# DeepSeek V3.2 ExpThinking > Source: Benchize (https://benchize.com) — https://benchize.com/models/deepseek-v3-2-exp-thinking. When citing or reusing this content, credit "Benchize" and link to https://benchize.com/models/deepseek-v3-2-exp-thinking. DeepSeek Canonical URL: https://benchize.com/models/deepseek-v3-2-exp-thinking Last updated: Thu, 22 Oct 2026 06:20:09 GMT Reproduction and quotation must name Benchize, link to the canonical HTML URL, and retain individual source citations. DeepSeek ## Benchmarks | Benchmark | Score | Rank | | | --- | --- | --- | --- | | [Arena text style control / french](https://benchize.com/benchmarks/lmarena%3Atext_style_control%3Afrench.md) | 1,418.91 | 85 / 132 | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1418.9146146856422 \| rating \| reported \| Higher is better \| ### Configuration category french config text_style_control thinkingEnabled true ### Reported statistics lower 1372.5166795571722 rank 148 upper 1465.3125498141121 variance 560.403868600291 votes 147 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label DeepSeek-V3.2-Exp (Thinking) Observed 2026-10-22T00:45:04.817Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/2985/row` | | | | | [Arena text style control / math](https://benchize.com/benchmarks/lmarena%3Atext_style_control%3Amath.md) | 1,422.56 | 77 / 149 | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1422.559583743318 \| rating \| reported \| Higher is better \| ### Configuration category math config text_style_control thinkingEnabled true ### Reported statistics lower 1396.0606608191813 rank 127 upper 1449.0585066674546 variance 182.79329518165994 votes 477 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label DeepSeek-V3.2-Exp (Thinking) Observed 2026-10-22T00:45:04.817Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/9039/row` | | | | | [Arena text / overall](https://benchize.com/benchmarks/lmarena%3Atext.md) | 1,424.87 | 62 / 151 | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1424.8707629711632 \| rating \| reported \| Higher is better \| ### Configuration category overall config text thinkingEnabled true ### Reported statistics lower 1418.325148934694 rank 105 upper 1431.4163770076325 variance 11.153331355165077 votes 9000 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) Source Arena Original model label DeepSeek-V3.2-Exp (Thinking) Observed 2026-10-22T00:45:04.817Z Evidence SHA-256 `8e027ef69b8de06c4b2a8b217bfe816b1f1536269bb257fd295b4ef1ba8246ac` Source locator `/rows/104/row` | | | | | [Arena text style control / longer query](https://benchize.com/benchmarks/lmarena%3Atext_style_control%3Alonger_query.md) | 1,434.02 | 73 / 150 | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1434.0237643180603 \| rating \| reported \| Higher is better \| ### Configuration category longer_query config text_style_control thinkingEnabled true ### Reported statistics lower 1421.4616403750492 rank 122 upper 1446.5858882610712 variance 41.07995564327194 votes 2110 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label DeepSeek-V3.2-Exp (Thinking) Observed 2026-10-22T00:45:04.817Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/8639/row` | | | | | [Arena text / hard prompts](https://benchize.com/benchmarks/lmarena%3Atext%3Ahard_prompts.md) | 1,426.91 | 71 / 151 | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1426.906636705638 \| rating \| reported \| Higher is better \| ### Configuration category hard_prompts config text thinkingEnabled true ### Reported statistics lower 1418.3406211372808 rank 119 upper 1435.4726522739952 variance 19.101238915293692 votes 4717 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) Source Arena Original model label DeepSeek-V3.2-Exp (Thinking) Observed 2026-10-22T00:45:04.817Z Evidence SHA-256 `8e027ef69b8de06c4b2a8b217bfe816b1f1536269bb257fd295b4ef1ba8246ac` Source locator `/rows/3569/row` | | | | | [Arena text style control / russian](https://benchize.com/benchmarks/lmarena%3Atext_style_control%3Arussian.md) | 1,414.17 | 73 / 150 | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1414.1728496850315 \| rating \| reported \| Higher is better \| ### Configuration category russian config text_style_control thinkingEnabled true ### Reported statistics lower 1392.661592911583 rank 123 upper 1435.68410645848 variance 120.4579274624701 votes 656 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label DeepSeek-V3.2-Exp (Thinking) Observed 2026-10-22T00:45:04.817Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/10506/row` | | | | | [Arena text / polish](https://benchize.com/benchmarks/lmarena%3Atext%3Apolish.md) | 1,434.88 | 44 / 117 | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1434.878422460885 \| rating \| reported \| Higher is better \| ### Configuration category polish config text thinkingEnabled true ### Reported statistics lower 1405.9399683237311 rank 72 upper 1463.8168765980392 variance 217.99898604584038 votes 397 