# DeepSeek V3.2Thinking

> Source: Benchize (https://benchize.com) — https://benchize.com/models/deepseek-v3-2-thinking. When citing or reusing this content, credit "Benchize" and link to https://benchize.com/models/deepseek-v3-2-thinking.

DeepSeek

Canonical URL: https://benchize.com/models/deepseek-v3-2-thinking
Last updated: Thu, 22 Oct 2026 07:10:12 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 / exclude ties](https://benchize.com/benchmarks/lmarena%3Atext_style_control%3Aexclude_ties.md) | 1,411.72 | 93 / 173 |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1411.7194373089767 \| rating \| reported \| Higher is better \| ### Configuration category exclude_ties config text_style_control thinkingEnabled true ### Reported statistics lower 1406.6340732012345 rank 131 upper 1416.8048014167189 variance 6.732059177361913 votes 29437 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label DeepSeek-V3.2 (Thinking) Observed 2026-10-22T06:45:03.380Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/2184/row` |  |  |  |
| [Arena text / korean](https://benchize.com/benchmarks/lmarena%3Atext%3Akorean.md) | 1,363.31 | 77 / 144 |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1363.3092489927706 \| rating \| reported \| Higher is better \| ### Configuration category korean config text thinkingEnabled true ### Reported statistics lower 1340.5128574179162 rank 116 upper 1386.1056405676252 variance 135.28076001611166 votes 698 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) Source Arena Original model label DeepSeek-V3.2 (Thinking) Observed 2026-10-22T06:45:03.380Z Evidence SHA-256 `8e027ef69b8de06c4b2a8b217bfe816b1f1536269bb257fd295b4ef1ba8246ac` Source locator `/rows/8349/row` |  |  |  |
| [Arena text style control / industry legal and government](https://benchize.com/benchmarks/lmarena%3Atext_style_control%3Aindustry_legal_and_government.md) | 1,429.2 | 93 / 173 |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1429.2010880967293 \| rating \| reported \| Higher is better \| ### Configuration category industry_legal_and_government config text_style_control thinkingEnabled true ### Reported statistics lower 1418.6771419683603 rank 130 upper 1439.7250342250984 variance 28.831089250828256 votes 3080 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label DeepSeek-V3.2 (Thinking) Observed 2026-10-22T06:45:03.380Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/5237/row` |  |  |  |
| [Arena text style control / industry mathematical](https://benchize.com/benchmarks/lmarena%3Atext_style_control%3Aindustry_mathematical.md) | 1,450.42 | 71 / 169 |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1450.4169493996 \| rating \| reported \| Higher is better \| ### Configuration category industry_mathematical config text_style_control thinkingEnabled true ### Reported statistics lower 1437.0863654123546 rank 93 upper 1463.7475333868456 variance 46.25963149304134 votes 1968 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label DeepSeek-V3.2 (Thinking) Observed 2026-10-22T06:45:03.380Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/6005/row` |  |  |  |
| [Arena text style control / hard prompts english](https://benchize.com/benchmarks/lmarena%3Atext_style_control%3Ahard_prompts_english.md) | 1,460.19 | 79 / 173 |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1460.1897788519755 \| rating \| reported \| Higher is better \| ### Configuration category hard_prompts_english config text_style_control thinkingEnabled true ### Reported statistics lower 1453.7302187832088 rank 108 upper 1466.6493389207421 variance 10.861997545626217 votes 9597 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label DeepSeek-V3.2 (Thinking) Observed 2026-10-22T06:45:03.380Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/3975/row` |  |  |  |
| [Arena text / industry legal and government](https://benchize.com/benchmarks/lmarena%3Atext%3Aindustry_legal_and_government.md) | 1,418.95 | 92 / 173 |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1418.953493884722 \| rating \| reported \| Higher is better \| ### Configuration category industry_legal_and_government config text thinkingEnabled true ### Reported statistics lower 1408.4868116522152 rank 132 upper 1429.420176117229 variance 28.518185946994034 votes 3080 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) Source Arena Original model label DeepSeek-V3.2 (Thinking) Observed 2026-10-22T06:45:03.380Z Evidence SHA-256 `8e027ef69b8de06c4b2a8b217bfe816b1f1536269bb257fd295b4ef1ba8246ac` Source locator `/rows/5239/row` |  |  |  |
| [Arena text / spanish](https://benchize.com/benchmarks/lmarena%3Atext%3Aspanish.md) | 1,415.53 | 83 / 155 |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1415.5303613426872 \| rating \| reported \| Higher is better \| ### Configuration category spanish config text thinkingEnabled true ### Reported statistics lower 1399.3922211680574 rank 121 upper 1431.6685015173166 variance 67.79704806231243 votes 1364 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) Source Arena Original model label DeepSeek-V3.2 (Thinking) Observed 2026-10-22T06:45:03.380Z Evidence SHA-256 `8e027ef69b8de06c4b2a8b217bfe816b1f1536269bb257fd295b4ef1ba8246ac` Source locator `/rows/10885/row` |  |  |  |
