# Arena vision / chinese (config: vision) > Source: Benchize (https://benchize.com) — https://benchize.com/benchmarks/benchmark%3Avision%3Achinese--config-vision. When citing or reusing this content, credit "Benchize" and link to https://benchize.com/benchmarks/benchmark%3Avision%3Achinese--config-vision. Human pairwise preferences on chinese prompts in Arena’s vision evaluation. The original organizer publishes model ratings and uncertainty; these are preference ratings rather than task accuracy. Canonical URL: https://benchize.com/benchmarks/benchmark%3Avision%3Achinese--config-vision Last updated: Wed, 21 Oct 2026 18:52:20 GMT Reproduction and quotation must name Benchize, link to the canonical HTML URL, and retain individual source citations. Human pairwise preferences on chinese prompts in Arena’s vision evaluation. The original organizer publishes model ratings and uncertainty; 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 | [Gemini 3.8 Flash](https://benchize.com/models/gemini-3-8-flash-high.md)High | 1,416.08 | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1416.0843379029016 \| rating \| reported \| Higher is better \| ### Configuration category chinese config vision Reasoning effort high thinkingEnabled true ### Reported statistics lower 1376.7727774160692 rank 1 upper 1455.395898389734 variance 402.2947687437774 votes 224 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/vision/latest) Source Arena Original model label Gemini 3.8 Flash (High) Observed 2026-10-21T18:45:05.190Z Evidence SHA-256 `06e61305486dce3fec5dc776ac2fd8321104e84c346cf9e08fa6f8e8a66ce0d7` Source locator `/rows/201/row` | | | | | 2 | [Claude Opus 5](https://benchize.com/models/claude-opus-5-high.md)High | 1,400.39 | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1400.387166976013 \| rating \| reported \| Higher is better \| ### Configuration category chinese config vision Reasoning effort high thinkingEnabled true ### Reported statistics lower 1380.1483376905433 rank 2 upper 1420.6259962614831 variance 106.62881732320155 votes 1037 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/vision/latest) Source Arena Original model label Claude Opus 5 (High) Observed 2026-10-21T18:45:05.190Z Evidence SHA-256 `06e61305486dce3fec5dc776ac2fd8321104e84c346cf9e08fa6f8e8a66ce0d7` Source locator `/rows/202/row` | | | | | 3 | [Gemini 3.7 Flash](https://benchize.com/models/gemini-3-7-flash-high.md)High | 1,394.11 | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1394.1059568384335 \| rating \| reported \| Higher is better \| ### Configuration category chinese config vision Reasoning effort high thinkingEnabled true ### Reported statistics lower 1360.0046419693256 rank 3 upper 1428.2072717075412 variance 302.72345223055095 votes 302 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/vision/latest) Source Arena Original model label Gemini 3.7 Flash (High) Observed 2026-10-21T18:45:05.190Z Evidence SHA-256 `06e61305486dce3fec5dc776ac2fd8321104e84c346cf9e08fa6f8e8a66ce0d7` Source locator `/rows/203/row` | | | | | 4 | [Claude Fable 5.1](https://benchize.com/models/claude-fable-5-1-max.md)Max | 1,391.14 | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1391.1367829374449 \| rating \| reported \| Higher is better \| ### Configuration category chinese config vision Reasoning effort max thinkingEnabled true ### Reported statistics lower 1356.4097412202386 rank 4 upper 1425.8638246546514 variance 313.93475310264506 votes 284 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/vision/latest) Source Arena Original model label Claude Fable 5.1 (Max) Observed 2026-10-21T18:45:05.190Z Evidence SHA-256 `06e61305486dce3fec5dc776ac2fd8321104e84c346cf9e08fa6f8e8a66ce0d7` Source locator `/rows/204/row` | | | | | 5 | [Muse Spark 1.3](https://benchize.com/models/muse-spark-1-3-xhigh.md)Extra high | 1,384.43 | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1384.4279856726387 \| rating \| reported \| Higher is better \| ### Configuration category chinese config vision Reasoning effort xhigh thinkingEnabled true ### Reported statistics lower 1348.2121446559775 rank 5 upper 1420.6438266893 variance 341.4294417210743 votes 257 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/vision/latest) Source Arena Original model label Muse Spark 1.3 (xHigh) Observed 2026-10-21T18:45:05.190Z Evidence SHA-256 `06e61305486dce3fec5dc776ac2fd8321104e84c346cf9e08fa6f8e8a66ce0d7` Source locator `/rows/205/row` | | | | | 6 | [Gemini 3.5 Flash](https://benchize.com/models/gemini-3-5-flash-high.md)High | 1,377.07 | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1377.065533142831 \| rating \| reported \| Higher is better \| ### Configuration category chinese config vision Reasoning effort high thinkingEnabled true ### Reported statistics lower 1354.8201684976225 rank 6 upper 1399.3108977880397 variance 128.81987580668113 votes 847 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/vision/latest) Source Arena Original model label Gemini 3.5 Flash (High) Observed 2026-10-21T18:45:05.190Z Evidence SHA-256 `06e61305486dce3fec5dc776ac2fd8321104e84c346cf9e08fa6f8e8a66ce0d7` Source locator `/rows/206/row` | | | | | 7 | [Gemini 3.5 Flash](https://benchize.com/models/gemini-3-5-flash-medium.md)Medium | 1,374.66 | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1374.658434948607 \| rating \| reported \| Higher is better \| ### Configuration category chinese config vision Reasoning effort medium thinkingEnabled true ### Reported statistics lower 1352.7479588474434 rank 7 upper 1396.5689110497706 variance 124.97048267015215 votes 818 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/vision/latest) Source Arena Original model label Gemini 3.5 Flash (Medium) Observed 2026-10-21T18:45:05.190Z Evidence SHA-256 `06e61305486dce3fec5dc776ac2fd8321104e84c346cf9e08fa6f8e8a66ce0d7` Source locator `/rows/207/row` | | | | | 8 | [Claude Fable 5](https://benchize.com/models/claude-fable-5-high.md)High | 1,372.77 | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1372.7727144688824 \| rating \| reported \| Higher is better \| ### Configuration category chinese config vision Reasoning effort high thinkingEnabled true ### Reported statistics lower 1350.0624001983253 rank 8 upper 1395.4830287394395 variance 134.2610706872746 votes 784 