# DeepSeek V3.2

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

DeepSeek

Canonical URL: https://benchize.com/models/deepseek-v3-2
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 | Cost | Source |  |
| --- | --- | --- | --- | --- | --- | --- |
| [DesignArena Overall frontend coding](https://benchize.com/benchmarks/designarena%3Acode.md) | 1,164elo | SE ±2.18 | 70 / 116 | — | [designarena · public](https://www.designarena.ai/api/leaderboard#board=code) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `elo` \| 1164 \| elo \| code \| Higher is better \| ### Configuration arenaType models category allcategories inputModality text sourceModelVersion deepseek-v3p2 variationName public ### Reported statistics Uncertainty Standard error: ±2.18 averageGenerationTimeMs 183663 battles 29125 losses 14757 standardError 2.1849 winRate 49.3 wins 14368 ### Source [Original source](https://www.designarena.ai/api/leaderboard#board=code) Source designarena Original model label DeepSeek-V3.2 Source version public Observed 2026-10-21T16:37:57.301Z Evidence SHA-256 `0c897b58670f5e352bd123db999a40c0d1781a443964c502b90774a76a3a7758` Source locator `/data/105` |  |  |  |  |  |  |
| [τ-bench retail (legacy)](https://benchize.com/benchmarks/sierra%3Alegacy%3Aretail.md) | 81.1% | — | 6 / 14 | — | [sierra](https://sierra-tau-bench-public.s3.us-west-2.amazonaws.com/submissions/deepseek-v3.2_deepseek_2025-12-01/submission.json) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `pass_1` \| 81.1 \| percent \| consistent_success_across_k_trials \| Higher is better \| ### Configuration benchmarkVersion v0.1.3 harness tau-bench methodology {"evaluation_date":"2025-12-01","notes":"","tau2_bench_version":"v0.1.3","user_simulator":"DeepSeek-V3.2","verification":{"details":"Unverified submission - results from technical report, no trajectory data available, exact evaluation methodology not specified","modified_prompts":null,"omitted_questions":null}} modality text Reasoning effort unknown retrieval Not reported sourceSubmission deepseek-v3.2_deepseek_2025-12-01 ### Source [Original source](https://sierra-tau-bench-public.s3.us-west-2.amazonaws.com/submissions/deepseek-v3.2_deepseek_2025-12-01/submission.json) Source sierra Original model label DeepSeek-V3.2 Evaluated 2025-12-01 Observed 2026-10-21T16:55:03.526Z Evidence SHA-256 `ea902585a8aa18933efd69bfcaee7a0d6f7134084f274c81b5ded67cab3fd35f` Source locator `/results/retail` |  |  |  |  |  |  |
| [Arena text / industry software and it services](https://benchize.com/benchmarks/lmarena%3Atext%3Aindustry_software_and_it_services.md) | 1,443.72 | — | 81 / 173 | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1443.718829075518 \| rating \| reported \| Higher is better \| ### Configuration category industry_software_and_it_services config text ### Reported statistics lower 1438.4908898182962 rank 113 upper 1448.9467683327398 variance 7.114835835273016 votes 17247 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) Source Arena Original model label DeepSeek-V3.2 Observed 2026-10-22T06:45:03.380Z Evidence SHA-256 `8e027ef69b8de06c4b2a8b217bfe816b1f1536269bb257fd295b4ef1ba8246ac` Source locator `/rows/6813/row` |  |  |  |  |  |  |
| [Vending-Bench 2](https://benchize.com/benchmarks/vendingbench%3Av2.md) | — | — | — | $1,034 | [vendingbench](https://andonlabs.com/_app/immutable/chunks/Cjn0_qj9.js) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `final_balance` \| 1034.0040000000001 \| USD \| one_simulated_year \| Higher is better \| \| `geometric_mean_balance` \| 1603.2221507421768 \| USD \| positive_final_balances \| Higher is better \| ### Configuration Reasoning effort unknown Model configuration DeepSeek-V3.2 thinkingEnabled Not reported ### Reported statistics confidenceHalfWidth95 986.1716546701318 positiveBalanceRuns 3 runCount 5 standardDeviation 1125.074927207073 standardError 503.1488034031285 ### Source [Original source](https://andonlabs.com/_app/immutable/chunks/Cjn0_qj9.js) Source vendingbench Original model label DeepSeek-V3.2 Observed 2026-10-21T16:36:40.592Z Evidence SHA-256 `1a0b043147050298c405bcb743d73e425d532464202231cd18c27f836fa5f223` Source locator `/rows/19` |  |  |  |  |  |  |