| [Arena webdev / webdev](https://benchize.com/benchmarks/lmarena%3Awebdev%3Awebdev.md) | 1,362.39 | 81 / 107 |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1362.3917105699861 \| rating \| reported \| Higher is better \| ### Configuration category webdev config webdev thinkingEnabled true ### Reported statistics lower 1353.2899901145347 rank 111 upper 1371.4934310254375 variance 21.56506658431802 votes 6914 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/webdev/latest) Source Arena Original model label DeepSeek-V3.2 (Thinking) Observed 2026-10-22T06:45:03.380Z Evidence SHA-256 `f82507859808110820a4ab6df15561b8864137ddefc1f6fb0c552af2e58ea738` Source locator `/rows/322/row` |  |  |  |
| [Arena text / hard prompts](https://benchize.com/benchmarks/lmarena%3Atext%3Ahard_prompts.md) | 1,430.51 | 78 / 173 |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1430.5114022538273 \| rating \| reported \| Higher is better \| ### Configuration category hard_prompts config text thinkingEnabled true ### Reported statistics lower 1425.9416469450762 rank 110 upper 1435.0811575625785 variance 5.436128449266248 votes 23323 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) Source Arena Original model label DeepSeek-V3.2 (Thinking) Observed 2026-10-22T06:45:03.380Z Evidence SHA-256 `8e027ef69b8de06c4b2a8b217bfe816b1f1536269bb257fd295b4ef1ba8246ac` Source locator `/rows/3560/row` |  |  |  |
| [Arena text style control / russian](https://benchize.com/benchmarks/lmarena%3Atext_style_control%3Arussian.md) | 1,406.92 | 97 / 172 |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1406.9230026082205 \| rating \| reported \| Higher is better \| ### Configuration category russian config text_style_control thinkingEnabled true ### Reported statistics lower 1398.8009281052282 rank 140 upper 1415.0450771112123 variance 17.17266728899432 votes 5421 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label DeepSeek-V3.2 (Thinking) Observed 2026-10-22T06:45:03.380Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/10523/row` |  |  |  |
| [Arena text style control / coding](https://benchize.com/benchmarks/lmarena%3Atext_style_control%3Acoding.md) | 1,475.35 | 84 / 173 |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1475.3487434105637 \| rating \| reported \| Higher is better \| ### Configuration category coding config text_style_control thinkingEnabled true ### Reported statistics lower 1468.6888210696009 rank 117 upper 1482.0086657515267 variance 11.546281675262641 votes 8880 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label DeepSeek-V3.2 (Thinking) Observed 2026-10-22T06:45:03.380Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/926/row` |  |  |  |
| [Arena text style control / instruction following](https://benchize.com/benchmarks/lmarena%3Atext_style_control%3Ainstruction_following.md) | 1,419.17 | 83 / 173 |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1419.1744065901437 \| rating \| reported \| Higher is better \| ### Configuration category instruction_following config text_style_control thinkingEnabled true ### Reported statistics lower 1413.278015529509 rank 113 upper 1425.070797650778 variance 9.05057926239797 votes 11719 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label DeepSeek-V3.2 (Thinking) Observed 2026-10-22T06:45:03.380Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/7646/row` |  |  |  |
| [Arena text style control / overall](https://benchize.com/benchmarks/lmarena%3Atext_style_control%3Aoverall.md) | 1,422.39 | 90 / 173 |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1422.3872869278875 \| rating \| reported \| Higher is better \| ### Configuration category overall config text_style_control thinkingEnabled true ### Reported statistics lower 1418.813750453109 rank 128 upper 1425.9608234026662 variance 3.3243003589625597 votes 42042 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label DeepSeek-V3.2 (Thinking) Observed 2026-10-22T06:45:03.380Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/127/row` |  |  |  |
| [Arena text style control / chinese](https://benchize.com/benchmarks/lmarena%3Atext_style_control%3Achinese.md) | 1,454.36 | 92 / 168 |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1454.3599824622513 \| rating \| reported \| Higher is better \| ### Configuration category chinese config text_style_control thinkingEnabled true ### Reported statistics lower 1443.6646849210392 rank 131 upper 1465.0552800034634 variance 29.777590971126806 votes 3129 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label DeepSeek-V3.2 (Thinking) Observed 2026-10-22T06:45:03.380Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/547/row` |  |  |  |
| [Arena text / chinese](https://benchize.com/benchmarks/lmarena%3Atext%3Achinese.md) | 1,447.89 | 92 / 168 |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1447.8931527761022 \| rating \| reported \| Higher is better \| ### Configuration category chinese config text thinkingEnabled true ### Reported statistics lower 1437.308057319191 rank 130 upper 1458.4782482330136 variance 29.167108398594706 votes 3129 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) Source Arena Original model label DeepSeek-V3.2 (Thinking) Observed 2026-10-22T06:45:03.380Z Evidence SHA-256 `8e027ef69b8de06c4b2a8b217bfe816b1f1536269bb257fd295b4ef1ba8246ac` Source locator `/rows/546/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) | 1,422.8 | 87 / 173 |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1422.8036537446171 \| rating \| reported \| Higher is better \| ### Configuration category industry_business_and_management_and_financial_operations config text_style_control thinkingEnabled true ### Reported statistics lower 1415.9477595426317 rank 121 upper 1429.6595479466023 variance 12.235790490739335 votes 8098 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label DeepSeek-V3.2 (Thinking) Observed 2026-10-22T06:45:03.380Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/4403/row` |  |  |  |
