuration category ocr config vision_style_control Reasoning effort xhigh thinkingEnabled true ### Reported statistics lower 1289.6590451946838 rank 23 upper 1305.2273795935262 variance 15.773502155516033 votes 7710 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/vision_style_control/latest) Source Arena Original model label GPT-5.6 Sol (xHigh) Observed 2026-10-21T16:40:19.533Z Evidence SHA-256 `38568936995f36625aae49e9ea05557d55c1b1df9b2954f5c50cee523f26fe92` Source locator `/rows/1041/row` |  |  |  |
| 23 | [GPT-5.5](https://benchize.com/models/gpt-5-5-high.md)High | 1,297 |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1297.004611348844 \| rating \| reported \| Higher is better \| ### Configuration category ocr config vision_style_control Reasoning effort high thinkingEnabled true ### Reported statistics lower 1291.13522433841 rank 24 upper 1302.8739983592782 variance 8.967870146796896 votes 18851 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/vision_style_control/latest) Source Arena Original model label GPT-5.5 (High) Observed 2026-10-21T16:40:19.533Z Evidence SHA-256 `38568936995f36625aae49e9ea05557d55c1b1df9b2954f5c50cee523f26fe92` Source locator `/rows/1042/row` |  |  |  |
| 24 | [GPT-6.1 Sol](https://benchize.com/models/gpt-6-1-sol-max.md)Max | 1,296.73 |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1296.7343184533854 \| rating \| reported \| Higher is better \| ### Configuration category ocr config vision_style_control Reasoning effort max thinkingEnabled true ### Reported statistics lower 1281.8714962546267 rank 25 upper 1311.5971406521442 variance 57.50510262452774 votes 1654 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/vision_style_control/latest) Source Arena Original model label GPT-6.1 Sol (Max) Observed 2026-10-21T16:40:19.533Z Evidence SHA-256 `38568936995f36625aae49e9ea05557d55c1b1df9b2954f5c50cee523f26fe92` Source locator `/rows/1043/row` |  |  |  |
| 25 | [Muse Spark 1.1](https://benchize.com/models/muse-spark-1-1.md) | 1,294.62 |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1294.6171337347164 \| rating \| reported \| Higher is better \| ### Configuration category ocr config vision_style_control ### Reported statistics lower 1287.2706001855488 rank 26 upper 1301.963667283884 variance 14.04975497805609 votes 8699 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/vision_style_control/latest) Source Arena Original model label Muse Spark 1.1 Observed 2026-10-21T16:40:19.533Z Evidence SHA-256 `38568936995f36625aae49e9ea05557d55c1b1df9b2954f5c50cee523f26fe92` Source locator `/rows/1044/row` |  |  |  |
| 26 | [Gemini 3.1 Pro Preview](https://benchize.com/models/gemini-3-1-pro-preview.md) | 1,294.2 |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1294.1983479852643 \| rating \| reported \| Higher is better \| ### Configuration category ocr config vision_style_control ### Reported statistics lower 1289.212063868414 rank 27 upper 1299.1846321021144 variance 6.472288381698778 votes 32719 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/vision_style_control/latest) Source Arena Original model label Gemini 3.1 Pro Preview Observed 2026-10-21T16:40:19.533Z Evidence SHA-256 `38568936995f36625aae49e9ea05557d55c1b1df9b2954f5c50cee523f26fe92` Source locator `/rows/1045/row` |  |  |  |
| 27 | [Claude Opus 4.8](https://benchize.com/models/claude-opus-4-8.md) | 1,293.06 |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1293.0589785225222 \| rating \| reported \| Higher is better \| ### Configuration category ocr config vision_style_control ### Reported statistics lower 1286.3753256684195 rank 28 upper 1299.7426313766252 variance 11.628711268102826 votes 13248 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/vision_style_control/latest) Source Arena Original model label Claude Opus 4.8 Observed 2026-10-21T16:40:19.533Z Evidence SHA-256 `38568936995f36625aae49e9ea05557d55c1b1df9b2954f5c50cee523f26fe92` Source locator `/rows/1046/row` |  |  |  |
| 28 | [Gemini 3.5 Flash](https://benchize.com/models/gemini-3-5-flash-high.md)High | 1,292.36 |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1292.3606194925915 \| rating \| reported \| Higher is better \| ### Configuration category ocr config vision_style_control Reasoning effort high thinkingEnabled true ### Reported statistics lower 1285.2411285694295 rank 29 upper 1299.4801104157532 variance 13.194766199739103 votes 9583 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/vision_style_control/latest) Source Arena Original model label Gemini 3.5 Flash (High) Observed 2026-10-21T16:40:19.533Z Evidence SHA-256 `38568936995f36625aae49e9ea05557d55c1b1df9b2954f5c50cee523f26fe92` Source locator `/rows/1047/row` |  |  |  |