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/vision/latest) Source Arena Original model label Claude Fable 5 (High) Observed 2026-10-21T18:45:05.190Z Evidence SHA-256 `06e61305486dce3fec5dc776ac2fd8321104e84c346cf9e08fa6f8e8a66ce0d7` Source locator `/rows/208/row` | | | | | 9 | [Claude Opus 4.7](https://benchize.com/models/claude-opus-4-7.md) | 1,371.04 | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1371.041080621802 \| rating \| reported \| Higher is better \| ### Configuration category chinese config vision ### Reported statistics lower 1353.4668854547704 rank 9 upper 1388.6152757888333 variance 80.39975180915819 votes 1504 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/vision/latest) Source Arena Original model label Claude Opus 4.7 Observed 2026-10-21T18:45:05.190Z Evidence SHA-256 `06e61305486dce3fec5dc776ac2fd8321104e84c346cf9e08fa6f8e8a66ce0d7` Source locator `/rows/209/row` | | | | | 10 | [Gemini 3 Pro](https://benchize.com/models/gemini-3-pro.md) | 1,370.42 | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1370.417305292307 \| rating \| reported \| Higher is better \| ### Configuration category chinese config vision ### Reported statistics lower 1353.6176228993666 rank 10 upper 1387.2169876852472 variance 73.46930988386154 votes 1687 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/vision/latest) Source Arena Original model label Gemini 3 Pro Observed 2026-10-21T18:45:05.190Z Evidence SHA-256 `06e61305486dce3fec5dc776ac2fd8321104e84c346cf9e08fa6f8e8a66ce0d7` Source locator `/rows/210/row` | | | | | 11 | [Claude Opus 4.6](https://benchize.com/models/claude-opus-4-6.md) | 1,370.32 | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1370.3195668722983 \| rating \| reported \| Higher is better \| ### Configuration category chinese config vision ### Reported statistics lower 1353.1898760375675 rank 11 upper 1387.4492577070291 variance 76.38408265962886 votes 1681 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/vision/latest) Source Arena Original model label Claude Opus 4.6 Observed 2026-10-21T18:45:05.190Z Evidence SHA-256 `06e61305486dce3fec5dc776ac2fd8321104e84c346cf9e08fa6f8e8a66ce0d7` Source locator `/rows/211/row` | | | | | 12 | [Muse Spark 1.3](https://benchize.com/models/muse-spark-1-3-max.md)Max | 1,367.78 | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1367.7795402913257 \| rating \| reported \| Higher is better \| ### Configuration category chinese config vision Reasoning effort max thinkingEnabled true ### Reported statistics lower 1333.369252727528 rank 12 upper 1402.1898278551234 variance 308.23391463800715 votes 290 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/vision/latest) Source Arena Original model label Muse Spark 1.3 (Max) Observed 2026-10-21T18:45:05.190Z Evidence SHA-256 `06e61305486dce3fec5dc776ac2fd8321104e84c346cf9e08fa6f8e8a66ce0d7` Source locator `/rows/212/row` | | | | | 13 | [Claude Opus 4.6](https://benchize.com/models/claude-opus-4-6-high.md)High | 1,367.21 | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1367.2109369529164 \| rating \| reported \| Higher is better \| ### Configuration category chinese config vision Reasoning effort high thinkingEnabled true ### Reported statistics lower 1349.4740910296634 rank 13 upper 1384.9477828761692 variance 81.89485244784372 votes 1487 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/vision/latest) Source Arena Original model label Claude Opus 4.6 (High) Observed 2026-10-21T18:45:05.190Z Evidence SHA-256 `06e61305486dce3fec5dc776ac2fd8321104e84c346cf9e08fa6f8e8a66ce0d7` Source locator `/rows/213/row` | | | | | 14 | [Gemini 3.1 Pro Preview](https://benchize.com/models/gemini-3-1-pro-preview.md) | 1,363.82 | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1363.8153952917796 \| rating \| reported \| Higher is better \| ### Configuration category chinese config vision ### Reported statistics lower 1350.5404858486095 rank 14 upper 1377.09030473495 variance 45.874036127902464 votes 3186 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/vision/latest) Source Arena Original model label Gemini 3.1 Pro Preview Observed 2026-10-21T18:45:05.190Z Evidence SHA-256 `06e61305486dce3fec5dc776ac2fd8321104e84c346cf9e08fa6f8e8a66ce0d7` Source locator `/rows/214/row` | | | | | 15 | [GPT-6 Astra](https://benchize.com/models/gpt-6-astra-max.md)Max | 1,361.16 | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1361.1607425257414 \| rating \| reported \| Higher is better \| ### Configuration category chinese config vision Reasoning effort max thinkingEnabled true ### Reported statistics lower 1324.1090101460086 rank 16 upper 1398.212474905474 variance 357.3722735081347 votes 259 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/vision/latest) Source Arena Original model label GPT-6 Astra (Max) Observed 2026-10-21T18:45:05.190Z Evidence SHA-256 `06e61305486dce3fec5dc776ac2fd8321104e84c346cf9e08fa6f8e8a66ce0d7` Source locator `/rows/216/row` | | | | | 16 | [GPT-5.5](https://benchize.com/models/gpt-5-5.md) | 1,360.09 | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1360.0916508118032 \| rating \| reported \| Higher is better \| ### Configuration category chinese config vision ### Reported statistics lower 1343.470231506973 rank 17 upper 1376.7130701166334 variance 71.91840199319367 votes 1777 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/vision/latest) Source Arena Original model label GPT-5.5 Observed 2026-10-21T18:45:05.190Z Evidence SHA-256 `06e61305486dce3fec5dc776ac2fd8321104e84c346cf9e08fa6f8e8a66ce0d7` Source locator `/rows/217/row` | | | | | 17 | [Qwen3.8 Max](https://benchize.com/models/qwen3-8-max.md) | 1,357.9 | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1357.8958612377721 \| rating \| reported \| Higher is better \| ### Configuration category chinese config vision ### Reported statistics lower 1331.878376085737 rank 18 upper 1383.913346389807 variance 176.21158138929235 votes 541 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/vision/latest) Source Arena Original model label Qwen3.8-Max Observed 2026-10-21T18:45:05.190Z Evidence SHA-256 `06e61305486dce3fec5dc776ac2fd8321104e84c346cf9e08fa6f8e8a66ce0d7` Source locator `/rows/218/row` | | | | | 18 | [Gemini 3.6 Flash](https://benchize.com/models/gemini-3-6-flash-high.md)High | 1,356.93 | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1356.9261228252938 \| rating \| reported \| Higher is better \| ### Configuration category chinese config vision Reasoning effort high thinkingEnabled true ### Reported statistics lower 1330.8393772782583 rank 19 upper 1383.0128683723292 variance 177.15100564654966 votes 536 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/vision/latest) Source Arena Original model label Gemini 3.6 Flash (High) Observed 2026-10-21T18:45:05.190Z Evidence SHA-256 `06e61305486dce3fec5dc776ac2fd8321104e84c346cf9e08fa6f8e8a66ce0d7` Source locator `/rows/219/row` | | | | | 19 | [GPT-5.5](https://benchize.com/models/gpt-5-5-high.md)High | 1,356.91 | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1356.9057574023489 \| rating \| reported \| Higher is better \| ### Configuration category chinese config vision Reasoning effort high thinkingEnabled true ### Reported statistics lower 1339.8736078345426 rank 20 upper 1373.937906970155 variance 75.51665459417922 votes 1603 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/vision/latest) Source Arena Original model label GPT-5.5 (High) Observed 2026-10-21T18:45:05.190Z Evidence SHA-256 `06e61305486dce3fec5dc776ac2fd8321104e84c346cf9e08fa6f8e8a66ce0d7` Source locator `/rows/220/row` | | | | | 20 | [Claude Opus 4.7](https://benchize.com/models/claude-opus-4-7-high.md)High | 1,355.24 | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1355.23786327834 \| rating \| reported \| Higher is better \| ### Configuration category chinese config vision Reasoning effort high thinkingEnabled true ### Reported statistics lower 1337.0884935584984 rank 21 upper 1373.3872329981816 variance 85.74857537272324 votes 1388 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/vision/latest) Source Arena Original model label Claude Opus 4.7 (High) Observed 2026-10-21T18:45:05.190Z Evidence SHA-256 `06e61305486dce3fec5dc776ac2fd8321104e84c346cf9e08fa6f8e8a66ce0d7` Source locator `/rows/221/row` | | | | | 21 | [GPT-5.4](https://benchize.com/models/gpt-5-4-high.md)High | 1,353.96 | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1353.962092611682 \| rating \| reported \| Higher is better \| ### Configuration category chinese config vision Reasoning effort high thinkingEnabled true ### Reported statistics lower 1337.7646515509334 rank 22 upper 1370.1595336724304 variance 68.29621483981296 votes 1846 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/vision/latest) Source Arena Original model label GPT-5.4 (High) Observed 2026-10-21T18:45:05.190Z Evidence SHA-256 `06e61305486dce3fec5dc776ac2fd8321104e84c346cf9e08fa6f8e8a66ce0d7` Source locator `/rows/222/row` | | | | | 22 | [Muse Spark 1.1](https://benchize.com/models/muse-spark-1-1.md) | 1,348.34 | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1348.3429086766755 \| rating \| reported \| Higher is better \| ### Configuration category chinese config vision ### Reported statistics lower 1325.896424201155 rank 23 upper 1370.789393152196 variance 131.159720519598 votes 767 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/vision/latest) Source Arena Original model label Muse Spark 1.1 Observed 2026-10-21T18:45:05.190Z Evidence SHA-256 `06e61305486dce3fec5dc776ac2fd8321104e84c346cf9e08fa6f8e8a66ce0d7` Source locator `/rows/223/row` | | | | | 23 | [Claude Opus 4.8](https://benchize.com/models/claude-opus-4-8.md) | 1,345.56 | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1345.560862120775 \| rating \| reported \| Higher is better \| ### Configuration category chinese config vision ### Reported statistics lower 1325.9637701983906 rank 26 upper 1365.1579540431592 variance 99.9740019977584 votes 1131 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/vision/latest) Source Arena Original model label Claude Opus 4.8 Observed 2026-10-21T18:45:05.190Z Evidence SHA-256 `06e61305486dce3fec5dc776ac2fd8321104e84c346cf9e08fa6f8e8a66ce0d7` Source locator `/rows/226/row` | | | | | 24 | [Claude Opus 4.8](https://benchize.com/models/claude-opus-4-8-high.md)High | 1,342.41 | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1342.4056303314649 \| rating \| reported \| Higher is better \| ### Configuration category chinese config vision Reasoning effort high thinkingEnabled true ### Reported statistics lower 1322.1846059807144 rank 28 upper 1362.6266546822153 variance 106.44128829155623 votes 1030 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/vision/latest) Source Arena Original model label Claude Opus 4.8 (High) Observed 2026-10-21T18:45:05.190Z Evidence SHA-256 `06e61305486dce3fec5dc776ac2fd8321104e84c346cf9e08fa6f8e8a66ce0d7` Source locator `/rows/228/row` | | | | | 25 | [GPT-5.6 Terra](https://benchize.com/models/gpt-5-6-terra-xhigh.md)Extra high | 1,336.72 | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1336.7190736213865 \| rating \| reported \| Higher is better \| ### Configuration category chinese config vision Reasoning effort xhigh thinkingEnabled true ### Reported statistics lower 1313.0665916215198 rank 30 upper 1360.3715556212535 variance 145.63214936479199 votes 682 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/vision/latest) Source Arena Original model label GPT-5.6 Terra (xHigh) Observed 2026-10-21T18:45:05.190Z Evidence SHA-256 `06e61305486dce3fec5dc776ac2fd8321104e84c346cf9e08fa6f8e8a66ce0d7` Source locator `/rows/230/row` | | | | | 26 | [GPT-5.4](https://benchize.com/models/gpt-5-4.md) | 1,336.24 | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1336.2370687731266 \| rating \| reported \| Higher is better \| ### Configuration category chinese config vision ### Reported statistics lower 1317.694137185766 rank 31 upper 1354.780000360487 variance 89.50774377724557 votes 1356 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/vision/latest) Source Arena Original model label GPT-5.4 Observed 2026-10-21T18:45:05.190Z Evidence SHA-256 `06e61305486dce3fec5dc776ac2fd8321104e84c346cf9e08fa6f8e8a66ce0d7` Source locator `/rows/231/row` | | | | | 27 | [Claude Sonnet 5](https://benchize.com/models/claude-sonnet-5-high.md)High | 1,330.65 | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1330.6510622904786 \| rating \| reported \| Higher is better \| ### Configuration category chinese config vision Reasoning effort high thinkingEnabled true ### Reported statistics lower 1308.7056790020895 rank 33 upper 1352.596445578868 