| [Arena text / hard prompts english](https://benchize.com/benchmarks/lmarena%3Atext%3Ahard_prompts_english.md) | 1,445.67 | 70 / 173 |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1445.66515141717 \| rating \| reported \| Higher is better \| ### Configuration category hard_prompts_english config text thinkingEnabled true ### Reported statistics lower 1439.2397708450558 rank 95 upper 1452.090531989284 variance 10.747353394521618 votes 9597 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) Source Arena Original model label DeepSeek-V3.2 (Thinking) Observed 2026-10-22T06:45:03.380Z Evidence SHA-256 `8e027ef69b8de06c4b2a8b217bfe816b1f1536269bb257fd295b4ef1ba8246ac` Source locator `/rows/3962/row` |  |  |  |
| [Arena text / instruction following](https://benchize.com/benchmarks/lmarena%3Atext%3Ainstruction_following.md) | 1,408.37 | 79 / 173 |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1408.3663079317014 \| rating \| reported \| Higher is better \| ### Configuration category instruction_following config text thinkingEnabled true ### Reported statistics lower 1402.49655775261 rank 108 upper 1414.2360581107928 variance 8.968979956088038 votes 11719 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) Source Arena Original model label DeepSeek-V3.2 (Thinking) Observed 2026-10-22T06:45:03.380Z Evidence SHA-256 `8e027ef69b8de06c4b2a8b217bfe816b1f1536269bb257fd295b4ef1ba8246ac` Source locator `/rows/7641/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) | 1,437.24 | 95 / 173 |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1437.2397464891133 \| rating \| reported \| Higher is better \| ### Configuration category industry_life_and_physical_and_social_science config text_style_control thinkingEnabled true ### Reported statistics lower 1429.8288305154406 rank 133 upper 1444.650662462786 variance 14.29708819810119 votes 6861 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label DeepSeek-V3.2 (Thinking) Observed 2026-10-22T06:45:03.380Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/5630/row` |  |  |  |
| [Arena text / industry mathematical](https://benchize.com/benchmarks/lmarena%3Atext%3Aindustry_mathematical.md) | 1,439.61 | 74 / 169 |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1439.6090067111693 \| rating \| reported \| Higher is better \| ### Configuration category industry_mathematical config text thinkingEnabled true ### Reported statistics lower 1426.3239896316918 rank 95 upper 1452.8940237906468 variance 45.94392053644806 votes 1968 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) Source Arena Original model label DeepSeek-V3.2 (Thinking) Observed 2026-10-22T06:45:03.380Z Evidence SHA-256 `8e027ef69b8de06c4b2a8b217bfe816b1f1536269bb257fd295b4ef1ba8246ac` Source locator `/rows/6007/row` |  |  |  |
| [Arena text / russian](https://benchize.com/benchmarks/lmarena%3Atext%3Arussian.md) | 1,407.04 | 88 / 172 |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1407.0445884625744 \| rating \| reported \| Higher is better \| ### Configuration category russian config text thinkingEnabled true ### Reported statistics lower 1398.9907830671937 rank 123 upper 1415.0983938579552 variance 16.8851950194649 votes 5421 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) Source Arena Original model label DeepSeek-V3.2 (Thinking) Observed 2026-10-22T06:45:03.380Z Evidence SHA-256 `8e027ef69b8de06c4b2a8b217bfe816b1f1536269bb257fd295b4ef1ba8246ac` Source locator `/rows/10506/row` |  |  |  |
| [Arena text / japanese](https://benchize.com/benchmarks/lmarena%3Atext%3Ajapanese.md) | 1,374.2 | 76 / 138 |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1374.1956511243927 \| rating \| reported \| Higher is better \| ### Configuration category japanese config text thinkingEnabled true ### Reported statistics lower 1344.8332250199187 rank 109 upper 1403.558077228867 variance 224.43350481755692 votes 385 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) Source Arena Original model label DeepSeek-V3.2 (Thinking) Observed 2026-10-22T06:45:03.380Z Evidence SHA-256 `8e027ef69b8de06c4b2a8b217bfe816b1f1536269bb257fd295b4ef1ba8246ac` Source locator `/rows/8059/row` |  |  |  |
| [Arena text / creative writing](https://benchize.com/benchmarks/lmarena%3Atext%3Acreative_writing.md) | 1,389.24 | 83 / 173 |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1389.2370040088015 \| rating \| reported \| Higher is better \| ### Configuration category creative_writing config text thinkingEnabled true ### Reported statistics lower 1381.5888945325748 rank 118 upper 1396.8851134850283 variance 15.226918025319629 votes 6410 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) Source Arena Original model label DeepSeek-V3.2 (Thinking) Observed 2026-10-22T06:45:03.380Z Evidence SHA-256 `8e027ef69b8de06c4b2a8b217bfe816b1f1536269bb257fd295b4ef1ba8246ac` Source locator `/rows/1339/row` |  |  |  |