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) Source Arena Original model label DeepSeek-V3.2-Exp (Thinking) Observed 2026-10-22T00:45:04.817Z Evidence SHA-256 `8e027ef69b8de06c4b2a8b217bfe816b1f1536269bb257fd295b4ef1ba8246ac` Source locator `/rows/10219/row` | | | | | [Arena text / french](https://benchize.com/benchmarks/lmarena%3Atext%3Afrench.md) | 1,410.63 | 83 / 132 | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1410.63274882144 \| rating \| reported \| Higher is better \| ### Configuration category french config text thinkingEnabled true ### Reported statistics lower 1364.3953204624572 rank 143 upper 1456.8701771804228 variance 556.5333070174008 votes 147 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) Source Arena Original model label DeepSeek-V3.2-Exp (Thinking) Observed 2026-10-22T00:45:04.817Z Evidence SHA-256 `8e027ef69b8de06c4b2a8b217bfe816b1f1536269bb257fd295b4ef1ba8246ac` Source locator `/rows/2980/row` | | | | | [Arena text / korean](https://benchize.com/benchmarks/lmarena%3Atext%3Akorean.md) | 1,348.91 | 77 / 124 | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1348.912750907873 \| rating \| reported \| Higher is better \| ### Configuration category korean config text thinkingEnabled true ### Reported statistics lower 1307.2535816934949 rank 139 upper 1390.5719201222514 variance 451.7779470348756 votes 218 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) Source Arena Original model label DeepSeek-V3.2-Exp (Thinking) Observed 2026-10-22T00:45:04.817Z Evidence SHA-256 `8e027ef69b8de06c4b2a8b217bfe816b1f1536269bb257fd295b4ef1ba8246ac` Source locator `/rows/8372/row` | | | | | [Arena text style control / non english](https://benchize.com/benchmarks/lmarena%3Atext_style_control%3Anon_english.md) | 1,406.3 | 73 / 151 | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1406.3017408409562 \| rating \| reported \| Higher is better \| ### Configuration category non_english config text_style_control thinkingEnabled true ### Reported statistics lower 1398.1024360102476 rank 128 upper 1414.5010456716648 variance 17.50079926529907 votes 5109 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label DeepSeek-V3.2-Exp (Thinking) Observed 2026-10-22T00:45:04.817Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/9858/row` | | | | | [Arena text style control / hard prompts english](https://benchize.com/benchmarks/lmarena%3Atext_style_control%3Ahard_prompts_english.md) | 1,460.11 | 66 / 151 | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1460.1146902255555 \| rating \| reported \| Higher is better \| ### Configuration category hard_prompts_english config text_style_control thinkingEnabled true ### Reported statistics lower 1447.208534568802 rank 109 upper 1473.0208458823085 variance 43.36083285314192 votes 2060 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label DeepSeek-V3.2-Exp (Thinking) Observed 2026-10-22T00:45:04.817Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/3976/row` | | | | | [Arena text style control / expert](https://benchize.com/benchmarks/lmarena%3Atext_style_control%3Aexpert.md) | 1,451.02 | 72 / 148 | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1451.0193287752008 \| rating \| reported \| Higher is better \| ### Configuration category expert config text_style_control thinkingEnabled true ### Reported statistics lower 1422.7524355789933 rank 117 upper 1479.2862219714084 variance 207.99839026295325 votes 426 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label DeepSeek-V3.2-Exp (Thinking) Observed 2026-10-22T00:45:04.817Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/2587/row` | | | | | [Arena text / english](https://benchize.com/benchmarks/lmarena%3Atext%3Aenglish.md) | 1,441.25 | 55 / 151 | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1441.2494045523738 \| rating \| reported \| Higher is better \| ### Configuration category english config text thinkingEnabled true ### Reported statistics lower 1431.757958198396 rank 92 upper 1450.7408509063514 variance 23.45139128008597 votes 3891 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) Source Arena Original model label DeepSeek-V3.2-Exp (Thinking) Observed 2026-10-22T00:45:04.817Z Evidence SHA-256 `8e027ef69b8de06c4b2a8b217bfe816b1f1536269bb257fd295b4ef1ba8246ac` Source locator `/rows/1728/row` | | | | | [Arena text style control / korean](https://benchize.com/benchmarks/lmarena%3Atext_style_control%3Akorean.md) | 1,350.81 | 75 / 124 | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1350.813690365648 \| rating \| reported \| Higher is better \| ### Configuration category korean config text_style_control thinkingEnabled true ### Reported statistics lower 1308.9055705963108 rank 137 upper 1392.7218101349854 variance 457.1936299667953 votes 218 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label DeepSeek-V3.2-Exp (Thinking) Observed 2026-10-22T00:45:04.817Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/8370/row` | | | | | [Arena text / chinese](https://benchize.com/benchmarks/lmarena%3Atext%3Achinese.md) | 1,459.73 | 69 / 146 | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1459.7275130815526 \| rating \| reported \| Higher is better \| ### Configuration category chinese config text thinkingEnabled true ### Reported statistics lower 1433.7430301721206 rank 110 upper 1485.7119959909846 variance 175.76482882837774 votes 517 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) Source Arena Original model label DeepSeek-V3.2-Exp (Thinking) Observed 2026-10-22T00:45:04.817Z Evidence SHA-256 `8e027ef69b8de06c4b2a8b217bfe816b1f1536269bb257fd295b4ef1ba8246ac` Source locator `/rows/526/row` | | | | | [Arena text style control / industry writing and literature and language](https://benchize.com/benchmarks/lmarena%3Atext_style_control%3Aindustry_writing_and_literature_and_language.md) | 1,398.47 | 77 / 151 | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1398.469626074792 \| rating \| reported \| Higher is better \| ### Configuration category industry_writing_and_literature_and_language config text_style_control thinkingEnabled true ### Reported statistics lower 1385.5293375631347 rank 131 upper 1411.4099145864493 variance 43.590488556811344 votes 2097 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label DeepSeek-V3.2-Exp (Thinking) Observed 2026-10-22T00:45:04.817Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/7248/row` | | | | | [Arena text / industry entertainment and sports and media](https://benchize.com/benchmarks/lmarena%3Atext%3Aindustry_entertainment_and_sports_and_media.md) | 1,389.14 | 68 / 151 | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1389.1421590793766 \| rating \| reported \| Higher is better \| ### Configuration category industry_entertainment_and_sports_and_media config text thinkingEnabled true ### Reported statistics lower 1374.7739333821253 rank 118 upper 1403.510384776628 variance 53.74153917126957 votes 1664 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) Source Arena Original model label DeepSeek-V3.2-Exp (Thinking) Observed 2026-10-22T00:45:04.817Z Evidence SHA-256 `8e027ef69b8de06c4b2a8b217bfe816b1f1536269bb257fd295b4ef1ba8246ac` Source locator `/rows/4810/row` | | | | | [Arena text / multi turn](https://benchize.com/benchmarks/lmarena%3Atext%3Amulti_turn.md) | 1,412.72 | 77 / 151 | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1412.7237009107769 \| rating \| reported \| Higher is better \| ### Configuration category multi_turn config text thinkingEnabled true ### Reported statistics lower 1397.1612330244698 rank 132 upper 1428.2861687970842 variance 63.046466984795295 votes 1403 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) Source Arena Original model label DeepSeek-V3.2-Exp (Thinking) Observed 2026-10-22T00:45:04.817Z Evidence SHA-256 `8e027ef69b8de06c4b2a8b217bfe816b1f1536269bb257fd295b4ef1ba8246ac` Source locator `/rows/9447/row` | | | | | [Arena text / industry medicine and healthcare](https://benchize.com/benchmarks/lmarena%3Atext%3Aindustry_medicine_and_healthcare.md) | 1,468.44 | 27 / 151 | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1468.4351088287017 \| rating \| reported \| Higher is better \| ### Configuration category industry_medicine_and_healthcare config text thinkingEnabled true ### Reported statistics lower 1441.002161180329 rank 41 upper 1495.8680564770743 variance 195.90646465458363 votes 443 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) Source Arena Original model label DeepSeek-V3.2-Exp (Thinking) Observed 2026-10-22T00:45:04.817Z Evidence SHA-256 `8e027ef69b8de06c4b2a8b217bfe816b1f1536269bb257fd295b4ef1ba8246ac` Source locator `/rows/6353/row` | | | | | [Arena text style control / industry business and management and financial operations](https://benchize.com/benchmarks/lmarena%3Atext_style_control%3Aindustry_business_and_management_and_financial_operations.md) | 1,407.76 | 87 / 151 | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1407.7630022280457 \| rating \| reported \| Higher is better \| ### Configuration category industry_business_and_management_and_financial_operations config text_style_control thinkingEnabled true ### Reported statistics lower 1394.0408091972988 rank 151 upper 1421.4851952587926 variance 49.01746715562985 votes 1782 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label DeepSeek-V3.2-Exp (Thinking) Observed 2026-10-22T00:45:04.817Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/4433/row` | | | | | [Arena text / industry software and it services](https://benchize.com/benchmarks/lmarena%3Atext%3Aindustry_software_and_it_services.md) | 1,438.04 | 70 / 151 | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1438.0386287416873 \| rating \| reported \| Higher is better \| ### Configuration category industry_software_and_it_services config text thinkingEnabled true ### Reported statistics lower 1427.7012526940257 rank 122 upper 1448.3760047893493 variance 27.817906826204283 votes 3202 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) Source