| 29 | [Claude Sonnet 4.6](https://benchize.com/models/claude-sonnet-4-6.md) | 1,290.82 |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1290.8243585436205 \| rating \| reported \| Higher is better \| ### Configuration category ocr config vision_style_control ### Reported statistics lower 1284.6425036486369 rank 30 upper 1297.0062134386044 variance 9.948129532657452 votes 19839 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/vision_style_control/latest) Source Arena Original model label Claude Sonnet 4.6 Observed 2026-10-21T16:40:19.533Z Evidence SHA-256 `38568936995f36625aae49e9ea05557d55c1b1df9b2954f5c50cee523f26fe92` Source locator `/rows/1048/row` |  |  |  |
| 30 | [GPT-5.4](https://benchize.com/models/gpt-5-4.md) | 1,290.35 |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1290.3459332347802 \| rating \| reported \| Higher is better \| ### Configuration category ocr config vision_style_control ### Reported statistics lower 1283.704823214727 rank 31 upper 1296.9870432548337 variance 11.481144106208058 votes 16434 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/vision_style_control/latest) Source Arena Original model label GPT-5.4 Observed 2026-10-21T16:40:19.533Z Evidence SHA-256 `38568936995f36625aae49e9ea05557d55c1b1df9b2954f5c50cee523f26fe92` Source locator `/rows/1049/row` |  |  |  |
| 31 | [GPT-6 Sol](https://benchize.com/models/gpt-6-sol-max.md)Max | 1,285.47 |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1285.4738873981016 \| rating \| reported \| Higher is better \| ### Configuration category ocr config vision_style_control Reasoning effort max thinkingEnabled true ### Reported statistics lower 1272.5263568024943 rank 35 upper 1298.4214179937092 variance 43.63929339060235 votes 2285 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/vision_style_control/latest) Source Arena Original model label GPT-6 Sol (Max) Observed 2026-10-21T16:40:19.533Z Evidence SHA-256 `38568936995f36625aae49e9ea05557d55c1b1df9b2954f5c50cee523f26fe92` Source locator `/rows/1053/row` |  |  |  |
| 32 | [Gemini 3 Flash](https://benchize.com/models/gemini-3-flash.md) | 1,284.91 |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1284.9091089937074 \| rating \| reported \| Higher is better \| ### Configuration category ocr config vision_style_control ### Reported statistics lower 1279.8074071415635 rank 36 upper 1290.0108108458514 variance 6.775384822026095 votes 26690 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/vision_style_control/latest) Source Arena Original model label Gemini 3 Flash Observed 2026-10-21T16:40:19.533Z Evidence SHA-256 `38568936995f36625aae49e9ea05557d55c1b1df9b2954f5c50cee523f26fe92` Source locator `/rows/1054/row` |  |  |  |
| 33 | [Gemini 3.5 Flash-Lite](https://benchize.com/models/gemini-3-5-flash-lite.md) | 1,281.92 |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1281.9227538975608 \| rating \| reported \| Higher is better \| ### Configuration category ocr config vision_style_control ### Reported statistics lower 1273.5054904985482 rank 38 upper 1290.3400172965737 variance 18.443598235827952 votes 6262 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/vision_style_control/latest) Source Arena Original model label Gemini 3.5 Flash-Lite Observed 2026-10-21T16:40:19.533Z Evidence SHA-256 `38568936995f36625aae49e9ea05557d55c1b1df9b2954f5c50cee523f26fe92` Source locator `/rows/1056/row` |  |  |  |
| 34 | [Claude Sonnet 5.5](https://benchize.com/models/claude-sonnet-5-5-xhigh.md)Extra high | 1,281.73 |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1281.7283790939907 \| rating \| reported \| Higher is better \| ### Configuration category ocr config vision_style_control Reasoning effort xhigh thinkingEnabled true ### Reported statistics lower 1267.2426924497365 rank 39 upper 1296.214065738245 variance 54.62381021114498 votes 1780 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/vision_style_control/latest) Source Arena Original model label Claude Sonnet 5.5 (xHigh) Observed 2026-10-21T16:40:19.533Z Evidence SHA-256 `38568936995f36625aae49e9ea05557d55c1b1df9b2954f5c50cee523f26fe92` Source locator `/rows/1057/row` |  |  |  |