| [Arena text style control / expert](https://benchize.com/benchmarks/lmarena%3Atext_style_control%3Aexpert.md) | 1,453.46 | 83 / 170 |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1453.4574555857305 \| rating \| reported \| Higher is better \| ### Configuration category expert config text_style_control thinkingEnabled true ### Reported statistics lower 1442.357149037476 rank 110 upper 1464.557762133985 variance 32.075524225705344 votes 2878 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label DeepSeek-V3.2 (Thinking) Observed 2026-10-22T06:45:03.380Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/2580/row` |  |  |  |
| [Arena webdev / webdev-react](https://benchize.com/benchmarks/lmarena%3Awebdev%3Awebdev-react.md) | 1,349.68 | 81 / 97 |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1349.6829539474327 \| rating \| reported \| Higher is better \| ### Configuration category webdev-react config webdev thinkingEnabled true ### Reported statistics lower 1338.034937930032 rank 110 upper 1361.3309699648335 variance 35.318946128156874 votes 3629 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/webdev/latest) Source Arena Original model label DeepSeek-V3.2 (Thinking) Observed 2026-10-22T06:45:03.380Z Evidence SHA-256 `f82507859808110820a4ab6df15561b8864137ddefc1f6fb0c552af2e58ea738` Source locator `/rows/616/row` |  |  |  |
| [Arena text style control / industry software and it services](https://benchize.com/benchmarks/lmarena%3Atext_style_control%3Aindustry_software_and_it_services.md) | 1,464.17 | 84 / 173 |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1464.1718120715361 \| rating \| reported \| Higher is better \| ### Configuration category industry_software_and_it_services config text_style_control thinkingEnabled true ### Reported statistics lower 1458.6797730915898 rank 119 upper 1469.6638510514822 variance 7.851832745091708 votes 14296 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label DeepSeek-V3.2 (Thinking) Observed 2026-10-22T06:45:03.380Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/6819/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) | 1,388.55 | 90 / 173 |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1388.5463721137426 \| rating \| reported \| Higher is better \| ### Configuration category industry_entertainment_and_sports_and_media config text_style_control thinkingEnabled true ### Reported statistics lower 1381.5028097348084 rank 130 upper 1395.5899344926765 variance 12.914825669528442 votes 7747 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label DeepSeek-V3.2 (Thinking) Observed 2026-10-22T06:45:03.380Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/4822/row` |  |  |  |
| [Arena text / multi turn](https://benchize.com/benchmarks/lmarena%3Atext%3Amulti_turn.md) | 1,423.83 | 80 / 173 |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1423.8281995031623 \| rating \| reported \| Higher is better \| ### Configuration category multi_turn config text thinkingEnabled true ### Reported statistics lower 1416.3993731641845 rank 112 upper 1431.2570258421404 variance 14.366276810620498 votes 6992 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) Source Arena Original model label DeepSeek-V3.2 (Thinking) Observed 2026-10-22T06:45:03.380Z Evidence SHA-256 `8e027ef69b8de06c4b2a8b217bfe816b1f1536269bb257fd295b4ef1ba8246ac` Source locator `/rows/9427/row` |  |  |  |
| [Arena text style control / french](https://benchize.com/benchmarks/lmarena%3Atext_style_control%3Afrench.md) | 1,430.2 | 95 / 152 |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1430.1988688118076 \| rating \| reported \| Higher is better \| ### Configuration category french config text_style_control thinkingEnabled true ### Reported statistics lower 1411.0531130148047 rank 133 upper 1449.3446246088101 variance 95.42207326648537 votes 1046 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label DeepSeek-V3.2 (Thinking) Observed 2026-10-22T06:45:03.380Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/2970/row` |  |  |  |
| [Arena text style control / math](https://benchize.com/benchmarks/lmarena%3Atext_style_control%3Amath.md) | 1,428.52 | 82 / 170 |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1428.5165926384566 \| rating \| reported \| Higher is better \| ### Configuration category math config text_style_control thinkingEnabled true ### Reported statistics lower 1417.0753066368825 rank 112 upper 1439.957878640031 variance 34.076383863504596 votes 2633 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label DeepSeek-V3.2 (Thinking) Observed 2026-10-22T06:45:03.380Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/9024/row` |  |  |  |
| [Arena text style control / hard prompts](https://benchize.com/benchmarks/lmarena%3Atext_style_control%3Ahard_prompts.md) | 1,445.89 | 89 / 173 |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1445.8897405900339 \| rating \| reported \| Higher is better \| ### Configuration category hard_prompts config text_style_control thinkingEnabled true ### Reported statistics lower 1441.2925449203497 rank 123 upper 1450.4869362597183 variance 5.501609938264247 votes 23323 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label DeepSeek-V3.2 (Thinking) Observed 2026-10-22T06:45:03.380Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/3573/row` |  |  |  |