| [Arena webdev / webdev-html](https://benchize.com/benchmarks/lmarena%3Awebdev%3Awebdev-html.md) | 1,305.77 | — | 96 / 106 | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/webdev/latest) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1305.7673129734014 \| rating \| reported \| Higher is better \| ### Configuration category webdev-html config webdev ### Reported statistics lower 1293.3755456946901 rank 128 upper 1318.1590802521127 variance 39.97332874233211 votes 4240 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/webdev/latest) Source Arena Original model label DeepSeek-V3.2 Observed 2026-10-22T06:45:03.380Z Evidence SHA-256 `f82507859808110820a4ab6df15561b8864137ddefc1f6fb0c552af2e58ea738` Source locator `/rows/487/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) | 1,422.21 | — | 88 / 173 | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1422.2094729059527 \| rating \| reported \| Higher is better \| ### Configuration category industry_business_and_management_and_financial_operations config text_style_control ### Reported statistics lower 1415.4455405083932 rank 122 upper 1428.9734053035122 variance 11.909741484743952 votes 9046 ### 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 Observed 2026-10-22T06:45:03.380Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/4404/row` |  |  |  |  |  |  |
| [Arena webdev / webdev-react](https://benchize.com/benchmarks/lmarena%3Awebdev%3Awebdev-react.md) | 1,333.7 | — | 85 / 97 | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/webdev/latest) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1333.6994342721541 \| rating \| reported \| Higher is better \| ### Configuration category webdev-react config webdev ### Reported statistics lower 1323.8239403992081 rank 115 upper 1343.5749281450999 variance 25.387589399427235 votes 5115 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/webdev/latest) Source Arena Original model label DeepSeek-V3.2 Observed 2026-10-22T06:45:03.380Z Evidence SHA-256 `f82507859808110820a4ab6df15561b8864137ddefc1f6fb0c552af2e58ea738` Source locator `/rows/621/row` |  |  |  |  |  |  |
| [τ-bench telecom (legacy)](https://benchize.com/benchmarks/sierra%3Alegacy%3Atelecom.md) | 96.2% | — | 4 / 10 | — | [sierra](https://sierra-tau-bench-public.s3.us-west-2.amazonaws.com/submissions/deepseek-v3.2_deepseek_2025-12-01/submission.json) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `pass_1` \| 96.2 \| percent \| consistent_success_across_k_trials \| Higher is better \| ### Configuration benchmarkVersion v0.1.3 harness tau-bench methodology {"evaluation_date":"2025-12-01","notes":"","tau2_bench_version":"v0.1.3","user_simulator":"DeepSeek-V3.2","verification":{"details":"Unverified submission - results from technical report, no trajectory data available, exact evaluation methodology not specified","modified_prompts":null,"omitted_questions":null}} modality text Reasoning effort unknown retrieval Not reported sourceSubmission deepseek-v3.2_deepseek_2025-12-01 ### Source [Original source](https://sierra-tau-bench-public.s3.us-west-2.amazonaws.com/submissions/deepseek-v3.2_deepseek_2025-12-01/submission.json) Source sierra Original model label DeepSeek-V3.2 Evaluated 2025-12-01 Observed 2026-10-21T16:55:03.526Z Evidence SHA-256 `ea902585a8aa18933efd69bfcaee7a0d6f7134084f274c81b5ded67cab3fd35f` Source locator `/results/telecom` |  |  |  |  |  |  |
| [Arena text style control / expert](https://benchize.com/benchmarks/lmarena%3Atext_style_control%3Aexpert.md) | 1,448.82 | — | 87 / 170 | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1448.822506067376 \| rating \| reported \| Higher is better \| ### Configuration category expert config text_style_control ### Reported statistics lower 1438.500257270631 rank 121 upper 1459.1447548641208 variance 27.73655144965214 votes 3427 ### 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 Observed 2026-10-22T06:45:03.380Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/2591/row` |  |  |  |  |  |  |
| [Arena text style control / multi turn](https://benchize.com/benchmarks/lmarena%3Atext_style_control%3Amulti_turn.md) | 1,428.21 | — | 86 / 173 | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1428.2110529672404 \| rating \| reported \| Higher is better \| ### Configuration category multi_turn config text_style_control ### Reported statistics lower 1421.1229040737212 rank 122 upper 1435.2992018607597 variance 13.078847667464816 votes 8335 ### 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 Observed 2026-10-22T06:45:03.380Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/9437/row` |  |  |  |  |  |  |