| 35 | [Claude Sonnet 5](https://benchize.com/models/claude-sonnet-5-high.md)High | 1,281.41 |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1281.4064104298222 \| rating \| reported \| Higher is better \| ### Configuration category ocr config vision_style_control Reasoning effort high thinkingEnabled true ### Reported statistics lower 1274.3248916959587 rank 40 upper 1288.4879291636857 variance 13.054391552477439 votes 9827 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/vision_style_control/latest) Source Arena Original model label Claude Sonnet 5 (High) Observed 2026-10-21T16:40:19.533Z Evidence SHA-256 `38568936995f36625aae49e9ea05557d55c1b1df9b2954f5c50cee523f26fe92` Source locator `/rows/1058/row` |  |  |  |
| 36 | [GPT-5.6 Terra](https://benchize.com/models/gpt-5-6-terra-xhigh.md)Extra high | 1,277.65 |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1277.6457295746598 \| rating \| reported \| Higher is better \| ### Configuration category ocr config vision_style_control Reasoning effort xhigh thinkingEnabled true ### Reported statistics lower 1269.9678264661268 rank 43 upper 1285.3236326831925 variance 15.345783697185793 votes 8104 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/vision_style_control/latest) Source Arena Original model label GPT-5.6 Terra (xHigh) Observed 2026-10-21T16:40:19.533Z Evidence SHA-256 `38568936995f36625aae49e9ea05557d55c1b1df9b2954f5c50cee523f26fe92` Source locator `/rows/1061/row` |  |  |  |
| 37 | [Gemma 4 31B](https://benchize.com/models/gemma-4-31b-it.md) | 1,273.46 |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1273.4608943039966 \| rating \| reported \| Higher is better \| ### Configuration category ocr config vision_style_control ### Reported statistics lower 1267.7711311851572 rank 45 upper 1279.150657422836 variance 8.427372479983148 votes 28054 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/vision_style_control/latest) Source Arena Original model label Gemma 4 31B Observed 2026-10-21T16:40:19.533Z Evidence SHA-256 `38568936995f36625aae49e9ea05557d55c1b1df9b2954f5c50cee523f26fe92` Source locator `/rows/1063/row` |  |  |  |
| 38 | [Gemini 3 Flash](https://benchize.com/models/gemini-3-flash-minimal.md)Minimal | 1,272.27 |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1272.2704092737758 \| rating \| reported \| Higher is better \| ### Configuration category ocr config vision_style_control Reasoning effort minimal thinkingEnabled true ### Reported statistics lower 1267.0249288396665 rank 46 upper 1277.5158897078852 variance 7.162660402969473 votes 25665 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/vision_style_control/latest) Source Arena Original model label Gemini 3 Flash (Minimal) Observed 2026-10-21T16:40:19.533Z Evidence SHA-256 `38568936995f36625aae49e9ea05557d55c1b1df9b2954f5c50cee523f26fe92` Source locator `/rows/1064/row` |  |  |  |
| 39 | [DeepSeek V4.1 Flash](https://benchize.com/models/deepseek-v4-1-flash-max.md)Max | 1,271.94 |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1271.9412739686923 \| rating \| reported \| Higher is better \| ### Configuration category ocr config vision_style_control Reasoning effort max thinkingEnabled true ### Reported statistics lower 1260.1367927770436 rank 47 upper 1283.745755160341 variance 36.274181947057244 votes 2786 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/vision_style_control/latest) Source Arena Original model label DeepSeek-V4.1-Flash-20260910 (Max) Observed 2026-10-21T16:40:19.533Z Evidence SHA-256 `38568936995f36625aae49e9ea05557d55c1b1df9b2954f5c50cee523f26fe92` Source locator `/rows/1065/row` |  |  |  |
| 40 | [Step 5 Preview](https://benchize.com/models/step-5-preview.md) | 1,270.14 |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1270.1417129810275 \| rating \| reported \| Higher is better \| ### Configuration category ocr config vision_style_control ### Reported statistics lower 1252.20101753123 rank 50 upper 1288.082408430825 variance 83.78810453165936 votes 1102 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/vision_style_control/latest) Source Arena Original model label Step 5 Preview Observed 2026-10-21T16:40:19.533Z Evidence SHA-256 `38568936995f36625aae49e9ea05557d55c1b1df9b2954f5c50cee523f26fe92` Source locator `/rows/1068/row` |  |  |  |
| 41 | [GPT-5.6 Luna](https://benchize.com/models/gpt-5-6-luna-xhigh.md)Extra high | 1,266.14 |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1266.1413718934548 \| rating \| reported \| Higher is better \| ### Configuration category ocr config vision_style_control Reasoning effort xhigh thinkingEnabled true ### Reported statistics lower 1258.207924766898 rank 52 upper 1274.0748190200115 variance 16.38429207435815 votes 7472 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/vision_style_control/latest) Source Arena Original model label GPT-5.6 Luna (xHigh) Observed 2026-10-21T16:40:19.533Z Evidence SHA-256 `38568936995f36625aae49e9ea05557d55c1b1df9b2954f5c50cee523f26fe92` Source locator `/rows/1070/row` |  |  |  |