| [Arena text / exclude ties](https://benchize.com/benchmarks/lmarena%3Atext%3Aexclude_ties.md) | 1,406.98 | 84 / 173 |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1406.9813571995417 \| rating \| reported \| Higher is better \| ### Configuration category exclude_ties config text thinkingEnabled true ### Reported statistics lower 1401.9829479934654 rank 121 upper 1411.979766405618 variance 6.503803830148669 votes 29437 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) Source Arena Original model label DeepSeek-V3.2 (Thinking) Observed 2026-10-22T06:45:03.380Z Evidence SHA-256 `8e027ef69b8de06c4b2a8b217bfe816b1f1536269bb257fd295b4ef1ba8246ac` Source locator `/rows/2174/row` |  |  |  |
| [Arena webdev / overall](https://benchize.com/benchmarks/lmarena%3Awebdev%3Aoverall.md) | 1,362.39 | 81 / 107 |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1362.3917105699861 \| rating \| reported \| Higher is better \| ### Configuration category overall config webdev thinkingEnabled true ### Reported statistics lower 1353.2899901145347 rank 111 upper 1371.4934310254375 variance 21.56506658431802 votes 6914 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/webdev/latest) Source Arena Original model label DeepSeek-V3.2 (Thinking) Observed 2026-10-22T06:45:03.380Z Evidence SHA-256 `f82507859808110820a4ab6df15561b8864137ddefc1f6fb0c552af2e58ea738` Source locator `/rows/110/row` |  |  |  |
| [Arena text / industry life and physical and social science](https://benchize.com/benchmarks/lmarena%3Atext%3Aindustry_life_and_physical_and_social_science.md) | 1,425.72 | 93 / 173 |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1425.7159445752702 \| rating \| reported \| Higher is better \| ### Configuration category industry_life_and_physical_and_social_science config text thinkingEnabled true ### Reported statistics lower 1418.3805397499953 rank 134 upper 1433.0513494005452 variance 14.007221334978377 votes 6861 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) Source Arena Original model label DeepSeek-V3.2 (Thinking) Observed 2026-10-22T06:45:03.380Z Evidence SHA-256 `8e027ef69b8de06c4b2a8b217bfe816b1f1536269bb257fd295b4ef1ba8246ac` Source locator `/rows/5631/row` |  |  |  |
| [Arena webdev / webdev-html](https://benchize.com/benchmarks/lmarena%3Awebdev%3Awebdev-html.md) | 1,370.59 | 80 / 106 |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1370.591057839043 \| rating \| reported \| Higher is better \| ### Configuration category webdev-html config webdev thinkingEnabled true ### Reported statistics lower 1356.716144674325 rank 109 upper 1384.4659710037608 variance 50.11461122305518 votes 3269 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/webdev/latest) Source Arena Original model label DeepSeek-V3.2 (Thinking) Observed 2026-10-22T06:45:03.380Z Evidence SHA-256 `f82507859808110820a4ab6df15561b8864137ddefc1f6fb0c552af2e58ea738` Source locator `/rows/468/row` |  |  |  |
| [Arena text / french](https://benchize.com/benchmarks/lmarena%3Atext%3Afrench.md) | 1,422.37 | 91 / 152 |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1422.3684858363786 \| rating \| reported \| Higher is better \| ### Configuration category french config text thinkingEnabled true ### Reported statistics lower 1403.5609064652197 rank 128 upper 1441.1760652075372 variance 92.08091465068046 votes 1046 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) Source Arena Original model label DeepSeek-V3.2 (Thinking) Observed 2026-10-22T06:45:03.380Z Evidence SHA-256 `8e027ef69b8de06c4b2a8b217bfe816b1f1536269bb257fd295b4ef1ba8246ac` Source locator `/rows/2965/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) | 1,403.36 | 89 / 173 |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1403.3582122031285 \| rating \| reported \| Higher is better \| ### Configuration category industry_writing_and_literature_and_language config text_style_control thinkingEnabled true ### Reported statistics lower 1396.935310104152 rank 123 upper 1409.781114302105 variance 10.739063803261843 votes 9736 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label DeepSeek-V3.2 (Thinking) Observed 2026-10-22T06:45:03.380Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/7240/row` |  |  |  |
| [Arena text / coding](https://benchize.com/benchmarks/lmarena%3Atext%3Acoding.md) | 1,453.32 | 72 / 173 |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1453.315673059699 \| rating \| reported \| Higher is better \| ### Configuration category coding config text thinkingEnabled true ### Reported statistics lower 1446.6905578988953 rank 97 upper 1459.9407882205028 variance 11.425906912619121 votes 8880 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) Source Arena Original model label DeepSeek-V3.2 (Thinking) Observed 2026-10-22T06:45:03.380Z Evidence SHA-256 `8e027ef69b8de06c4b2a8b217bfe816b1f1536269bb257fd295b4ef1ba8246ac` Source locator `/rows/906/row` |  |  |  |
| [Arena text / polish](https://benchize.com/benchmarks/lmarena%3Atext%3Apolish.md) | 1,419.22 | 73 / 137 |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1419.2179961698184 \| rating \| reported \| Higher is better \| ### Configuration category polish config text thinkingEnabled true ### Reported statistics lower 1402.0967731344515 rank 101 upper 1436.3392192051854 variance 76.30858273103004 votes 1119 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) Source Arena Original model label DeepSeek-V3.2 (Thinking) Observed 2026-10-22T06:45:03.380Z Evidence SHA-256 `8e027ef69b8de06c4b2a8b217bfe816b1f1536269bb257fd295b4ef1ba8246ac` Source locator `/rows/10248/row` |  |  |  |