| [Arena text style control / spanish](https://benchize.com/benchmarks/lmarena%3Atext_style_control%3Aspanish.md) | 1,417.98 | — | 84 / 155 | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1417.9754459022815 \| rating \| reported \| Higher is better \| ### Configuration category spanish config text_style_control ### Reported statistics lower 1402.1828125032107 rank 119 upper 1433.768079301352 variance 64.92514467000767 votes 1531 ### 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 Observed 2026-10-22T06:45:03.380Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/10883/row` |  |  |  |  |  |  |
| [Arena text / chinese](https://benchize.com/benchmarks/lmarena%3Atext%3Achinese.md) | 1,455.17 | — | 88 / 168 | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1455.1655650201603 \| rating \| reported \| Higher is better \| ### Configuration category chinese config text ### Reported statistics lower 1445.1212575221778 rank 121 upper 1465.2098725181427 variance 26.262968789496625 votes 3732 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) Source Arena Original model label DeepSeek-V3.2 Observed 2026-10-22T06:45:03.380Z Evidence SHA-256 `8e027ef69b8de06c4b2a8b217bfe816b1f1536269bb257fd295b4ef1ba8246ac` Source locator `/rows/537/row` |  |  |  |  |  |  |
| [Arena text / industry life and physical and social science](https://benchize.com/benchmarks/lmarena%3Atext%3Aindustry_life_and_physical_and_social_science.md) | 1,445.6 | — | 69 / 173 | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1445.5977658865972 \| rating \| reported \| Higher is better \| ### Configuration category industry_life_and_physical_and_social_science config text ### Reported statistics lower 1438.4229310264834 rank 89 upper 1452.7726007467113 variance 13.400704699108005 votes 7628 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) Source Arena Original model label DeepSeek-V3.2 Observed 2026-10-22T06:45:03.380Z Evidence SHA-256 `8e027ef69b8de06c4b2a8b217bfe816b1f1536269bb257fd295b4ef1ba8246ac` Source locator `/rows/5586/row` |  |  |  |  |  |  |
| [Arena text / industry mathematical](https://benchize.com/benchmarks/lmarena%3Atext%3Aindustry_mathematical.md) | 1,439.06 | — | 75 / 169 | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1439.0613294098614 \| rating \| reported \| Higher is better \| ### Configuration category industry_mathematical config text ### Reported statistics lower 1426.923066680487 rank 96 upper 1451.1995921392356 variance 38.3545493950386 votes 2483 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) Source Arena Original model label DeepSeek-V3.2 Observed 2026-10-22T06:45:03.380Z Evidence SHA-256 `8e027ef69b8de06c4b2a8b217bfe816b1f1536269bb257fd295b4ef1ba8246ac` Source locator `/rows/6008/row` |  |  |  |  |  |  |
| [Arena text / spanish](https://benchize.com/benchmarks/lmarena%3Atext%3Aspanish.md) | 1,423.89 | — | 75 / 155 | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1423.8917346241033 \| rating \| reported \| Higher is better \| ### Configuration category spanish config text ### Reported statistics lower 1408.1767185383592 rank 106 upper 1439.606750709847 variance 64.28852738048077 votes 1531 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) Source Arena Original model label DeepSeek-V3.2 Observed 2026-10-22T06:45:03.380Z Evidence SHA-256 `8e027ef69b8de06c4b2a8b217bfe816b1f1536269bb257fd295b4ef1ba8246ac` Source locator `/rows/10870/row` |  |  |  |  |  |  |
| [Arena text style control / industry medicine and healthcare](https://benchize.com/benchmarks/lmarena%3Atext_style_control%3Aindustry_medicine_and_healthcare.md) | 1,446.03 | — | 84 / 173 | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1446.0316740549679 \| rating \| reported \| Higher is better \| ### Configuration category industry_medicine_and_healthcare config text_style_control ### Reported statistics lower 1435.0564305739945 rank 117 upper 1457.006917535941 variance 31.35682955072808 votes 3116 ### 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 Observed 2026-10-22T06:45:03.380Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/6429/row` |  |  |  |  |  |  |