| 42 | [GPT-5.1](https://benchize.com/models/gpt-5-1-high.md)High | 1,262.5 |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1262.5029499360521 \| rating \| reported \| Higher is better \| ### Configuration category ocr config vision_style_control Reasoning effort high thinkingEnabled true ### Reported statistics lower 1253.6633026697834 rank 54 upper 1271.342597202321 variance 20.34106505869932 votes 6005 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/vision_style_control/latest) Source Arena Original model label GPT-5.1 (High) Observed 2026-10-21T16:40:19.533Z Evidence SHA-256 `38568936995f36625aae49e9ea05557d55c1b1df9b2954f5c50cee523f26fe92` Source locator `/rows/1072/row` |  |  |  |
| 43 | [GPT-5.4 Mini](https://benchize.com/models/gpt-5-4-mini-high.md)High | 1,262.48 |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1262.479134859703 \| rating \| reported \| Higher is better \| ### Configuration category ocr config vision_style_control Reasoning effort high thinkingEnabled true ### Reported statistics lower 1256.192735098103 rank 55 upper 1268.765534621303 variance 10.287451670640417 votes 18272 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/vision_style_control/latest) Source Arena Original model label GPT-5.4 mini (High) Observed 2026-10-21T16:40:19.533Z Evidence SHA-256 `38568936995f36625aae49e9ea05557d55c1b1df9b2954f5c50cee523f26fe92` Source locator `/rows/1073/row` |  |  |  |
| 44 | [MiMo-V2.6-Flash](https://benchize.com/models/mimo-v2-6-flash.md) | 1,262.44 |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1262.4447529943234 \| rating \| reported \| Higher is better \| ### Configuration category ocr config vision_style_control ### Reported statistics lower 1249.8656815379384 rank 56 upper 1275.0238244507084 variance 41.19087203341304 votes 2504 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/vision_style_control/latest) Source Arena Original model label MiMo-V2.6-Flash Observed 2026-10-21T16:40:19.533Z Evidence SHA-256 `38568936995f36625aae49e9ea05557d55c1b1df9b2954f5c50cee523f26fe92` Source locator `/rows/1074/row` |  |  |  |
| 45 | [Qwen3.8 27B](https://benchize.com/models/qwen3-8-27b.md) | 1,261.53 |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1261.5294384256183 \| rating \| reported \| Higher is better \| ### Configuration category ocr config vision_style_control ### Reported statistics lower 1252.4734486648006 rank 57 upper 1270.585428186436 variance 21.348907895677108 votes 5124 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/vision_style_control/latest) Source Arena Original model label Qwen3.8-27B Observed 2026-10-21T16:40:19.533Z Evidence SHA-256 `38568936995f36625aae49e9ea05557d55c1b1df9b2954f5c50cee523f26fe92` Source locator `/rows/1075/row` |  |  |  |
| 46 | [Qwen3.5 397B A17B](https://benchize.com/models/qwen3-5-397b-a17b.md) | 1,260.16 |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1260.1596381338738 \| rating \| reported \| Higher is better \| ### Configuration category ocr config vision_style_control ### Reported statistics lower 1254.9590939935085 rank 59 upper 1265.360182274239 variance 7.040465775707531 votes 22696 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/vision_style_control/latest) Source Arena Original model label Qwen3.5-397B-A17B Observed 2026-10-21T16:40:19.533Z Evidence SHA-256 `38568936995f36625aae49e9ea05557d55c1b1df9b2954f5c50cee523f26fe92` Source locator `/rows/1077/row` |  |  |  |
| 47 | [GPT-5.2](https://benchize.com/models/gpt-5-2-high.md)High | 1,260.05 |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1260.051886535324 \| rating \| reported \| Higher is better \| ### Configuration category ocr config vision_style_control Reasoning effort high thinkingEnabled true ### Reported statistics lower 1253.6372611193326 rank 60 upper 1266.4665119513154 variance 10.711404481500585 votes 12905 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/vision_style_control/latest) Source Arena Original model label GPT-5.2 (High) Observed 2026-10-21T16:40:19.533Z Evidence SHA-256 `38568936995f36625aae49e9ea05557d55c1b1df9b2954f5c50cee523f26fe92` Source locator `/rows/1078/row` |  |  |  |