| [Arena text / german](https://benchize.com/benchmarks/lmarena%3Atext%3Agerman.md) | 1,413.22 | 75 / 149 |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1413.2151107578757 \| rating \| reported \| Higher is better \| ### Configuration category german config text thinkingEnabled true ### Reported statistics lower 1392.138239510888 rank 106 upper 1434.2919820048633 variance 115.64213552647824 votes 748 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) Source Arena Original model label DeepSeek-V3.2 (Thinking) Observed 2026-10-22T06:45:03.380Z Evidence SHA-256 `8e027ef69b8de06c4b2a8b217bfe816b1f1536269bb257fd295b4ef1ba8246ac` Source locator `/rows/3242/row` |  |  |  |
| [Arena text style control / spanish](https://benchize.com/benchmarks/lmarena%3Atext_style_control%3Aspanish.md) | 1,412.72 | 89 / 155 |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1412.7217939477814 \| rating \| reported \| Higher is better \| ### Configuration category spanish config text_style_control thinkingEnabled true ### Reported statistics lower 1396.6444435509447 rank 126 upper 1428.799144344618 variance 67.28724889362715 votes 1364 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label DeepSeek-V3.2 (Thinking) Observed 2026-10-22T06:45:03.380Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/10890/row` |  |  |  |
| [Arena text / industry entertainment and sports and media](https://benchize.com/benchmarks/lmarena%3Atext%3Aindustry_entertainment_and_sports_and_media.md) | 1,386.62 | 84 / 173 |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1386.6177626526742 \| rating \| reported \| Higher is better \| ### Configuration category industry_entertainment_and_sports_and_media config text thinkingEnabled true ### Reported statistics lower 1379.6271758744076 rank 120 upper 1393.6083494309405 variance 12.721287871477074 votes 7747 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) Source Arena Original model label DeepSeek-V3.2 (Thinking) Observed 2026-10-22T06:45:03.380Z Evidence SHA-256 `8e027ef69b8de06c4b2a8b217bfe816b1f1536269bb257fd295b4ef1ba8246ac` Source locator `/rows/4812/row` |  |  |  |
| [Arena text / longer query](https://benchize.com/benchmarks/lmarena%3Atext%3Alonger_query.md) | 1,425.93 | 76 / 172 |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1425.9273958045035 \| rating \| reported \| Higher is better \| ### Configuration category longer_query config text thinkingEnabled true ### Reported statistics lower 1419.9813997451083 rank 102 upper 1431.8733918638986 variance 9.20350075025782 votes 11724 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) Source Arena Original model label DeepSeek-V3.2 (Thinking) Observed 2026-10-22T06:45:03.380Z Evidence SHA-256 `8e027ef69b8de06c4b2a8b217bfe816b1f1536269bb257fd295b4ef1ba8246ac` Source locator `/rows/8619/row` |  |  |  |
| [Arena text / industry medicine and healthcare](https://benchize.com/benchmarks/lmarena%3Atext%3Aindustry_medicine_and_healthcare.md) | 1,420.3 | 93 / 173 |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1420.2990055620535 \| rating \| reported \| Higher is better \| ### Configuration category industry_medicine_and_healthcare config text thinkingEnabled true ### Reported statistics lower 1409.212808688832 rank 131 upper 1431.3852024352755 variance 31.994033217210635 votes 2825 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) Source Arena Original model label DeepSeek-V3.2 (Thinking) Observed 2026-10-22T06:45:03.380Z Evidence SHA-256 `8e027ef69b8de06c4b2a8b217bfe816b1f1536269bb257fd295b4ef1ba8246ac` Source locator `/rows/6443/row` |  |  |  |
| [Arena text / overall](https://benchize.com/benchmarks/lmarena%3Atext.md) | 1,419.84 | 83 / 173 |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1419.8352648569082 \| rating \| reported \| Higher is better \| ### Configuration category overall config text thinkingEnabled true ### Reported statistics lower 1416.2822381060748 rank 116 upper 1423.3882916077416 variance 3.286251312686708 votes 42042 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) Source Arena Original model label DeepSeek-V3.2 (Thinking) Observed 2026-10-22T06:45:03.380Z Evidence SHA-256 `8e027ef69b8de06c4b2a8b217bfe816b1f1536269bb257fd295b4ef1ba8246ac` Source locator `/rows/115/row` |  |  |  |
| [Arena text style control / multi turn](https://benchize.com/benchmarks/lmarena%3Atext_style_control%3Amulti_turn.md) | 1,427.59 | 88 / 173 |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1427.5912972246083 \| rating \| reported \| Higher is better \| ### Configuration category multi_turn config text_style_control thinkingEnabled true ### Reported statistics lower 1420.1302788311568 rank 124 upper 1435.0523156180598 variance 14.491056149695071 votes 6992 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label DeepSeek-V3.2 (Thinking) Observed 2026-10-22T06:45:03.380Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/9439/row` |  |  |  |
| [Arena text style control / polish](https://benchize.com/benchmarks/lmarena%3Atext_style_control%3Apolish.md) | 1,418.52 | 78 / 137 |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1418.5184329545648 \| rating \| reported \| Higher is better \| ### Configuration category polish config text_style_control thinkingEnabled true ### Reported statistics lower 1401.124911305064 rank 112 upper 1435.9119546040656 variance 78.75513170722776 votes 1119 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label DeepSeek-V3.2 (Thinking) Observed 2026-10-22T06:45:03.380Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/10259/row` |  |  |  |