| [SpreadsheetBench v2-full](https://benchize.com/benchmarks/spreadsheetbench%3Av2-full.md) | 15.58% | — | 4 / 6 | — | [spreadsheetbench](https://spreadsheetbench.github.io/data/leaderboard-v2-full.json) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `score` \| 15.58 \| percent \| reported \| Higher is better \| \| `Template` \| 25.77 \| percent \| task_category \| Higher is better \| \| `Fin.Model` \| 7 \| percent \| task_category \| Higher is better \| \| `Debug` \| 10 \| percent \| task_category \| Higher is better \| \| `Visualization` \| 33.33 \| percent \| task_category \| Higher is better \| ### Configuration Reasoning effort unknown scaffold SWE-agent verifiedSubmission true ### Source [Original source](https://spreadsheetbench.github.io/data/leaderboard-v2-full.json) Source spreadsheetbench Original model label Deepseek-V3.2 Observed 2026-10-22T04:20:04.823Z Evidence SHA-256 `56490b18fd005f51e088710996636a4de82054809673f24cca40200915be338a` Source locator `/rows/7` |  |  |  |  |  |  |
| [Arena text / exclude ties](https://benchize.com/benchmarks/lmarena%3Atext%3Aexclude_ties.md) | 1,414.77 | — | 76 / 173 | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1414.7733980173562 \| rating \| reported \| Higher is better \| ### Configuration category exclude_ties config text ### Reported statistics lower 1409.924314192113 rank 106 upper 1419.6224818425994 variance 6.121011584861043 votes 34019 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) Source Arena Original model label DeepSeek-V3.2 Observed 2026-10-22T06:45:03.380Z Evidence SHA-256 `8e027ef69b8de06c4b2a8b217bfe816b1f1536269bb257fd295b4ef1ba8246ac` Source locator `/rows/2159/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) | 1,395.8 | — | 84 / 173 | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1395.7960759027555 \| rating \| reported \| Higher is better \| ### Configuration category industry_entertainment_and_sports_and_media config text_style_control ### Reported statistics lower 1388.9354634458657 rank 118 upper 1402.6566883596454 variance 12.252637729727644 votes 8782 ### 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 Observed 2026-10-22T06:45:03.380Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/4810/row` |  |  |  |  |  |  |
| [Arena text style control / english](https://benchize.com/benchmarks/lmarena%3Atext_style_control%3Aenglish.md) | 1,437.76 | — | 87 / 173 | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1437.75555475157 \| rating \| reported \| Higher is better \| ### Configuration category english config text_style_control ### Reported statistics lower 1432.7152904299173 rank 121 upper 1442.7958190732224 variance 6.613181506793801 votes 19609 ### 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 Observed 2026-10-22T06:45:03.380Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/1757/row` |  |  |  |  |  |  |
| [Arena text / industry business and management and financial operations](https://benchize.com/benchmarks/lmarena%3Atext%3Aindustry_business_and_management_and_financial_operations.md) | 1,409.99 | — | 87 / 173 | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1409.9920342604016 \| rating \| reported \| Higher is better \| ### Configuration category industry_business_and_management_and_financial_operations config text ### Reported statistics lower 1403.2719832218677 rank 123 upper 1416.7120852989356 variance 11.755712625949919 votes 9046 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) Source Arena Original model label DeepSeek-V3.2 Observed 2026-10-22T06:45:03.380Z Evidence SHA-256 `8e027ef69b8de06c4b2a8b217bfe816b1f1536269bb257fd295b4ef1ba8246ac` Source locator `/rows/4405/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) | 1,409.82 | — | 79 / 173 | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1409.8242206970142 \| rating \| reported \| Higher is better \| ### Configuration category industry_writing_and_literature_and_language config text_style_control ### Reported statistics lower 1403.5086604559153 rank 106 upper 1416.1397809381133 variance 10.383113036141545 votes 10687 ### 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 Observed 2026-10-22T06:45:03.380Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/7223/row` |  |  |  |  |  |  |