| 48 | [Gemini 2.5 Pro](https://benchize.com/models/gemini-2-5-pro.md) | 1,258.98 |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1258.9832441853382 \| rating \| reported \| Higher is better \| ### Configuration category ocr config vision_style_control ### Reported statistics lower 1254.1355945585194 rank 62 upper 1263.830893812157 variance 6.117391335240229 votes 32875 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/vision_style_control/latest) Source Arena Original model label Gemini 2.5 Pro Observed 2026-10-21T16:40:19.533Z Evidence SHA-256 `38568936995f36625aae49e9ea05557d55c1b1df9b2954f5c50cee523f26fe92` Source locator `/rows/1080/row` |  |  |  |
| 49 | [Gemma 4 26B A4B](https://benchize.com/models/gemma-4-26b-a4b-it.md) | 1,257.38 |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1257.3821250251417 \| rating \| reported \| Higher is better \| ### Configuration category ocr config vision_style_control ### Reported statistics lower 1250.8404249523774 rank 63 upper 1263.923825097906 variance 11.139997027033763 votes 16862 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/vision_style_control/latest) Source Arena Original model label Gemma 4 26B A4B Observed 2026-10-21T16:40:19.533Z Evidence SHA-256 `38568936995f36625aae49e9ea05557d55c1b1df9b2954f5c50cee523f26fe92` Source locator `/rows/1081/row` |  |  |  |
| 50 | [MiMo-V2.6-Pro](https://benchize.com/models/mimo-v2-6-pro.md) | 1,254.81 |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1254.8063048982017 \| rating \| reported \| Higher is better \| ### Configuration category ocr config vision_style_control ### Reported statistics lower 1237.4020544558678 rank 64 upper 1272.2105553405358 variance 78.85231824631448 votes 1195 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/vision_style_control/latest) Source Arena Original model label MiMo-V2.6-Pro Observed 2026-10-21T16:40:19.533Z Evidence SHA-256 `38568936995f36625aae49e9ea05557d55c1b1df9b2954f5c50cee523f26fe92` Source locator `/rows/1082/row` |  |  |  |
| 51 | [GPT-5.1](https://benchize.com/models/gpt-5-1.md) | 1,250.96 |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1250.956048728718 \| rating \| reported \| Higher is better \| ### Configuration category ocr config vision_style_control ### Reported statistics lower 1242.4146465396516 rank 66 upper 1259.4974509177844 variance 18.991626556654023 votes 6725 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/vision_style_control/latest) Source Arena Original model label GPT-5.1 Observed 2026-10-21T16:40:19.533Z Evidence SHA-256 `38568936995f36625aae49e9ea05557d55c1b1df9b2954f5c50cee523f26fe92` Source locator `/rows/1084/row` |  |  |  |
| 52 | [GPT-6 Luna](https://benchize.com/models/gpt-6-luna-max.md)Max | 1,250.53 |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1250.5340704045552 \| rating \| reported \| Higher is better \| ### Configuration category ocr config vision_style_control Reasoning effort max thinkingEnabled true ### Reported statistics lower 1238.0390555578422 rank 67 upper 1263.0290852512683 variance 40.64221518620082 votes 2489 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/vision_style_control/latest) Source Arena Original model label GPT-6 Luna (Max) Observed 2026-10-21T16:40:19.533Z Evidence SHA-256 `38568936995f36625aae49e9ea05557d55c1b1df9b2954f5c50cee523f26fe92` Source locator `/rows/1085/row` |  |  |  |
| 53 | [MiMo-V2.5](https://benchize.com/models/mimo-v2-5.md) | 1,247.18 |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1247.1821992044722 \| rating \| reported \| Higher is better \| ### Configuration category ocr config vision_style_control ### Reported statistics lower 1241.4033539425773 rank 68 upper 1252.9610444663672 variance 8.693325666026803 votes 20901 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/vision_style_control/latest) Source Arena Original model label MiMo-V2.5 Observed 2026-10-21T16:40:19.533Z Evidence SHA-256 `38568936995f36625aae49e9ea05557d55c1b1df9b2954f5c50cee523f26fe92` Source locator `/rows/1086/row` |  |  |  |
| 54 | [Gemini 3.1 Flash Lite Preview](https://benchize.com/models/gemini-3-1-flash-lite-preview.md) | 1,246.91 |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1246.9060395450151 \| rating \| reported \| Higher is better \| ### Configuration category ocr config vision_style_control ### Reported statistics lower 1241.0637742898602 rank 69 upper 1252.7483048001698 variance 8.885182662304715 votes 19353 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/vision_style_control/latest) Source Arena Original model label Gemini 3.1 Flash-Lite Preview Observed 2026-10-21T16:40:19.533Z Evidence SHA-256 `38568936995f36625aae49e9ea05557d55c1b1df9b2954f5c50cee523f26fe92` Source locator `/rows/1087/row` |  |  |  |