| [Arena text / math](https://benchize.com/benchmarks/lmarena%3Atext%3Amath.md) | 1,422.08 | 85 / 170 |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1422.0817793630465 \| rating \| reported \| Higher is better \| ### Configuration category math config text thinkingEnabled true ### Reported statistics lower 1410.6577945121526 rank 117 upper 1433.5057642139404 variance 33.973403325424975 votes 2633 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) Source Arena Original model label DeepSeek-V3.2 (Thinking) Observed 2026-10-22T06:45:03.380Z Evidence SHA-256 `8e027ef69b8de06c4b2a8b217bfe816b1f1536269bb257fd295b4ef1ba8246ac` Source locator `/rows/9029/row` |  |  |  |
| [Arena text / industry software and it services](https://benchize.com/benchmarks/lmarena%3Atext%3Aindustry_software_and_it_services.md) | 1,449.44 | 75 / 173 |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1449.4373379238314 \| rating \| reported \| Higher is better \| ### Configuration category industry_software_and_it_services config text thinkingEnabled true ### Reported statistics lower 1443.9773993306408 rank 104 upper 1454.897276517022 variance 7.76031472231781 votes 14296 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) Source Arena Original model label DeepSeek-V3.2 (Thinking) Observed 2026-10-22T06:45:03.380Z Evidence SHA-256 `8e027ef69b8de06c4b2a8b217bfe816b1f1536269bb257fd295b4ef1ba8246ac` Source locator `/rows/6804/row` |  |  |  |
| [Arena text / industry writing and literature and language](https://benchize.com/benchmarks/lmarena%3Atext%3Aindustry_writing_and_literature_and_language.md) | 1,398.42 | 83 / 173 |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1398.421079611751 \| rating \| reported \| Higher is better \| ### Configuration category industry_writing_and_literature_and_language config text thinkingEnabled true ### Reported statistics lower 1392.037604728942 rank 115 upper 1404.80455449456 variance 10.6076242077461 votes 9736 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) Source Arena Original model label DeepSeek-V3.2 (Thinking) Observed 2026-10-22T06:45:03.380Z Evidence SHA-256 `8e027ef69b8de06c4b2a8b217bfe816b1f1536269bb257fd295b4ef1ba8246ac` Source locator `/rows/7232/row` |  |  |  |
| [Arena text / non english](https://benchize.com/benchmarks/lmarena%3Atext%3Anon_english.md) | 1,398.84 | 95 / 173 |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1398.8351827920494 \| rating \| reported \| Higher is better \| ### Configuration category non_english config text thinkingEnabled true ### Reported statistics lower 1394.4075521211846 rank 137 upper 1403.262813462914 variance 5.103247040414537 votes 24872 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) Source Arena Original model label DeepSeek-V3.2 (Thinking) Observed 2026-10-22T06:45:03.380Z Evidence SHA-256 `8e027ef69b8de06c4b2a8b217bfe816b1f1536269bb257fd295b4ef1ba8246ac` Source locator `/rows/9867/row` |  |  |  |
| [Arena text / english](https://benchize.com/benchmarks/lmarena%3Atext%3Aenglish.md) | 1,439.1 | 74 / 173 |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1439.1027741866824 \| rating \| reported \| Higher is better \| ### Configuration category english config text thinkingEnabled true ### Reported statistics lower 1434.0204095462368 rank 100 upper 1444.1851388271282 variance 6.72412006587268 votes 17150 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) Source Arena Original model label DeepSeek-V3.2 (Thinking) Observed 2026-10-22T06:45:03.380Z Evidence SHA-256 `8e027ef69b8de06c4b2a8b217bfe816b1f1536269bb257fd295b4ef1ba8246ac` Source locator `/rows/1736/row` |  |  |  |
| [Arena text style control / longer query](https://benchize.com/benchmarks/lmarena%3Atext_style_control%3Alonger_query.md) | 1,441.61 | 80 / 172 |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1441.609455887969 \| rating \| reported \| Higher is better \| ### Configuration category longer_query config text_style_control thinkingEnabled true ### Reported statistics lower 1435.6266596140015 rank 108 upper 1447.5922521619364 variance 9.317775596858 votes 11724 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label DeepSeek-V3.2 (Thinking) Observed 2026-10-22T06:45:03.380Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/8625/row` |  |  |  |
| [Arena text style control / non english](https://benchize.com/benchmarks/lmarena%3Atext_style_control%3Anon_english.md) | 1,400.99 | 95 / 173 |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1400.9910591373075 \| rating \| reported \| Higher is better \| ### Configuration category non_english config text_style_control thinkingEnabled true ### Reported statistics lower 1396.5350605252102 rank 138 upper 1405.447057749405 variance 5.168849793221763 votes 24872 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label DeepSeek-V3.2 (Thinking) Observed 2026-10-22T06:45:03.380Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/9868/row` |  |  |  |