variance 125.36899916248392 votes 847 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/vision/latest) Source Arena Original model label Claude Sonnet 5 (High) Observed 2026-10-21T18:45:05.190Z Evidence SHA-256 `06e61305486dce3fec5dc776ac2fd8321104e84c346cf9e08fa6f8e8a66ce0d7` Source locator `/rows/233/row` | | | | | 28 | [Gemini 3 Flash](https://benchize.com/models/gemini-3-flash.md) | 1,328.89 | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1328.8930038114934 \| rating \| reported \| Higher is better \| ### Configuration category chinese config vision ### Reported statistics lower 1315.1786651238879 rank 35 upper 1342.6073424990989 variance 48.96136973410683 votes 2749 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/vision/latest) Source Arena Original model label Gemini 3 Flash Observed 2026-10-21T18:45:05.190Z Evidence SHA-256 `06e61305486dce3fec5dc776ac2fd8321104e84c346cf9e08fa6f8e8a66ce0d7` Source locator `/rows/235/row` | | | | | 29 | [DeepSeek V4.1 Flash](https://benchize.com/models/deepseek-v4-1-flash-max.md)Max | 1,327.27 | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1327.267086403513 \| rating \| reported \| Higher is better \| ### Configuration category chinese config vision Reasoning effort max thinkingEnabled true ### Reported statistics lower 1285.7251088414132 rank 37 upper 1368.809063965613 variance 449.23972384485444 votes 199 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/vision/latest) Source Arena Original model label DeepSeek-V4.1-Flash-20260910 (Max) Observed 2026-10-21T18:45:05.190Z Evidence SHA-256 `06e61305486dce3fec5dc776ac2fd8321104e84c346cf9e08fa6f8e8a66ce0d7` Source locator `/rows/237/row` | | | | | 30 | [Gemma 4 31B](https://benchize.com/models/gemma-4-31b-it.md) | 1,325.85 | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1325.8485587778885 \| rating \| reported \| Higher is better \| ### Configuration category chinese config vision ### Reported statistics lower 1311.8002240972876 rank 38 upper 1339.896893458489 variance 51.37519794173132 votes 2734 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/vision/latest) Source Arena Original model label Gemma 4 31B Observed 2026-10-21T18:45:05.190Z Evidence SHA-256 `06e61305486dce3fec5dc776ac2fd8321104e84c346cf9e08fa6f8e8a66ce0d7` Source locator `/rows/238/row` | | | | | 31 | [MiMo-V2.5](https://benchize.com/models/mimo-v2-5.md) | 1,325.57 | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1325.5678259146455 \| rating \| reported \| Higher is better \| ### Configuration category chinese config vision ### Reported statistics lower 1308.5239045105984 rank 39 upper 1342.6117473186926 variance 75.62107792550665 votes 1580 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/vision/latest) Source Arena Original model label MiMo-V2.5 Observed 2026-10-21T18:45:05.190Z Evidence SHA-256 `06e61305486dce3fec5dc776ac2fd8321104e84c346cf9e08fa6f8e8a66ce0d7` Source locator `/rows/239/row` | | | | | 32 | [Qwen3.8 27B](https://benchize.com/models/qwen3-8-27b.md) | 1,325.53 | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1325.530808132724 \| rating \| reported \| Higher is better \| ### Configuration category chinese config vision ### Reported statistics lower 1295.7359525864147 rank 40 upper 1355.3256636790334 variance 231.0927849188896 votes 409 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/vision/latest) Source Arena Original model label Qwen3.8-27B Observed 2026-10-21T18:45:05.190Z Evidence SHA-256 `06e61305486dce3fec5dc776ac2fd8321104e84c346cf9e08fa6f8e8a66ce0d7` Source locator `/rows/240/row` | | | | | 33 | [Gemini 3 Flash](https://benchize.com/models/gemini-3-flash-minimal.md)Minimal | 1,316.64 | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1316.6445718831112 \| rating \| reported \| Higher is better \| ### Configuration category chinese config vision Reasoning effort minimal thinkingEnabled true ### Reported statistics lower 1302.4772286879156 rank 42 upper 1330.8119150783068 variance 52.249320526150164 votes 2539 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/vision/latest) Source Arena Original model label Gemini 3 Flash (Minimal) Observed 2026-10-21T18:45:05.190Z Evidence SHA-256 `06e61305486dce3fec5dc776ac2fd8321104e84c346cf9e08fa6f8e8a66ce0d7` Source locator `/rows/242/row` | | | | | 34 | [Qwen3.5 397B A17B](https://benchize.com/models/qwen3-5-397b-a17b.md) | 1,313.96 | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1313.9609595219395 \| rating \| reported \| Higher is better \| ### Configuration category chinese config vision ### Reported statistics lower 1298.7012722773727 rank 43 upper 1329.2206467665064 variance 60.61708993145447 votes 2045 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/vision/latest) Source Arena Original model label Qwen3.5-397B-A17B Observed 2026-10-21T18:45:05.190Z Evidence SHA-256 `06e61305486dce3fec5dc776ac2fd8321104e84c346cf9e08fa6f8e8a66ce0d7` Source locator `/rows/243/row` | | | | | 35 | [GPT-5.6 Sol](https://benchize.com/models/gpt-5-6-sol-xhigh.md)Extra high | 1,312.55 | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1312.552453794647 \| rating \| reported \| Higher is better \| ### Configuration category chinese config vision Reasoning effort xhigh thinkingEnabled true ### Reported statistics lower 1288.6478220864635 rank 44 upper 1336.4570855028303 variance 148.7537531381462 votes 677 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/vision/latest) Source Arena Original model label GPT-5.6 Sol (xHigh) Observed 2026-10-21T18:45:05.190Z Evidence SHA-256 `06e61305486dce3fec5dc776ac2fd8321104e84c346cf9e08fa6f8e8a66ce0d7` Source locator `/rows/244/row` | | | | | 36 | [Gemma 4 26B A4B](https://benchize.com/models/gemma-4-26b-a4b-it.md) | 1,312.49 | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1312.4924093711375 \| rating \| reported \| Higher is better \| ### Configuration category chinese config vision ### Reported statistics lower 1295.4587964341104 rank 45 upper 1329.5260223081646 variance 75.52963164031264 votes 1609 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/vision/latest) Source Arena Original model label Gemma 4 26B A4B Observed 2026-10-21T18:45:05.190Z Evidence SHA-256 `06e61305486dce3fec5dc776ac2fd8321104e84c346cf9e08fa6f8e8a66ce0d7` Source locator `/rows/245/row` | | | | | 37 | [MiniMax