| 55 | [MiniMax M3](https://benchize.com/models/minimax-m3.md) | 1,246.45 |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1246.4547626186645 \| rating \| reported \| Higher is better \| ### Configuration category ocr config vision_style_control ### Reported statistics lower 1239.9625343532425 rank 71 upper 1252.9469908840865 variance 10.972141006246103 votes 13947 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/vision_style_control/latest) Source Arena Original model label MiniMax-M3 Observed 2026-10-21T16:40:19.533Z Evidence SHA-256 `38568936995f36625aae49e9ea05557d55c1b1df9b2954f5c50cee523f26fe92` Source locator `/rows/1089/row` |  |  |  |
| 56 | [GPT-5 Chat](https://benchize.com/models/gpt-5-chat.md) | 1,245.87 |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1245.8731418931964 \| rating \| reported \| Higher is better \| ### Configuration category ocr config vision_style_control ### Reported statistics lower 1236.8171833032607 rank 72 upper 1254.929100483132 variance 21.348760929269254 votes 10674 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/vision_style_control/latest) Source Arena Original model label GPT-5 Chat Observed 2026-10-21T16:40:19.533Z Evidence SHA-256 `38568936995f36625aae49e9ea05557d55c1b1df9b2954f5c50cee523f26fe92` Source locator `/rows/1090/row` |  |  |  |
| 57 | [Qwen3.5-122B-A10B](https://benchize.com/models/qwen3-5-122b-a10b.md) | 1,239 |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1238.9993375741087 \| rating \| reported \| Higher is better \| ### Configuration category ocr config vision_style_control ### Reported statistics lower 1231.8091290318932 rank 75 upper 1246.1895461163242 variance 13.45819421570872 votes 9185 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/vision_style_control/latest) Source Arena Original model label Qwen3.5-122B-A10B Observed 2026-10-21T16:40:19.533Z Evidence SHA-256 `38568936995f36625aae49e9ea05557d55c1b1df9b2954f5c50cee523f26fe92` Source locator `/rows/1093/row` |  |  |  |
| 58 | [GPT-5.2](https://benchize.com/models/gpt-5-2.md) | 1,237.73 |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1237.7275643462926 \| rating \| reported \| Higher is better \| ### Configuration category ocr config vision_style_control ### Reported statistics lower 1231.4529975690537 rank 77 upper 1244.0021311235316 variance 10.248759671701341 votes 13789 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/vision_style_control/latest) Source Arena Original model label GPT-5.2 Observed 2026-10-21T16:40:19.533Z Evidence SHA-256 `38568936995f36625aae49e9ea05557d55c1b1df9b2954f5c50cee523f26fe92` Source locator `/rows/1095/row` |  |  |  |
| 59 | [GPT-5](https://benchize.com/models/gpt-5-high.md)High | 1,231.74 |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1231.7375127253424 \| rating \| reported \| Higher is better \| ### Configuration category ocr config vision_style_control Reasoning effort high thinkingEnabled true ### Reported statistics lower 1222.8542922526237 rank 78 upper 1240.6207331980609 variance 20.542093420818485 votes 10702 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/vision_style_control/latest) Source Arena Original model label GPT-5 (High) Observed 2026-10-21T16:40:19.533Z Evidence SHA-256 `38568936995f36625aae49e9ea05557d55c1b1df9b2954f5c50cee523f26fe92` Source locator `/rows/1096/row` |  |  |  |
| 60 | [MiMo-V2-Omni](https://benchize.com/models/mimo-v2-omni.md) | 1,230.41 |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1230.413094040424 \| rating \| reported \| Higher is better \| ### Configuration category ocr config vision_style_control ### Reported statistics lower 1222.4696472797143 rank 79 upper 1238.3565408011339 variance 16.42562093866977 votes 7549 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/vision_style_control/latest) Source Arena Original model label MiMo-V2-Omni Observed 2026-10-21T16:40:19.533Z Evidence SHA-256 `38568936995f36625aae49e9ea05557d55c1b1df9b2954f5c50cee523f26fe92` Source locator `/rows/1097/row` |  |  |  |
| 61 | [Qwen3.5-27B](https://benchize.com/models/qwen3-5-27b.md) | 1,228.62 |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1228.624877740905 \| rating \| reported \| Higher is better \| ### Configuration category ocr config vision_style_control ### Reported statistics lower 1223.2101844415317 rank 81 upper 1234.0395710402781 variance 7.632231632507758 votes 21340 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/vision_style_control/latest) Source Arena Original model label Qwen3.5-27B Observed 2026-10-21T16:40:19.533Z Evidence SHA-256 `38568936995f36625aae49e9ea05557d55c1b1df9b2954f5c50cee523f26fe92` Source locator `/rows/1099/row` |  |  |  |