| [Arena text style control / korean](https://benchize.com/benchmarks/lmarena%3Atext_style_control%3Akorean.md) | 1,371.7 | 77 / 144 |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1371.700398883405 \| rating \| reported \| Higher is better \| ### Configuration category korean config text_style_control thinkingEnabled true ### Reported statistics lower 1348.6635248639222 rank 113 upper 1394.737272902888 variance 138.1500074218233 votes 698 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label DeepSeek-V3.2 (Thinking) Observed 2026-10-22T06:45:03.380Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/8346/row` |  |  |  |
| [Arena text style control / industry medicine and healthcare](https://benchize.com/benchmarks/lmarena%3Atext_style_control%3Aindustry_medicine_and_healthcare.md) | 1,431.65 | 97 / 173 |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1431.6544874179783 \| rating \| reported \| Higher is better \| ### Configuration category industry_medicine_and_healthcare config text_style_control thinkingEnabled true ### Reported statistics lower 1420.3522418129296 rank 147 upper 1442.9567330230268 variance 33.25318887415724 votes 2825 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label DeepSeek-V3.2 (Thinking) Observed 2026-10-22T06:45:03.380Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/6459/row` |  |  |  |
| [Arena text style control / english](https://benchize.com/benchmarks/lmarena%3Atext_style_control%3Aenglish.md) | 1,442 | 82 / 173 |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1442.00298821427 \| rating \| reported \| Higher is better \| ### Configuration category english config text_style_control thinkingEnabled true ### Reported statistics lower 1436.8884942217098 rank 111 upper 1447.1174822068306 variance 6.809404973709983 votes 17150 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label DeepSeek-V3.2 (Thinking) Observed 2026-10-22T06:45:03.380Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/1747/row` |  |  |  |
| [Arena text style control / creative writing](https://benchize.com/benchmarks/lmarena%3Atext_style_control%3Acreative_writing.md) | 1,391.33 | 86 / 173 |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1391.331348575779 \| rating \| reported \| Higher is better \| ### Configuration category creative_writing config text_style_control thinkingEnabled true ### Reported statistics lower 1383.6008692124783 rank 124 upper 1399.0618279390796 variance 15.556671039783879 votes 6410 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label DeepSeek-V3.2 (Thinking) Observed 2026-10-22T06:45:03.380Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/1345/row` |  |  |  |
| [Arena text / industry business and management and financial operations](https://benchize.com/benchmarks/lmarena%3Atext%3Aindustry_business_and_management_and_financial_operations.md) | 1,409.29 | 89 / 173 |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1409.2863707707909 \| rating \| reported \| Higher is better \| ### Configuration category industry_business_and_management_and_financial_operations config text thinkingEnabled true ### Reported statistics lower 1402.4701521650795 rank 126 upper 1416.1025893765022 variance 12.094581316493437 votes 8098 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) Source Arena Original model label DeepSeek-V3.2 (Thinking) Observed 2026-10-22T06:45:03.380Z Evidence SHA-256 `8e027ef69b8de06c4b2a8b217bfe816b1f1536269bb257fd295b4ef1ba8246ac` Source locator `/rows/4408/row` |  |  |  |
| [Arena text / expert](https://benchize.com/benchmarks/lmarena%3Atext%3Aexpert.md) | 1,431.17 | 86 / 170 |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1431.173476937255 \| rating \| reported \| Higher is better \| ### Configuration category expert config text thinkingEnabled true ### Reported statistics lower 1420.1330798281003 rank 115 upper 1442.2138740464095 variance 31.730229065895173 votes 2878 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) Source Arena Original model label DeepSeek-V3.2 (Thinking) Observed 2026-10-22T06:45:03.380Z Evidence SHA-256 `8e027ef69b8de06c4b2a8b217bfe816b1f1536269bb257fd295b4ef1ba8246ac` Source locator `/rows/2585/row` |  |  |  |
| [Arena text style control / german](https://benchize.com/benchmarks/lmarena%3Atext_style_control%3Agerman.md) | 1,419.78 | 75 / 149 |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1419.777364907088 \| rating \| reported \| Higher is better \| ### Configuration category german config text_style_control thinkingEnabled true ### Reported statistics lower 1398.57500548791 rank 110 upper 1440.979724326266 variance 117.02326275588757 votes 748 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label DeepSeek-V3.2 (Thinking) Observed 2026-10-22T06:45:03.380Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/3246/row` |  |  |  |
| [Arena text style control / japanese](https://benchize.com/benchmarks/lmarena%3Atext_style_control%3Ajapanese.md) | 1,384.43 | 74 / 138 |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1384.427155691458 \| rating \| reported \| Higher is better \| ### Configuration category japanese config text_style_control thinkingEnabled true ### Reported statistics lower 1354.4965701905285 rank 104 upper 1414.3577411923875 variance 233.2030591093448 votes 385 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label DeepSeek-V3.2 (Thinking) Observed 2026-10-22T06:45:03.380Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/8054/row` |  |  |  |

---
Cite as: DeepSeek V3.2Thinking — Benchize, https://benchize.com/models/deepseek-v3-2-thinking (retrieved 2026-10-22)