Arena Original model label DeepSeek-V3.2-Exp (Thinking) Observed 2026-10-22T00:45:04.817Z Evidence SHA-256 `8e027ef69b8de06c4b2a8b217bfe816b1f1536269bb257fd295b4ef1ba8246ac` Source locator `/rows/6822/row` | | | | | [Arena text style control / coding](https://benchize.com/benchmarks/lmarena%3Atext_style_control%3Acoding.md) | 1,474.38 | 70 / 151 | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1474.3794356983733 \| rating \| reported \| Higher is better \| ### Configuration category coding config text_style_control thinkingEnabled true ### Reported statistics lower 1461.0949610428515 rank 119 upper 1487.663910353895 variance 45.94016885525597 votes 1930 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label DeepSeek-V3.2-Exp (Thinking) Observed 2026-10-22T00:45:04.817Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/928/row` | | | | | [Arena text / german](https://benchize.com/benchmarks/lmarena%3Atext%3Agerman.md) | 1,436.95 | 46 / 129 | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1436.9525743753752 \| rating \| reported \| Higher is better \| ### Configuration category german config text thinkingEnabled true ### Reported statistics lower 1394.776550053355 rank 77 upper 1479.1285986973953 variance 463.05768476003124 votes 184 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) Source Arena Original model label DeepSeek-V3.2-Exp (Thinking) Observed 2026-10-22T00:45:04.817Z Evidence SHA-256 `8e027ef69b8de06c4b2a8b217bfe816b1f1536269bb257fd295b4ef1ba8246ac` Source locator `/rows/3213/row` | | | | | [Arena text style control / multi turn](https://benchize.com/benchmarks/lmarena%3Atext_style_control%3Amulti_turn.md) | 1,420.14 | 78 / 151 | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1420.1376290361573 \| rating \| reported \| Higher is better \| ### Configuration category multi_turn config text_style_control thinkingEnabled true ### Reported statistics lower 1404.5421620198672 rank 136 upper 1435.7330960524473 variance 63.31412174613473 votes 1403 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label DeepSeek-V3.2-Exp (Thinking) Observed 2026-10-22T00:45:04.817Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/9451/row` | | | | | [Arena text style control / creative writing](https://benchize.com/benchmarks/lmarena%3Atext_style_control%3Acreative_writing.md) | 1,390.49 | 73 / 151 | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1390.4889861352049 \| rating \| reported \| Higher is better \| ### Configuration category creative_writing config text_style_control thinkingEnabled true ### Reported statistics lower 1373.1057790427076 rank 127 upper 1407.8721932277022 variance 78.66175401720014 votes 1193 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label DeepSeek-V3.2-Exp (Thinking) Observed 2026-10-22T00:45:04.817Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/1348/row` | | | | | [Arena text / hard prompts english](https://benchize.com/benchmarks/lmarena%3Atext%3Ahard_prompts_english.md) | 1,443.86 | 62 / 151 | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1443.8576246265197 \| rating \| reported \| Higher is better \| ### Configuration category hard_prompts_english config text thinkingEnabled true ### Reported statistics lower 1430.9634678303878 rank 101 upper 1456.7517814226517 variance 43.280245147387284 votes 2060 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) Source Arena Original model label DeepSeek-V3.2-Exp (Thinking) Observed 2026-10-22T00:45:04.817Z Evidence SHA-256 `8e027ef69b8de06c4b2a8b217bfe816b1f1536269bb257fd295b4ef1ba8246ac` Source locator `/rows/3968/row` | | | | | [Arena text style control / industry legal and government](https://benchize.com/benchmarks/lmarena%3Atext_style_control%3Aindustry_legal_and_government.md) | 1,423.2 | 80 / 151 | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1423.1980859037444 \| rating \| reported \| Higher is better \| ### Configuration category industry_legal_and_government config text_style_control thinkingEnabled true ### Reported statistics lower 1398.1034420020144 rank 139 upper 1448.2927298054744 variance 163.93281353484454 votes 502 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label DeepSeek-V3.2-Exp (Thinking) Observed 2026-10-22T00:45:04.817Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/5246/row` | | | | | [Arena text style control / polish](https://benchize.com/benchmarks/lmarena%3Atext_style_control%3Apolish.md) | 1,429.46 | 57 / 117 | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1429.4596084329698 \| rating \| reported \| Higher is better \| ### Configuration category polish config text_style_control thinkingEnabled true ### Reported statistics lower 1399.954957568028 rank 98 upper 1458.964259297912 variance 226.61297785428897 votes 397 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label DeepSeek-V3.2-Exp (Thinking) Observed 2026-10-22T00:45:04.817Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/10245/row` | | | | | [Arena