| 62 | [Qwen3 VL 235B A22B Instruct](https://benchize.com/models/qwen3-vl-235b-a22b-instruct.md) | 1,228.05 |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1228.048674409815 \| rating \| reported \| Higher is better \| ### Configuration category ocr config vision_style_control ### Reported statistics lower 1220.135371330758 rank 82 upper 1235.9619774888722 variance 16.30119403693067 votes 7752 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/vision_style_control/latest) Source Arena Original model label Qwen3-VL-235B-A22B-Instruct Observed 2026-10-21T16:40:19.533Z Evidence SHA-256 `38568936995f36625aae49e9ea05557d55c1b1df9b2954f5c50cee523f26fe92` Source locator `/rows/1100/row` |  |  |  |
| 63 | [Gemini 2.5 Flash](https://benchize.com/models/gemini-2-5-flash.md) | 1,222.73 |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1222.7272850833622 \| rating \| reported \| Higher is better \| ### Configuration category ocr config vision_style_control ### Reported statistics lower 1217.7374913065319 rank 86 upper 1227.7170788601923 variance 6.481402794471134 votes 27156 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/vision_style_control/latest) Source Arena Original model label Gemini 2.5 Flash Observed 2026-10-21T16:40:19.533Z Evidence SHA-256 `38568936995f36625aae49e9ea05557d55c1b1df9b2954f5c50cee523f26fe92` Source locator `/rows/1104/row` |  |  |  |
| 64 | [Mistral Medium 3.5](https://benchize.com/models/mistral-medium-3-5.md) | 1,214.85 |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1214.8542983767566 \| rating \| reported \| Higher is better \| ### Configuration category ocr config vision_style_control ### Reported statistics lower 1204.3090830928863 rank 90 upper 1225.399513660627 variance 28.94774370198195 votes 3905 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/vision_style_control/latest) Source Arena Original model label Mistral Medium 3.5 Observed 2026-10-21T16:40:19.533Z Evidence SHA-256 `38568936995f36625aae49e9ea05557d55c1b1df9b2954f5c50cee523f26fe92` Source locator `/rows/1108/row` |  |  |  |
| 65 | [Mistral Large 3](https://benchize.com/models/mistral-large-3.md) | 1,214.04 |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1214.0414416071 \| rating \| reported \| Higher is better \| ### Configuration category ocr config vision_style_control ### Reported statistics lower 1205.5721996731427 rank 91 upper 1222.5106835410575 variance 18.67208846532506 votes 6194 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/vision_style_control/latest) Source Arena Original model label Mistral Large 3 Observed 2026-10-21T16:40:19.533Z Evidence SHA-256 `38568936995f36625aae49e9ea05557d55c1b1df9b2954f5c50cee523f26fe92` Source locator `/rows/1109/row` |  |  |  |
| 66 | [GPT-5.4 Nano](https://benchize.com/models/gpt-5-4-nano-high.md)High | 1,212.65 |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1212.6459343427243 \| rating \| reported \| Higher is better \| ### Configuration category ocr config vision_style_control Reasoning effort high thinkingEnabled true ### Reported statistics lower 1206.2460579654144 rank 93 upper 1219.0458107200343 variance 10.662204010675953 votes 18222 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/vision_style_control/latest) Source Arena Original model label GPT-5.4 nano (High) Observed 2026-10-21T16:40:19.533Z Evidence SHA-256 `38568936995f36625aae49e9ea05557d55c1b1df9b2954f5c50cee523f26fe92` Source locator `/rows/1111/row` |  |  |  |
| 67 | [Qwen3 VL 235B A22B Thinking](https://benchize.com/models/qwen3-vl-235b-a22b-thinking.md) | 1,200.31 |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1200.314723348562 \| rating \| reported \| Higher is better \| ### Configuration category ocr config vision_style_control ### Reported statistics lower 1184.241950721409 rank 97 upper 1216.3874959757152 variance 67.24893640210425 votes 1322 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/vision_style_control/latest) Source Arena Original model label Qwen3-VL-235B-A22B-Thinking Observed 2026-10-21T16:40:19.533Z Evidence SHA-256 `38568936995f36625aae49e9ea05557d55c1b1df9b2954f5c50cee523f26fe92` Source locator `/rows/1115/row` |  |  |  |
| 68 | [GPT-5 Mini](https://benchize.com/models/gpt-5-mini-high.md)High | 1,198.95 |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1198.954279203454 \| rating \| reported \| Higher is better \| ### Configuration category ocr config vision_style_control Reasoning effort high thinkingEnabled true ### Reported statistics lower 1188.4052942133942 rank 98 upper 1209.5032641935136 variance 28.968443894550827 votes 7999 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/vision_style_control/latest) Source Arena Original model label GPT-5 mini (High) Observed 2026-10-21T16:40:19.533Z Evidence SHA-256 `38568936995f36625aae49e9ea05557d55c1b1df9b2954f5c50cee523f26fe92` Source locator `/rows/1116/row` |  |  |  |