M3](https://benchize.com/models/minimax-m3.md) | 1,311.08 | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1311.0829185183948 \| rating \| reported \| Higher is better \| ### Configuration category chinese config vision ### Reported statistics lower 1290.9220516333614 rank 46 upper 1331.2437854034283 variance 105.80890555598704 votes 1048 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/vision/latest) Source Arena Original model label MiniMax-M3 Observed 2026-10-21T18:45:05.190Z Evidence SHA-256 `06e61305486dce3fec5dc776ac2fd8321104e84c346cf9e08fa6f8e8a66ce0d7` Source locator `/rows/246/row` | | | | | 38 | [Gemini 3.5 Flash-Lite](https://benchize.com/models/gemini-3-5-flash-lite.md) | 1,310.62 | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1310.6153073770736 \| rating \| reported \| Higher is better \| ### Configuration category chinese config vision ### Reported statistics lower 1283.9167744590648 rank 47 upper 1337.3138402950826 variance 185.55754291417938 votes 524 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/vision/latest) Source Arena Original model label Gemini 3.5 Flash-Lite Observed 2026-10-21T18:45:05.190Z Evidence SHA-256 `06e61305486dce3fec5dc776ac2fd8321104e84c346cf9e08fa6f8e8a66ce0d7` Source locator `/rows/247/row` | | | | | 39 | [Claude Sonnet 4.6](https://benchize.com/models/claude-sonnet-4-6.md) | 1,307.11 | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1307.1115698456329 \| rating \| reported \| Higher is better \| ### Configuration category chinese config vision ### Reported statistics lower 1290.3637792028633 rank 48 upper 1323.8593604884024 variance 73.01613905192316 votes 1736 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/vision/latest) Source Arena Original model label Claude Sonnet 4.6 Observed 2026-10-21T18:45:05.190Z Evidence SHA-256 `06e61305486dce3fec5dc776ac2fd8321104e84c346cf9e08fa6f8e8a66ce0d7` Source locator `/rows/248/row` | | | | | 40 | [GPT-5.2](https://benchize.com/models/gpt-5-2-high.md)High | 1,304.84 | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1304.8361998345263 \| rating \| reported \| Higher is better \| ### Configuration category chinese config vision Reasoning effort high thinkingEnabled true ### Reported statistics lower 1286.958139191658 rank 49 upper 1322.7142604773949 variance 83.20408138393873 votes 1351 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/vision/latest) Source Arena Original model label GPT-5.2 (High) Observed 2026-10-21T18:45:05.190Z Evidence SHA-256 `06e61305486dce3fec5dc776ac2fd8321104e84c346cf9e08fa6f8e8a66ce0d7` Source locator `/rows/249/row` | | | | | 41 | [Qwen3.5-122B-A10B](https://benchize.com/models/qwen3-5-122b-a10b.md) | 1,300.8 | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1300.7980399592495 \| rating \| reported \| Higher is better \| ### Configuration category chinese config vision ### Reported statistics lower 1280.4980729830702 rank 51 upper 1321.098006935429 variance 107.27400148454949 votes 1011 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/vision/latest) Source Arena Original model label Qwen3.5-122B-A10B Observed 2026-10-21T18:45:05.190Z Evidence SHA-256 `06e61305486dce3fec5dc776ac2fd8321104e84c346cf9e08fa6f8e8a66ce0d7` Source locator `/rows/251/row` | | | | | 42 | [Qwen3.5-27B](https://benchize.com/models/qwen3-5-27b.md) | 1,300.51 | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1300.5112705237486 \| rating \| reported \| Higher is better \| ### Configuration category chinese config vision ### Reported statistics lower 1285.019622172438 rank 52 upper 1316.002918875059 variance 62.473966230698615 votes 1997 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/vision/latest) Source Arena Original model label Qwen3.5-27B Observed 2026-10-21T18:45:05.190Z Evidence SHA-256 `06e61305486dce3fec5dc776ac2fd8321104e84c346cf9e08fa6f8e8a66ce0d7` Source locator `/rows/252/row` | | | | | 43 | [Gemini 2.5 Pro](https://benchize.com/models/gemini-2-5-pro.md) | 1,300.18 | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1300.1780954784963 \| rating \| reported \| Higher is better \| ### Configuration category chinese config vision ### Reported statistics lower 1287.2950894162125 rank 53 upper 1313.06110154078 variance 43.20542089550477 votes 4797 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/vision/latest) Source Arena Original model label Gemini 2.5 Pro Observed 2026-10-21T18:45:05.190Z Evidence SHA-256 `06e61305486dce3fec5dc776ac2fd8321104e84c346cf9e08fa6f8e8a66ce0d7` Source locator `/rows/253/row` | | | | | 44 | [GPT-5.6 Luna](https://benchize.com/models/gpt-5-6-luna-xhigh.md)Extra high | 1,293.64 | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1293.6357915051103 \| rating \| reported \| Higher is better \| ### Configuration category chinese config vision Reasoning effort xhigh thinkingEnabled true ### Reported statistics lower 1268.7691717861662 rank 55 upper 1318.5024112240544 variance 160.96717552079474 votes 631 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/vision/latest) Source Arena Original model label GPT-5.6 Luna (xHigh) Observed 2026-10-21T18:45:05.190Z Evidence SHA-256 `06e61305486dce3fec5dc776ac2fd8321104e84c346cf9e08fa6f8e8a66ce0d7` Source locator `/rows/255/row` | | | | | 45 | [GPT-5.4 Mini](https://benchize.com/models/gpt-5-4-mini-high.md)High | 1,286.17 | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1286.1698246055905 \| rating \| reported \| Higher is better \| ### Configuration category chinese config vision Reasoning effort high thinkingEnabled true ### Reported statistics lower 1269.0579362126468 rank 59 upper 1303.2817129985342 variance 76.22539718378366 votes 1661 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/vision/latest) Source Arena Original model label GPT-5.4 mini (High) Observed 2026-10-21T18:45:05.190Z Evidence SHA-256 `06e61305486dce3fec5dc776ac2fd8321104e84c346cf9e08fa6f8e8a66ce0d7` Source locator `/rows/259/row` | | | | | 46 | [Gemini 2.5 Flash](https://benchize.com/models/gemini-2-5-flash.md) | 1,284.4 | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1284.4043286903836 \| rating \| reported \| Higher is better \| ### Configuration category chinese config vision ### Reported statistics lower 1271.382101600562 rank 60 upper 1297.426555780205 variance 44.14427078206692 votes 3692 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/vision/latest) Source