# Arena vision style control / entity recognition > Source: Benchize (https://benchize.com) — https://benchize.com/benchmarks/lmarena%3Avision_style_control%3Aentity_recognition. When citing or reusing this content, credit "Benchize" and link to https://benchize.com/benchmarks/lmarena%3Avision_style_control%3Aentity_recognition. Human pairwise preferences on entity recognition 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%3Aentity_recognition 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 entity recognition 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: 34 · Score publishers: [Arena](https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset) ## Model results | # | Model | Score | | | --- | --- | --- | --- | | 1 | [Gemini 3 Pro](https://benchize.com/models/gemini-3-pro.md) | 1,291.66 | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1291.657001068069 \| rating \| reported \| Higher is better \| ### Configuration category entity_recognition config vision_style_control ### Reported statistics lower 1255.5015530137384 rank 1 upper 1327.8124491223996 variance 340.2916665323492 votes 249 ### 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/757/row` | | | | | 2 | [Gemini 3 Flash](https://benchize.com/models/gemini-3-flash.md) | 1,290.01 | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1290.0107442149324 \| rating \| reported \| Higher is better \| ### Configuration category entity_recognition config vision_style_control ### Reported statistics lower 1260.4237267882947 rank 2 upper 1319.59776164157 variance 227.8799906661449 votes 368 ### 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/758/row` | | | | | 3 | [Gemini 3.1 Pro Preview](https://benchize.com/models/gemini-3-1-pro-preview.md) | 1,283.98 | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1283.9787158045426 \| rating \| reported \| Higher is better \| ### Configuration category entity_recognition config vision_style_control ### Reported statistics lower 1254.8697178950629 rank 3 upper 1313.0877137140226 variance 220.57603604377425 votes 388 ### 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/759/row` | | | | | 4 | [Gemini 3 Flash](https://benchize.com/models/gemini-3-flash-minimal.md)Minimal | 1,273.94 | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1273.939702589047 \| rating \| reported \| Higher is better \| ### Configuration category entity_recognition config vision_style_control Reasoning effort minimal thinkingEnabled true ### Reported statistics lower 1243.6366676277066 rank 4 upper 1304.2427375503878 variance 239.04302264583532 votes 323 ### 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/760/row` | | | | | 5 | [Gemini 3.1 Flash Lite Preview](https://benchize.com/models/gemini-3-1-flash-lite-preview.md) | 1,271.11 | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1271.1110591255751 \| rating \| reported \| Higher is better \| ### Configuration category entity_recognition config vision_style_control ### Reported statistics lower 1237.5178318157036 rank 5 upper 1304.7042864354464 variance 293.7698863289591 votes 259 ### 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/761/row` | | | | | 6 | [GPT-5](https://benchize.com/models/gpt-5-high.md)High | 1,261.48 | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1261.4764662180164 \| rating \| reported \| Higher is better \| ### Configuration category entity_recognition config vision_style_control Reasoning effort high thinkingEnabled true ### Reported statistics lower 1228.34654720239 rank 6 upper 1294.606385233643 variance 285.7225822828547 votes 432 ### 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/762/row` | | | | | 7 | [Gemini 2.5 Pro](https://benchize.com/models/gemini-2-5-pro.md) | 1,250.81 | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1250.8092307286204 \| rating \| reported \| Higher is better \| ### Configuration category entity_recognition config vision_style_control ### Reported statistics lower 1228.6515633184058 rank 7 upper 1272.966898138835 variance 127.80619238109334 votes 917 ### 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/763/row` | | | | | 8 | [Claude Opus 4.7](https://benchize.com/models/claude-opus-4-7-high.md)High | 1,242.39 | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1242.389374555394 \| rating \| reported \| Higher is better \| ### Configuration category entity_recognition config vision_style_control Reasoning effort high thinkingEnabled true ### Reported statistics lower 1202.0956586906664 rank 8 upper 1282.6830904201215 variance 422.6476487112341 votes 154 ### 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/764/row` | | | | | 9 | [Claude Opus 4.6](https://benchize.com/models/claude-opus-4-6.md) | 1,236.57 | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1236.5650908197508 \| rating \| reported \| Higher is better \| ### Configuration category entity_recognition config vision_style_control ### Reported statistics lower 1197.28488241031 rank 11 upper 1275.8452992291916 variance 401.65334179224857 votes 189 ### 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/767/row` | | | | | 10 | [Claude Opus 4.6](https://benchize.com/models/claude-opus-4-6-high.md)High | 1,235.85 | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1235.8476377838215 \| rating \| reported \| Higher is better \| ### Configuration category entity_recognition config vision_style_control Reasoning effort high thinkingEnabled true ### Reported statistics lower 1188.8163354056292 rank 13 upper 1282.8789401620138 variance 575.8081777352685 votes 125 ### 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/769/row` | | | | | 11 | [GPT-5.1](https://benchize.com/models/gpt-5-1-high.md)High | 1,228.23 | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1228.225582986197 \| rating \| reported \| Higher is better \| ### Configuration category entity_recognition config vision_style_control Reasoning effort high thinkingEnabled true ### Reported statistics lower 1178.832000522109 rank 16 upper 1277.619165450285 variance 635.1040327423926 votes 112 ### 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/772/row` | | | | | 12 | [Gemini 2.5 Flash](https://benchize.com/models/gemini-2-5-flash.md) | 1,221.31 | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1221.314650650093 \| rating \| reported \| Higher is better \| ### Configuration category entity_recognition config vision_style_control ### Reported statistics lower 1197.2864716156332 rank 18 upper 1245.3428296845527 variance 150.29534733050338 votes 628 ### 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/774/row` | | | | | 13 | [GPT-5.5](https://benchize.com/models/gpt-5-5-high.md)High | 1,219.18 | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1219.1785976743606 \| rating \| reported \| Higher is better \| ### Configuration category entity_recognition config vision_style_control Reasoning effort high thinkingEnabled true ### Reported statistics lower 1171.3160825819264 rank 19 upper 1267.0411127667949 variance 596.3412489632132 votes 130 ### 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/775/row` | | | | | 14 | [GPT-5.5](https://benchize.com/models/gpt-5-5.md) | 1,218.58 | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1218.5756795809857 \| rating \| reported \| Higher is better \| ### Configuration category entity_recognition config vision_style_control ### Reported statistics lower 1166.2686784054922 rank 20 upper 1270.8826807564794 variance 712.2352469936707 votes 119 ### 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/776/row` | | | | | 15 | [GPT-5.4](https://benchize.com/models/gpt-5-4.md) | 1,215.38 | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1215.3759835843214 \| rating \| reported \| Higher is better \| ### Configuration category entity_recognition config vision_style_control ### Reported statistics lower 1169.1099259378382 rank 24 upper 1261.6420412308046 variance 557.2227088876925 votes 137 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/vision_style_control/latest) Source Arena Original model label GPT-5.4 Observed 2026-10-21T16:40:19.533Z Evidence SHA-256 `38568936995f36625aae49e9ea05557d55c1b1df9b2954f5c50cee523f26fe92` Source locator `/rows/780/row` | | | | | 16 | [Qwen3.5 397B A17B](https://benchize.com/models/qwen3-5-397b-a17b.md) | 1,211.34 | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1211.3362879420488 \| rating \| reported \| Higher is better \| ### Configuration category entity_recognition config vision_style_control ### Reported statistics lower 1174.2252263290811 rank 25 upper 1248.4473495550164 variance 358.51767735274655 votes 222 ### 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/781/row` | | | | | 17 | [GPT-5 Mini](https://benchize.com/models/gpt-5-mini-high.md)High | 1,211.19 | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1211.1918062129212 \| rating \| reported \| Higher is better \| ### Configuration category entity_recognition config vision_style_control Reasoning effort high thinkingEnabled true ### Reported statistics lower 1171.0380927933693 rank 26 upper 1251.3455196324733 variance 419.71573213120683 votes 282 ### 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/782/row` | | | | | 18 | [GPT-5.2](https://benchize.com/models/gpt-5-2-high.md)High | 1,201.3 | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1201.2995680449712 \| rating \| reported \| Higher is better \| ### Configuration category entity_recognition config vision_style_control Reasoning effort high thinkingEnabled true ### Reported statistics lower 1159.3912331755416 rank 28 upper 1243.2079029144008 variance 457.19832321693224 votes 168 ### 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/784/row` | | | | | 19 | [GPT-5.4 Mini](https://benchize.com/models/gpt-5-4-mini-high.md)High | 1,198.14 | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1198.144903606163 \| rating \| reported \| Higher is better \| ### Configuration category entity_recognition config vision_style_control Reasoning effort high thinkingEnabled true ### Reported statistics lower 1157.296815242478 rank 29 upper 1238.9929919698482 variance 434.35746700674696 votes 183 ### 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/785/row` | | | | | 20 | [Gemma 4 31B](https://benchize.com/models/gemma-4-31b-it.md) | 1,196.2 | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1196.195703305626 \| rating \| reported \| Higher is better \| ### Configuration category entity_recognition config vision_style_control ### Reported statistics lower 1167.4172572533498 rank 31 upper 1224.9741493579022 variance 215.59490699788998 votes 359 ### 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/787/row` | | | | | 21 | [GPT-5.4](https://benchize.com/models/gpt-5-4-high.md)High | 1,196.17 | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1196.168334874129 \| rating \| reported \| Higher is better \| ### Configuration category entity_recognition config vision_style_control Reasoning effort high thinkingEnabled true ### Reported statistics lower 1150.4129963976225 rank 32 upper 1241.9236733506357 variance 544.9885308731209 votes 159 ### 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/788/row` | | | | | 22 | [GPT-5 Chat](https://benchize.com/models/gpt-5-chat.md) | 1,190.37 | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1190.3672932593358 \| rating \| reported \| Higher is better \| ### Configuration category entity_recognition config vision_style_control ### Reported statistics lower 1157.4782384737796 rank 33 upper 1223.256348044892 variance 281.58311078598643 votes 377 ### 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/789/row` | | | | | 