| 69 | [Gemini 2.0 Flash 001](https://benchize.com/models/gemini-2-0-flash-001.md) | 1,166.86 |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1166.864714344602 \| rating \| reported \| Higher is better \| ### Configuration category ocr config vision_style_control ### Reported statistics lower 1155.300868689312 rank 109 upper 1178.4285599998916 variance 34.81035007299731 votes 3690 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/vision_style_control/latest) Source Arena Original model label Gemini 2.0 Flash (001) Observed 2026-10-21T16:40:19.533Z Evidence SHA-256 `38568936995f36625aae49e9ea05557d55c1b1df9b2954f5c50cee523f26fe92` Source locator `/rows/1127/row` |  |  |  |
| 70 | [Gemma 3 27B](https://benchize.com/models/gemma-3-27b-it.md) | 1,161.32 |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1161.3212992438362 \| rating \| reported \| Higher is better \| ### Configuration category ocr config vision_style_control ### Reported statistics lower 1151.2741769638428 rank 110 upper 1171.3684215238295 variance 26.277690539163064 votes 6196 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/vision_style_control/latest) Source Arena Original model label Gemma 3 27B IT Observed 2026-10-21T16:40:19.533Z Evidence SHA-256 `38568936995f36625aae49e9ea05557d55c1b1df9b2954f5c50cee523f26fe92` Source locator `/rows/1128/row` |  |  |  |
| 71 | [GPT-5 Nano](https://benchize.com/models/gpt-5-nano-high.md)High | 1,158.48 |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1158.484257841533 \| rating \| reported \| Higher is better \| ### Configuration category ocr config vision_style_control Reasoning effort high thinkingEnabled true ### Reported statistics lower 1143.1573197989699 rank 113 upper 1173.8111958840962 variance 61.15255706896287 votes 1673 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/vision_style_control/latest) Source Arena Original model label GPT-5 nano (High) Observed 2026-10-21T16:40:19.533Z Evidence SHA-256 `38568936995f36625aae49e9ea05557d55c1b1df9b2954f5c50cee523f26fe92` Source locator `/rows/1131/row` |  |  |  |
| 72 | [Llama 4 Maverick](https://benchize.com/models/llama-4-maverick.md) | 1,153.13 |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1153.1256553740561 \| rating \| reported \| Higher is better \| ### Configuration category ocr config vision_style_control ### Reported statistics lower 1141.3304137383604 rank 115 upper 1164.9208970097518 variance 36.217419407169245 votes 3083 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/vision_style_control/latest) Source Arena Original model label Llama 4 Maverick 17B 128E Instruct Observed 2026-10-21T16:40:19.533Z Evidence SHA-256 `38568936995f36625aae49e9ea05557d55c1b1df9b2954f5c50cee523f26fe92` Source locator `/rows/1133/row` |  |  |  |
| 73 | [Mistral Small 3.1 24B](https://benchize.com/models/mistral-small-3-1-24b-instruct.md) | 1,133.52 |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1133.5180876688964 \| rating \| reported \| Higher is better \| ### Configuration category ocr config vision_style_control ### Reported statistics lower 1122.9717764293396 rank 120 upper 1144.0643989084533 variance 28.953761045786077 votes 7209 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/vision_style_control/latest) Source Arena Original model label Mistral Small 3.1 24B Instruct (2503) Observed 2026-10-21T16:40:19.533Z Evidence SHA-256 `38568936995f36625aae49e9ea05557d55c1b1df9b2954f5c50cee523f26fe92` Source locator `/rows/1138/row` |  |  |  |
| 74 | [Llama 4 Scout](https://benchize.com/models/llama-4-scout.md) | 1,131.09 |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1131.089545879527 \| rating \| reported \| Higher is better \| ### Configuration category ocr config vision_style_control ### Reported statistics lower 1118.600877205361 rank 122 upper 1143.5782145536925 variance 40.600941603978384 votes 2788 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/vision_style_control/latest) Source Arena Original model label Llama 4 Scout 17B 16E Instruct Observed 2026-10-21T16:40:19.533Z Evidence SHA-256 `38568936995f36625aae49e9ea05557d55c1b1df9b2954f5c50cee523f26fe92` Source locator `/rows/1140/row` |  |  |  |

---
Cite as: Arena vision style control / ocr — Benchize, https://benchize.com/benchmarks/lmarena%3Avision_style_control%3Aocr (retrieved 2026-10-21)