Arena Original model label Gemini 2.5 Flash Observed 2026-10-21T18:45:05.190Z Evidence SHA-256 `06e61305486dce3fec5dc776ac2fd8321104e84c346cf9e08fa6f8e8a66ce0d7` Source locator `/rows/260/row` | | | | | 47 | [MiMo-V2-Omni](https://benchize.com/models/mimo-v2-omni.md) | 1,283.84 | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1283.8363152495679 \| rating \| reported \| Higher is better \| ### Configuration category chinese config vision ### Reported statistics lower 1259.8409437366045 rank 61 upper 1307.8316867625315 variance 149.88520791720956 votes 693 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/vision/latest) Source Arena Original model label MiMo-V2-Omni Observed 2026-10-21T18:45:05.190Z Evidence SHA-256 `06e61305486dce3fec5dc776ac2fd8321104e84c346cf9e08fa6f8e8a66ce0d7` Source locator `/rows/261/row` | | | | | 48 | [Qwen3 VL 235B A22B Instruct](https://benchize.com/models/qwen3-vl-235b-a22b-instruct.md) | 1,283.04 | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1283.0436924201372 \| rating \| reported \| Higher is better \| ### Configuration category chinese config vision ### Reported statistics lower 1263.6635808710273 rank 62 upper 1302.423803969247 variance 97.77241959034532 votes 998 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/vision/latest) Source Arena Original model label Qwen3-VL-235B-A22B-Instruct Observed 2026-10-21T18:45:05.190Z Evidence SHA-256 `06e61305486dce3fec5dc776ac2fd8321104e84c346cf9e08fa6f8e8a66ce0d7` Source locator `/rows/262/row` | | | | | 49 | [Gemini 3.1 Flash Lite Preview](https://benchize.com/models/gemini-3-1-flash-lite-preview.md) | 1,277.74 | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1277.7363395714083 \| rating \| reported \| Higher is better \| ### Configuration category chinese config vision ### Reported statistics lower 1261.956176004658 rank 64 upper 1293.5165031381587 variance 64.82265561508753 votes 1989 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/vision/latest) Source Arena Original model label Gemini 3.1 Flash-Lite Preview Observed 2026-10-21T18:45:05.190Z Evidence SHA-256 `06e61305486dce3fec5dc776ac2fd8321104e84c346cf9e08fa6f8e8a66ce0d7` Source locator `/rows/264/row` | | | | | 50 | [GPT-5.2](https://benchize.com/models/gpt-5-2.md) | 1,270.41 | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1270.4138737696846 \| rating \| reported \| Higher is better \| ### Configuration category chinese config vision ### Reported statistics lower 1252.9846774957873 rank 65 upper 1287.843070043582 variance 79.07852119032862 votes 1437 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/vision/latest) Source Arena Original model label GPT-5.2 Observed 2026-10-21T18:45:05.190Z Evidence SHA-256 `06e61305486dce3fec5dc776ac2fd8321104e84c346cf9e08fa6f8e8a66ce0d7` Source locator `/rows/265/row` | | | | | 51 | [GPT-5.1](https://benchize.com/models/gpt-5-1-high.md)High | 1,270.29 | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1270.2931608048948 \| rating \| reported \| Higher is better \| ### Configuration category chinese config vision Reasoning effort high thinkingEnabled true ### Reported statistics lower 1246.9756089723855 rank 66 upper 1293.6107126374045 variance 141.53691314684443 votes 671 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/vision/latest) Source Arena Original model label GPT-5.1 (High) Observed 2026-10-21T18:45:05.190Z Evidence SHA-256 `06e61305486dce3fec5dc776ac2fd8321104e84c346cf9e08fa6f8e8a66ce0d7` Source locator `/rows/266/row` | | | | | 52 | [GPT-5.1](https://benchize.com/models/gpt-5-1.md) | 1,269.58 | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1269.581660840891 \| rating \| reported \| Higher is better \| ### Configuration category chinese config vision ### Reported statistics lower 1248.6197887926564 rank 67 upper 1290.5435328891253 variance 114.3836496175579 votes 813 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/vision/latest) Source Arena Original model label GPT-5.1 Observed 2026-10-21T18:45:05.190Z Evidence SHA-256 `06e61305486dce3fec5dc776ac2fd8321104e84c346cf9e08fa6f8e8a66ce0d7` Source locator `/rows/267/row` | | | | | 53 | [GPT-5 Chat](https://benchize.com/models/gpt-5-chat.md) | 1,267.38 | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1267.3772853913797 \| rating \| reported \| Higher is better \| ### Configuration category chinese config vision ### Reported statistics lower 1250.591354362509 rank 69 upper 1284.1632164202501 variance 73.34908264227747 votes 2052 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/vision/latest) Source Arena Original model label GPT-5 Chat Observed 2026-10-21T18:45:05.190Z Evidence SHA-256 `06e61305486dce3fec5dc776ac2fd8321104e84c346cf9e08fa6f8e8a66ce0d7` Source locator `/rows/269/row` | | | | | 54 | [GPT-6 Luna](https://benchize.com/models/gpt-6-luna-max.md)Max | 1,266.18 | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1266.1796511927982 \| rating \| reported \| Higher is better \| ### Configuration category chinese config vision Reasoning effort max thinkingEnabled true ### Reported statistics lower 1222.2446098178932 rank 70 upper 1310.1146925677033 variance 502.4882344738569 votes 169 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/vision/latest) Source Arena Original model label GPT-6 Luna (Max) Observed 2026-10-21T18:45:05.190Z Evidence SHA-256 `06e61305486dce3fec5dc776ac2fd8321104e84c346cf9e08fa6f8e8a66ce0d7` Source locator `/rows/270/row` | | | | | 55 | [Mistral Medium 3.5](https://benchize.com/models/mistral-medium-3-5.md) | 1,243.88 | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1243.875712172996 \| rating \| reported \| Higher is better \| ### Configuration category chinese config vision ### Reported statistics lower 1206.3293619337796 rank 76 upper 1281.4220624122122 variance 366.9773599268115 votes 287 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/vision/latest) Source Arena Original model label Mistral Medium 3.5 Observed 2026-10-21T18:45:05.190Z Evidence SHA-256 `06e61305486dce3fec5dc776ac2fd8321104e84c346cf9e08fa6f8e8a66ce0d7` Source locator `/rows/276/row` | | | | | 56 | [Mistral Large 3](https://benchize.com/models/mistral-large-3.md) | 1,240.36 | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1240.3585921530403 \| rating \| reported \| Higher is better \| ### Configuration category chinese config vision ### Reported statistics lower 1214.3193987928707 rank 77 upper 1266.3977855132098 variance 176.50575536451572 votes 569 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/vision/latest) Source Arena Original model label Mistral Large 3 Observed 2026-10-21T18:45:05.190Z Evidence SHA-256 `06e61305486dce3fec5dc776ac2fd8321104e84c346cf9e08fa6f8e8a66ce0d7` Source locator `/rows/277/row` | | | | | 57 | [GPT-5](https://benchize.com/models/gpt-5-high.md)High | 1,234.47 | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1234.4735077588427 \| rating \| reported \| Higher is better \| ### Configuration category chinese config vision Reasoning effort high thinkingEnabled true ### Reported statistics lower 1217.8210951556462 rank 80 upper 1251.1259203620396 variance 72.18685880823777 votes 2135 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/vision/latest) Source Arena Original model label GPT-5 (High) Observed 2026-10-21T18:45:05.190Z Evidence SHA-256 `06e61305486dce3fec5dc776ac2fd8321104e84c346cf9e08fa6f8e8a66ce0d7` Source locator `/rows/280/row` | | | | | 58 | [GPT-5.4 Nano](https://benchize.com/models/gpt-5-4-nano-high.md)High | 1,232.36 | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1232.3557625312205 \| rating \| reported \| Higher is better \| ### Configuration category chinese config vision Reasoning effort high thinkingEnabled true ### Reported statistics lower 1215.3344574588382 rank 83 upper 1249.3770676036027 variance 75.42052118490587 votes 1739 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/vision/latest) Source Arena Original model label GPT-5.4 nano (High) Observed 2026-10-21T18:45:05.190Z Evidence SHA-256 `06e61305486dce3fec5dc776ac2fd8321104e84c346cf9e08fa6f8e8a66ce0d7` Source locator `/rows/283/row` | | | | | 59 | [Qwen3 VL 235B A22B Thinking](https://benchize.com/models/qwen3-vl-235b-a22b-thinking.md) | 1,219.35 | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1219.35212409733 \| rating \| reported \| Higher is better \| ### Configuration category chinese config vision ### Reported statistics lower 1176.434585167197 rank 85 upper 1262.2696630274631 variance 479.4832468063965 votes 164 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/vision/latest) Source Arena Original model label Qwen3-VL-235B-A22B-Thinking Observed 2026-10-21T18:45:05.190Z Evidence SHA-256 `06e61305486dce3fec5dc776ac2fd8321104e84c346cf9e08fa6f8e8a66ce0d7` Source locator `/rows/285/row` | | | | | 60 | [GPT-5 Mini](https://benchize.com/models/gpt-5-mini-high.md)High | 1,213.76 | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1213.7626993667068 \| rating \| reported \| Higher is better \| ### Configuration category chinese config vision Reasoning effort high thinkingEnabled true ### Reported statistics lower 1195.307062373991 rank 88 upper 1232.2183363594227 variance 88.66697593425089 votes 1600 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/vision/latest) Source Arena Original model label GPT-5 mini (High) Observed 2026-10-21T18:45:05.190Z Evidence SHA-256 `06e61305486dce3fec5dc776ac2fd8321104e84c346cf9e08fa6f8e8a66ce0d7` Source locator `/rows/288/row` | | | | | 61 | [Gemini 1.5 Pro 002](https://benchize.com/models/gemini-1-5-pro-002.md) | 1,186.7 | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1186.6964045842537 \| rating \| reported \| Higher is better \| ### Configuration category chinese config vision ### Reported statistics lower 1143.1281281568326 rank 91 upper 1230.264681011675 variance 494.1338172442498 votes 395 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/vision/latest) Source Arena Original model label Gemini 1.5 Pro (002) Observed 2026-10-21T18:45:05.190Z Evidence SHA-256 `06e61305486dce3fec5dc776ac2fd8321104e84c346cf9e08fa6f8e8a66ce0d7` Source locator `/rows/291/row` | | | | | 62 | [GPT-5 Nano](https://benchize.com/models/gpt-5-nano-high.md)High | 1,175.77 | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1175.772181298382 \| rating \| reported \| Higher is better \| ### Configuration category chinese config vision Reasoning effort high thinkingEnabled true ### Reported statistics lower 1132.5868223508107 rank 94 upper 1218.9575402459534 variance 485.4861953442955 votes 189 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/vision/latest) Source Arena Original model label GPT-5 nano (High) Observed 2026-10-21T18:45:05.190Z Evidence SHA-256 `06e61305486dce3fec5dc776ac2fd8321104e84c346cf9e08fa6f8e8a66ce0d7` Source locator `/rows/294/row` | | | | | 63 | [Gemma 3 27B](https://benchize.com/models/gemma-3-27b-it.md) | 1,163.67 | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1163.668923848267 \| rating \| reported \| Higher is better \| ### Configuration category chinese config vision ### Reported statistics lower 1142.8086836726573 rank 96 upper 1184.5291640238768 variance 113.27717945066885 votes 1020 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/vision/latest) Source Arena Original model label Gemma 3 27B IT Observed 2026-10-21T18:45:05.190Z Evidence SHA-256 `06e61305486dce3fec5dc776ac2fd8321104e84c346cf9e08fa6f8e8a66ce0d7` Source locator `/rows/296/row` | | | | | 64 | [Mistral Small 3.1 24B](https://benchize.com/models/mistral-small-3-1-24b-instruct.md) | 1,155.15 | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1155.147696425525 \| rating \| reported \| Higher is better \| ### Configuration category chinese config vision ### Reported statistics lower 1134.4378441497731 rank 99 upper 1175.8575487012772 variance 111.64976674303513 votes 1251 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/vision/latest) Source Arena Original model label Mistral Small 3.1 24B Instruct (2503) Observed 2026-10-21T18:45:05.190Z Evidence SHA-256 `06e61305486dce3fec5dc776ac2fd8321104e84c346cf9e08fa6f8e8a66ce0d7` Source locator `/rows/299/row` | | | | | 65 | [Gemini 2.0 Flash 001](https://benchize.com/models/gemini-2-0-flash-001.md) | 1,144.84 | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1144.8444118660354 \| rating \| reported \| Higher is better \| ### Configuration category chinese config vision ### Reported statistics lower 1115.1242673788072 rank 100 upper 1174.564556353264 variance 229.9353005122494 votes 414 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/vision/latest) Source Arena Original