text / longer query](https://benchize.com/benchmarks/lmarena%3Atext%3Alonger_query.md) | 1,410.83 | 76 / 150 | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1410.8333679527882 \| rating \| reported \| Higher is better \| ### Configuration category longer_query config text thinkingEnabled true ### Reported statistics lower 1398.250488867061 rank 128 upper 1423.4162470385152 variance 41.21581239739049 votes 2110 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) Source Arena Original model label DeepSeek-V3.2-Exp (Thinking) Observed 2026-10-22T00:45:04.817Z Evidence SHA-256 `8e027ef69b8de06c4b2a8b217bfe816b1f1536269bb257fd295b4ef1ba8246ac` Source locator `/rows/8645/row` | | | | | [Arena text style control / industry entertainment and sports and media](https://benchize.com/benchmarks/lmarena%3Atext_style_control%3Aindustry_entertainment_and_sports_and_media.md) | 1,389.4 | 73 / 151 | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1389.4008941251018 \| rating \| reported \| Higher is better \| ### Configuration category industry_entertainment_and_sports_and_media config text_style_control thinkingEnabled true ### Reported statistics lower 1375.072179747726 rank 128 upper 1403.7296085024775 variance 53.446376830173804 votes 1664 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label DeepSeek-V3.2-Exp (Thinking) Observed 2026-10-22T00:45:04.817Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/4820/row` | | | | | [Arena text style control / instruction following](https://benchize.com/benchmarks/lmarena%3Atext_style_control%3Ainstruction_following.md) | 1,415.72 | 73 / 151 | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1415.7160266422811 \| rating \| reported \| Higher is better \| ### Configuration category instruction_following config text_style_control thinkingEnabled true ### Reported statistics lower 1404.2381652426516 rank 120 upper 1427.1938880419107 variance 34.29460224834567 votes 2561 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label DeepSeek-V3.2-Exp (Thinking) Observed 2026-10-22T00:45:04.817Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/7653/row` | | | | | [Arena text / non english](https://benchize.com/benchmarks/lmarena%3Atext%3Anon_english.md) | 1,404.43 | 74 / 151 | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1404.429525548065 \| rating \| reported \| Higher is better \| ### Configuration category non_english config text thinkingEnabled true ### Reported statistics lower 1396.2394397759315 rank 123 upper 1412.6196113201984 variance 17.461466616159754 votes 5109 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) Source Arena Original model label DeepSeek-V3.2-Exp (Thinking) Observed 2026-10-22T00:45:04.817Z Evidence SHA-256 `8e027ef69b8de06c4b2a8b217bfe816b1f1536269bb257fd295b4ef1ba8246ac` Source locator `/rows/9853/row` | | | | | [Arena text / industry legal and government](https://benchize.com/benchmarks/lmarena%3Atext%3Aindustry_legal_and_government.md) | 1,419.03 | 76 / 151 | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1419.0275205718258 \| rating \| reported \| Higher is better \| ### Configuration category industry_legal_and_government config text thinkingEnabled true ### Reported statistics lower 1394.023152787566 rank 131 upper 1444.0318883560853 variance 162.75546282637356 votes 502 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) Source Arena Original model label DeepSeek-V3.2-Exp (Thinking) Observed 2026-10-22T00:45:04.817Z Evidence SHA-256 `8e027ef69b8de06c4b2a8b217bfe816b1f1536269bb257fd295b4ef1ba8246ac` Source locator `/rows/5238/row` | | | | | [Arena text / industry business and management and financial operations](https://benchize.com/benchmarks/lmarena%3Atext%3Aindustry_business_and_management_and_financial_operations.md) | 1,397.1 | 85 / 151 | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1397.0950176397037 \| rating \| reported \| Higher is better \| ### Configuration category industry_business_and_management_and_financial_operations config text thinkingEnabled true ### Reported statistics lower 1383.3723866393686 rank 146 upper 1410.8176486400387 variance 49.020596174795976 votes 1782 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) Source Arena Original model label DeepSeek-V3.2-Exp (Thinking) Observed 2026-10-22T00:45:04.817Z Evidence SHA-256 `8e027ef69b8de06c4b2a8b217bfe816b1f1536269bb257fd295b4ef1ba8246ac` Source locator `/rows/4428/row` | | | | | [Arena text / exclude ties](https://benchize.com/benchmarks/lmarena%3Atext%3Aexclude_ties.md) | 1,414.26 | 63 / 151 | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1414.2647128583976 \| rating \| reported \| Higher is better \| ### Configuration category exclude_ties config text thinkingEnabled true ### Reported statistics lower 1405.2014272091076 rank 107 upper 1423.3279985076877 variance 21.38332091915631 votes 6414 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) Source Arena Original model label DeepSeek-V3.2-Exp (Thinking) Observed 2026-10-22T00:45:04.817Z Evidence SHA-256 `8e027ef69b8de06c4b2a8b217bfe816b1f1536269bb257fd295b4ef1ba8246ac` Source locator `/rows/2160/row` | | | | | [Arena text style control / industry mathematical](https://benchize.com/benchmarks/lmarena%3Atext_style_control%3Aindustry_mathematical.md) | 1,437.67 | 69 / 148 | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1437.670716858513 \| rating \| reported \| Higher is better \| ### Configuration category industry_mathematical config text_style_control thinkingEnabled true ### Reported statistics lower 1408.7819540286987 rank 111 upper 1466.559479688327 variance 217.25096032305245 votes 404 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label DeepSeek-V3.2-Exp (Thinking) Observed 2026-10-22T00:45:04.817Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/6023/row` | | | | | [Arena text / creative writing](https://benchize.com/benchmarks/lmarena%3Atext%3Acreative_writing.md) | 1,388.08 | 70 / 151 | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1388.080073762084 \| rating \| reported \| Higher is better \| ### Configuration category creative_writing config text thinkingEnabled true ### Reported statistics lower 1370.7493947705216 rank 120 upper 1405.4107527536466 variance 78.18707640195849 votes 1193 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) Source Arena Original model label DeepSeek-V3.2-Exp (Thinking) Observed 2026-10-22T00:45:04.817Z Evidence SHA-256 `8e027ef69b8de06c4b2a8b217bfe816b1f1536269bb257fd295b4ef1ba8246ac` Source locator `/rows/1341/row` | | | | | [Arena text style control / industry software and it services](https://benchize.com/benchmarks/lmarena%3Atext_style_control%3Aindustry_software_and_it_services.md) | 1,459.15 | 72 / 151 | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1459.154737424085 \| rating \| reported \| Higher is better \| ### Configuration category industry_software_and_it_services config text_style_control thinkingEnabled true ### Reported statistics lower 1448.786089529385 rank 125 upper 1469.5233853187851 variance 27.986466647803418 votes 3202 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label DeepSeek-V3.2-Exp (Thinking) Observed 2026-10-22T00:45:04.817Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/6825/row` | | | | | [Arena text / spanish](https://benchize.com/benchmarks/lmarena%3Atext%3Aspanish.md) | 1,408.6 | 78 / 134 | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1408.5976399351039 \| rating \| reported \| Higher is better \| ### Configuration category spanish config text thinkingEnabled true ### Reported statistics lower 1375.6534490287913 rank 133 upper 1441.5418308414169 variance 282.52800957410034 votes 311 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) Source Arena Original model label DeepSeek-V3.2-Exp (Thinking) Observed 2026-10-22T00:45:04.817Z Evidence SHA-256 `8e027ef69b8de06c4b2a8b217bfe816b1f1536269bb257fd295b4ef1ba8246ac` Source locator `/rows/10897/row` | | | | | [Arena text style control / industry medicine and healthcare](https://benchize.com/benchmarks/lmarena%3Atext_style_control%3Aindustry_medicine_and_healthcare.md) | 1,474.49 | 43 / 151 | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1474.4874971349693 \| rating \| reported \| Higher is better \| ### Configuration category industry_medicine_and_healthcare config text_style_control thinkingEnabled true ### Reported statistics lower 1447.1118070433652 rank 69 upper 1501.8631872265737 variance 195.08953316233752 votes 443 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label DeepSeek-V3.2-Exp (Thinking) Observed 2026-10-22T00:45:04.817Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/6381/row` | | | | | [Arena text / industry life and physical and social science](https://benchize.com/benchmarks/lmarena%3Atext%3Aindustry_life_and_physical_and_social_science.md) | 1,443.01 | 62 / 151 | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1443.0108691780156 \| rating \| reported \| Higher is better \| ### Configuration category industry_life_and_physical_and_social_science config text thinkingEnabled true ### Reported statistics lower 1427.9727629927156 rank 98 upper 1458.0489753633158 variance 58.86946813593617 votes 1424 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) Source Arena Original model label DeepSeek-V3.2-Exp (Thinking) Observed 2026-10-22T00:45:04.817Z Evidence SHA-256 `8e027ef69b8de06c4b2a8b217bfe816b1f1536269bb257fd295b4ef1ba8246ac` Source locator `/rows/5595/row` | | | | | [Arena text style control / spanish](https://benchize.com/benchmarks/lmarena%3Atext_style_control%3Aspanish.md) | 1,407.76 | 79 / 134 | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1407.7594874672977 \| rating \| reported \| Higher is better \| ### Configuration category spanish config text_style_control thinkingEnabled true ### Reported statistics lower 1374.538792675612 rank 136 upper 1440.9801822589834 variance 287.29048363009986 votes 311 