23 | [GPT-5.1](https://benchize.com/models/gpt-5-1.md) | 1,186.9 | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1186.9041097122858 \| rating \| reported \| Higher is better \| ### Configuration category entity_recognition config vision_style_control ### Reported statistics lower 1143.6524746333064 rank 34 upper 1230.1557447912653 variance 486.97748025506127 votes 143 ### 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/790/row` | | | | | 24 | [Claude Opus 4.7](https://benchize.com/models/claude-opus-4-7.md) | 1,183.95 | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1183.9538515746535 \| rating \| reported \| Higher is better \| ### Configuration category entity_recognition config vision_style_control ### Reported statistics lower 1140.223135097625 rank 36 upper 1227.6845680516822 variance 497.8253452288008 votes 154 ### 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/792/row` | | | | | 25 | [Qwen3 VL 235B A22B Instruct](https://benchize.com/models/qwen3-vl-235b-a22b-instruct.md) | 1,181.47 | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1181.4716542348124 \| rating \| reported \| Higher is better \| ### Configuration category entity_recognition config vision_style_control ### Reported statistics lower 1138.3980312100416 rank 38 upper 1224.5452772595831 variance 482.9771935821046 votes 151 ### 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/794/row` | | | | | 26 | [GPT-5.2](https://benchize.com/models/gpt-5-2.md) | 1,174.56 | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1174.5586755378154 \| rating \| reported \| Higher is better \| ### Configuration category entity_recognition config vision_style_control ### Reported statistics lower 1133.5443620498893 rank 40 upper 1215.5729890257417 variance 437.8997639708982 votes 176 ### 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/796/row` | | | | | 27 | [Gemma 3 27B](https://benchize.com/models/gemma-3-27b-it.md) | 1,169.96 | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1169.9597789527795 \| rating \| reported \| Higher is better \| ### Configuration category entity_recognition config vision_style_control ### Reported statistics lower 1135.4337915342062 rank 41 upper 1204.4857663713528 variance 310.31018757923107 votes 313 ### 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/797/row` | | | | | 28 | [Claude Sonnet 4.6](https://benchize.com/models/claude-sonnet-4-6.md) | 1,166.6 | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1166.5967766509116 \| rating \| reported \| Higher is better \| ### Configuration category entity_recognition config vision_style_control ### Reported statistics lower 1121.1070253214011 rank 42 upper 1212.086527980422 variance 538.6801141465297 votes 162 ### 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/798/row` | | | | | 29 | [MiMo-V2.5](https://benchize.com/models/mimo-v2-5.md) | 1,162.53 | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1162.5256577150467 \| rating \| reported \| Higher is better \| ### Configuration category entity_recognition config vision_style_control ### Reported statistics lower 1121.8797401705235 rank 43 upper 1203.1715752595696 variance 430.0685469114686 votes 185 ### 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/799/row` | | | | | 30 | [MiniMax M3](https://benchize.com/models/minimax-m3.md) | 1,160.85 | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1160.847477319432 \| rating \| reported \| Higher is better \| ### Configuration category entity_recognition config vision_style_control ### Reported statistics lower 1107.2556895471457 rank 44 upper 1214.4392650917184 variance 747.653391768185 votes 107 ### 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/800/row` | | | | | 31 | [Gemma 4 26B A4B](https://benchize.com/models/gemma-4-26b-a4b-it.md) | 1,157.68 | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1157.6845032533433 \| rating \| reported \| Higher is better \| ### Configuration category entity_recognition config vision_style_control ### Reported statistics lower 1121.7369520951177 rank 45 upper 1193.6320544115692 variance 336.38950580752817 votes 235 ### 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/801/row` | | | | | 32 | [Qwen3.5-27B](https://benchize.com/models/qwen3-5-27b.md) | 1,149.23 | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1149.2256804306155 \| rating \| reported \| Higher is better \| ### Configuration category entity_recognition config vision_style_control ### Reported statistics lower 1108.0412182045643 rank 46 upper 1190.4101426566667 variance 441.540573001005 votes 187 ### 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/802/row` | | | | | 33 | [Mistral Small 3.1 24B](https://benchize.com/models/mistral-small-3-1-24b-instruct.md) | 1,130.53 | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1130.5294537872824 \| rating \| reported \| Higher is better \| ### Configuration category entity_recognition config vision_style_control ### Reported statistics lower 1089.7445072725654 rank 48 upper 1171.3144003019993 variance 433.01566926799916 votes 240 ### 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/804/row` | | | | | 34 | [GPT-5.4 Nano](https://benchize.com/models/gpt-5-4-nano-high.md)High | 1,116.1 | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1116.10391791962 \| rating \| reported \| Higher is better \| ### Configuration category entity_recognition config vision_style_control Reasoning effort high thinkingEnabled true ### Reported statistics lower 1073.8961037774652 rank 51 upper 1158.311732061775 variance 463.75599942961065 votes 178 ### 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/807/row` | | | | --- Cite as: Arena vision style control / entity recognition — Benchize, https://benchize.com/benchmarks/lmarena%3Avision_style_control%3Aentity_recognition (retrieved 2026-10-21)