model label Gemini 2.0 Flash (001) Observed 2026-10-21T18:45:05.190Z Evidence SHA-256 `06e61305486dce3fec5dc776ac2fd8321104e84c346cf9e08fa6f8e8a66ce0d7` Source locator `/rows/300/row` | | | | | 66 | [Llama 4 Maverick](https://benchize.com/models/llama-4-maverick.md) | 1,140.83 | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1140.8315081016071 \| rating \| reported \| Higher is better \| ### Configuration category chinese config vision ### Reported statistics lower 1106.7598156130064 rank 101 upper 1174.903200590208 variance 302.1977543489606 votes 294 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/vision/latest) Source Arena Original model label Llama 4 Maverick 17B 128E Instruct Observed 2026-10-21T18:45:05.190Z Evidence SHA-256 `06e61305486dce3fec5dc776ac2fd8321104e84c346cf9e08fa6f8e8a66ce0d7` Source locator `/rows/301/row` | | | | | 67 | [Gemini 1.5 Flash 002](https://benchize.com/models/gemini-1-5-flash-002.md) | 1,137.03 | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1137.029949830003 \| rating \| reported \| Higher is better \| ### Configuration category chinese config vision ### Reported statistics lower 1092.7305791814047 rank 102 upper 1181.3293204786016 variance 510.85650828538803 votes 370 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/vision/latest) Source Arena Original model label Gemini 1.5 Flash (002) Observed 2026-10-21T18:45:05.190Z Evidence SHA-256 `06e61305486dce3fec5dc776ac2fd8321104e84c346cf9e08fa6f8e8a66ce0d7` Source locator `/rows/302/row` | | | | | 68 | [GPT-4o (2024-05-13)](https://benchize.com/models/gpt-4o-2024-05-13.md) | 1,132.24 | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1132.2433124178356 \| rating \| reported \| Higher is better \| ### Configuration category chinese config vision ### Reported statistics lower 1094.0579934336213 rank 103 upper 1170.4286314020496 variance 379.57418105622673 votes 1472 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/vision/latest) Source Arena Original model label GPT-4o (2024-05-13) Observed 2026-10-21T18:45:05.190Z Evidence SHA-256 `06e61305486dce3fec5dc776ac2fd8321104e84c346cf9e08fa6f8e8a66ce0d7` Source locator `/rows/303/row` | | | | | 69 | [Qwen2.5 VL 72B Instruct](https://benchize.com/models/qwen2-5-vl-72b-instruct.md) | 1,107.14 | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1107.137183734385 \| rating \| reported \| Higher is better \| ### Configuration category chinese config vision ### Reported statistics lower 1051.8128546620758 rank 105 upper 1162.4615128066941 variance 796.7757901796523 votes 119 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/vision/latest) Source Arena Original model label Qwen2.5-VL-72B-Instruct Observed 2026-10-21T18:45:05.190Z Evidence SHA-256 `06e61305486dce3fec5dc776ac2fd8321104e84c346cf9e08fa6f8e8a66ce0d7` Source locator `/rows/305/row` | | | | | 70 | [Llama 4 Scout](https://benchize.com/models/llama-4-scout.md) | 1,106.25 | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1106.2490036670324 \| rating \| reported \| Higher is better \| ### Configuration category chinese config vision ### Reported statistics lower 1069.9363464061464 rank 106 upper 1142.5616609279184 variance 343.2573766620033 votes 278 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/vision/latest) Source Arena Original model label Llama 4 Scout 17B 16E Instruct Observed 2026-10-21T18:45:05.190Z Evidence SHA-256 `06e61305486dce3fec5dc776ac2fd8321104e84c346cf9e08fa6f8e8a66ce0d7` Source locator `/rows/306/row` | | | | | 71 | [GPT-4o-mini (2024-07-18)](https://benchize.com/models/gpt-4o-mini-2024-07-18.md) | 1,033.28 | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1033.2847527859115 \| rating \| reported \| Higher is better \| ### Configuration category chinese config vision ### Reported statistics lower 995.2282380534455 rank 112 upper 1071.3412675183774 variance 377.0177896429226 votes 954 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/vision/latest) Source Arena Original model label GPT-4o mini (2024-07-18) Observed 2026-10-21T18:45:05.190Z Evidence SHA-256 `06e61305486dce3fec5dc776ac2fd8321104e84c346cf9e08fa6f8e8a66ce0d7` Source locator `/rows/312/row` | | | | | 72 | [Gemini 1.5 Pro 001](https://benchize.com/models/gemini-1-5-pro-001.md) | 1,030.47 | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1030.4676039977205 \| rating \| reported \| Higher is better \| ### Configuration category chinese config vision ### Reported statistics lower 990.2515219836293 rank 113 upper 1070.683686011812 variance 421.020588285748 votes 1168 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/vision/latest) Source Arena Original model label Gemini 1.5 Pro (001) Observed 2026-10-21T18:45:05.190Z Evidence SHA-256 `06e61305486dce3fec5dc776ac2fd8321104e84c346cf9e08fa6f8e8a66ce0d7` Source locator `/rows/313/row` | | | | | 73 | [GPT-4o (2024-08-06)](https://benchize.com/models/gpt-4o-2024-08-06.md) | 1,009.36 | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1009.3611678562212 \| rating \| reported \| Higher is better \| ### Configuration category chinese config vision ### Reported statistics lower 957.1220762629812 rank 115 upper 1061.600259449461 variance 710.3870737299255 votes 186 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/vision/latest) Source Arena Original model label GPT-4o (2024-08-06) Observed 2026-10-21T18:45:05.190Z Evidence SHA-256 `06e61305486dce3fec5dc776ac2fd8321104e84c346cf9e08fa6f8e8a66ce0d7` Source locator `/rows/315/row` | | | | | 74 | [Llama 3.2 11B Vision Instruct](https://benchize.com/models/llama-3-2-11b-vision-instruct.md) | 914.83 | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 914.8315239457502 \| rating \| reported \| Higher is better \| ### Configuration category chinese config vision ### Reported statistics lower 865.9499472388029 rank 127 upper 963.7131006526974 variance 622.005506992632 votes 266 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/vision/latest) Source Arena Original model label Llama 3.2 11B Vision Instruct Observed 2026-10-21T18:45:05.190Z Evidence SHA-256 `06e61305486dce3fec5dc776ac2fd8321104e84c346cf9e08fa6f8e8a66ce0d7` Source locator `/rows/327/row` | | | | --- Cite as: Arena vision / chinese (config: vision) — Benchize, https://benchize.com/benchmarks/benchmark%3Avision%3Achinese--config-vision (retrieved 2026-10-21)