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label DeepSeek-V3.2-Exp (Thinking) Observed 2026-10-22T00:45:04.817Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/10900/row` | | | | | [Arena text style control / chinese](https://benchize.com/benchmarks/lmarena%3Atext_style_control%3Achinese.md) | 1,464.32 | 70 / 146 | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1464.3209612006178 \| rating \| reported \| Higher is better \| ### Configuration category chinese config text_style_control thinkingEnabled true ### Reported statistics lower 1438.1515460442838 rank 116 upper 1490.4903763569516 variance 178.2755774799153 votes 517 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label DeepSeek-V3.2-Exp (Thinking) Observed 2026-10-22T00:45:04.817Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/532/row` | | | | | [Arena text style control / german](https://benchize.com/benchmarks/lmarena%3Atext_style_control%3Agerman.md) | 1,436.33 | 54 / 129 | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1436.328872992037 \| rating \| reported \| Higher is better \| ### Configuration category german config text_style_control thinkingEnabled true ### Reported statistics lower 1393.4827553227185 rank 93 upper 1479.1749906613559 variance 477.88870973798123 votes 184 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label DeepSeek-V3.2-Exp (Thinking) Observed 2026-10-22T00:45:04.817Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/3229/row` | | | | | [Arena text / russian](https://benchize.com/benchmarks/lmarena%3Atext%3Arussian.md) | 1,412.09 | 68 / 150 | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1412.0898898272942 \| rating \| reported \| Higher is better \| ### Configuration category russian config text thinkingEnabled true ### Reported statistics lower 1390.4954321303544 rank 115 upper 1433.684347524234 variance 121.3915402952733 votes 656 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) Source Arena Original model label DeepSeek-V3.2-Exp (Thinking) Observed 2026-10-22T00:45:04.817Z Evidence SHA-256 `8e027ef69b8de06c4b2a8b217bfe816b1f1536269bb257fd295b4ef1ba8246ac` Source locator `/rows/10498/row` | | | | | [Arena text style control / overall](https://benchize.com/benchmarks/lmarena%3Atext_style_control%3Aoverall.md) | 1,425.04 | 72 / 151 | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1425.0402890042067 \| rating \| reported \| Higher is better \| ### Configuration category overall config text_style_control thinkingEnabled true ### Reported statistics lower 1418.4795807731775 rank 123 upper 1431.6009972352358 variance 11.204829858078668 votes 9000 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label DeepSeek-V3.2-Exp (Thinking) Observed 2026-10-22T00:45:04.817Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/122/row` | | | | | [Arena text style control / hard prompts](https://benchize.com/benchmarks/lmarena%3Atext_style_control%3Ahard_prompts.md) | 1,446.41 | 73 / 151 | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1446.4142739852555 \| rating \| reported \| Higher is better \| ### Configuration category hard_prompts config text_style_control thinkingEnabled true ### Reported statistics lower 1437.854975179927 rank 121 upper 1454.973572790584 variance 19.07129542668435 votes 4717 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label DeepSeek-V3.2-Exp (Thinking) Observed 2026-10-22T00:45:04.817Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/3571/row` | | | | | [Arena text style control / exclude ties](https://benchize.com/benchmarks/lmarena%3Atext_style_control%3Aexclude_ties.md) | 1,415.35 | 73 / 151 | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1415.3511282455502 \| rating \| reported \| Higher is better \| ### Configuration category exclude_ties config text_style_control thinkingEnabled true ### Reported statistics lower 1406.1841687847912 rank 126 upper 1424.5180877063092 variance 21.87532124580105 votes 6414 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label DeepSeek-V3.2-Exp (Thinking) Observed 2026-10-22T00:45:04.817Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/2179/row` | | | | | [Arena text / industry writing and literature and language](https://benchize.com/benchmarks/lmarena%3Atext%3Aindustry_writing_and_literature_and_language.md) | 1,396.03 | 73 / 151 | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1396.0277155119243 \| rating \| reported \| Higher is better \| ### Configuration category industry_writing_and_literature_and_language config text thinkingEnabled true ### Reported statistics lower 1383.1088927963258 rank 120 upper 1408.9465382275225 variance 43.44598970005434 votes 2097 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) Source Arena Original model label DeepSeek-V3.2-Exp (Thinking) Observed 2026-10-22T00:45:04.817Z Evidence SHA-256 `8e027ef69b8de06c4b2a8b217bfe816b1f1536269bb257fd295b4ef1ba8246ac` Source locator `/rows/7237/row` | | | | | [Arena text style control / english](https://benchize.com/benchmarks/lmarena%3Atext_style_control%3Aenglish.md) | 1,439.62 | 69 / 151 | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1439.6191581721507 \| rating \| reported \| Higher is better \| ### Configuration category english config text_style_control thinkingEnabled true ### Reported statistics lower 1430.1058582452865 rank 116 upper 1449.1324580990147 variance 23.559506875598455 votes 3891 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label DeepSeek-V3.2-Exp (Thinking) Observed 2026-10-22T00:45:04.817Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/1752/row` | | | | | [Arena text / coding](https://benchize.com/benchmarks/lmarena%3Atext%3Acoding.md) | 1,438.45 | 70 / 151 | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1438.4488460230182 \| rating \| reported \| Higher is better \| ### Configuration category coding config text thinkingEnabled true ### Reported statistics lower 1425.1797429346077 rank 119 upper 1451.7179491114287 variance 45.83391492377026 votes 1930 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) Source Arena Original model label DeepSeek-V3.2-Exp (Thinking) Observed 2026-10-22T00:45:04.817Z Evidence SHA-256 `8e027ef69b8de06c4b2a8b217bfe816b1f1536269bb257fd295b4ef1ba8246ac` Source locator `/rows/928/row` | | | | | [Arena text style control / industry life and physical and social science](https://benchize.com/benchmarks/lmarena%3Atext_style_control%3Aindustry_life_and_physical_and_social_science.md) | 1,450.1 | 69 / 151 | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1450.09877378801 \| rating \| reported \| Higher is better \| ### Configuration category industry_life_and_physical_and_social_science config text_style_control thinkingEnabled true ### Reported statistics lower 1435.1277252676832 rank 113 upper 1465.0698223083368 variance 58.34561927113879 votes 1424 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label DeepSeek-V3.2-Exp (Thinking) Observed 2026-10-22T00:45:04.817Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/5610/row` | | | | | [Arena text / math](https://benchize.com/benchmarks/lmarena%3Atext%3Amath.md) | 1,421.75 | 72 / 149 | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1421.7543942796601 \| rating \| reported \| Higher is better \| ### Configuration category math config text thinkingEnabled true ### Reported statistics lower 1395.2246255931389 rank 119 upper 1448.2841629661814 variance 183.21909967347935 votes 477 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) Source Arena Original model label DeepSeek-V3.2-Exp (Thinking) Observed 2026-10-22T00:45:04.817Z Evidence SHA-256 `8e027ef69b8de06c4b2a8b217bfe816b1f1536269bb257fd295b4ef1ba8246ac` Source locator `/rows/9031/row` | | | | | [Arena text / instruction following](https://benchize.com/benchmarks/lmarena%3Atext%3Ainstruction_following.md) | 1,400.49 | 77 / 151 | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1400.4936783561157 \| rating \| reported \| Higher is better \| ### Configuration category instruction_following config text thinkingEnabled true ### Reported statistics lower 1389.036471569153 rank 127 upper 1411.950885143078 variance 34.17128582820499 votes 2561 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) Source Arena Original model label DeepSeek-V3.2-Exp (Thinking) Observed 2026-10-22T00:45:04.817Z Evidence SHA-256 `8e027ef69b8de06c4b2a8b217bfe816b1f1536269bb257fd295b4ef1ba8246ac` Source locator `/rows/7660/row` | | | | | [Arena text / industry mathematical](https://benchize.com/benchmarks/lmarena%3Atext%3Aindustry_mathematical.md) | 1,433.36 | 70 / 148 | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1433.363845795835 \| rating \| reported \| Higher is better \| ### Configuration category industry_mathematical config text thinkingEnabled true ### Reported statistics lower 1404.3118392370748 rank 110 upper 1462.4158523545952 variance 219.71316744135788 votes 404 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) Source Arena Original model label DeepSeek-V3.2-Exp (Thinking) Observed 2026-10-22T00:45:04.817Z Evidence SHA-256 `8e027ef69b8de06c4b2a8b217bfe816b1f1536269bb257fd295b4ef1ba8246ac` Source locator `/rows/6022/row` | | | | | [Arena text / expert](https://benchize.com/benchmarks/lmarena%3Atext%3Aexpert.md) | 1,422.23 | 79 / 148 | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1422.2310443186484 \| rating \| reported \| Higher is better \| ### Configuration category expert config text thinkingEnabled true ### Reported statistics lower 1394.212852936308 rank 130 upper 1450.249235700989 variance 204.35440934796043 votes 426 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) Source Arena Original model label DeepSeek-V3.2-Exp (Thinking) Observed 2026-10-22T00:45:04.817Z Evidence SHA-256 `8e027ef69b8de06c4b2a8b217bfe816b1f1536269bb257fd295b4ef1ba8246ac` Source locator `/rows/2600/row` | | | | --- Cite as: DeepSeek V3.2 ExpThinking — Benchize, https://benchize.com/models/deepseek-v3-2-exp-thinking (retrieved 2026-10-22)