| [DesignArena Data visualization generation](https://benchize.com/benchmarks/designarena%3Adata-viz.md) | 1,158elo | — | 71 / 99 | — | [designarena · public](https://www.designarena.ai/api/leaderboard#board=data-viz) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `elo` \| 1158 \| elo \| data-viz \| Higher is better \| ### Configuration arenaType models category dataviz inputModality Not reported sourceModelVersion deepseek-v3p2 variationName public ### Reported statistics averageGenerationTimeMs 143084 battles 1102 losses 571 standardError Not reported winRate 48.2 wins 531 ### Source [Original source](https://www.designarena.ai/api/leaderboard#board=data-viz) Source designarena Original model label DeepSeek-V3.2 Source version public Observed 2026-10-21T16:37:58.264Z Evidence SHA-256 `a895f6f1a25fa8eb01f821c2097ddec4f884de7bd22f1b8a22e82e6679b71849` Source locator `/data/103` |  |  |  |  |  |  |
| [Arena text style control / industry mathematical](https://benchize.com/benchmarks/lmarena%3Atext_style_control%3Aindustry_mathematical.md) | 1,432.95 | — | 88 / 169 | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1432.9486084571522 \| rating \| reported \| Higher is better \| ### Configuration category industry_mathematical config text_style_control ### Reported statistics lower 1420.7011963112604 rank 122 upper 1445.196020603044 variance 39.04743256996091 votes 2483 ### 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 Observed 2026-10-22T06:45:03.380Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/6034/row` |  |  |  |  |  |  |
| [Arena text / creative writing](https://benchize.com/benchmarks/lmarena%3Atext%3Acreative_writing.md) | 1,399.51 | — | 76 / 173 | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1399.50691524756 \| rating \| reported \| Higher is better \| ### Configuration category creative_writing config text ### Reported statistics lower 1391.9582420155182 rank 103 upper 1407.0555884796022 variance 14.833548978107263 votes 6885 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) Source Arena Original model label DeepSeek-V3.2 Observed 2026-10-22T06:45:03.380Z Evidence SHA-256 `8e027ef69b8de06c4b2a8b217bfe816b1f1536269bb257fd295b4ef1ba8246ac` Source locator `/rows/1324/row` |  |  |  |  |  |  |
| [Arena text / russian](https://benchize.com/benchmarks/lmarena%3Atext%3Arussian.md) | 1,423.55 | — | 68 / 172 | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1423.5542886106516 \| rating \| reported \| Higher is better \| ### Configuration category russian config text ### Reported statistics lower 1415.844569393337 rank 93 upper 1431.2640078279662 variance 15.473228579107733 votes 6097 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) Source Arena Original model label DeepSeek-V3.2 Observed 2026-10-22T06:45:03.380Z Evidence SHA-256 `8e027ef69b8de06c4b2a8b217bfe816b1f1536269bb257fd295b4ef1ba8246ac` Source locator `/rows/10476/row` |  |  |  |  |  |  |
| [Arena text style control / chinese](https://benchize.com/benchmarks/lmarena%3Atext_style_control%3Achinese.md) | 1,457.09 | — | 90 / 168 | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1457.0892303601709 \| rating \| reported \| Higher is better \| ### Configuration category chinese config text_style_control ### Reported statistics lower 1447.0116610354405 rank 126 upper 1467.166799684901 variance 26.437196969976377 votes 3732 ### 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 Observed 2026-10-22T06:45:03.380Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/542/row` |  |  |  |  |  |  |
| [DesignArena UI component generation](https://benchize.com/benchmarks/designarena%3Aui-components.md) | 1,149elo | — | 73 / 112 | — | [designarena · public](https://www.designarena.ai/api/leaderboard#board=ui-components) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `elo` \| 1149 \| elo \| ui-components \| Higher is better \| ### Configuration arenaType models category uicomponent inputModality Not reported sourceModelVersion deepseek-v3p2 variationName public ### Reported statistics averageGenerationTimeMs 129279 battles 1615 losses 860 standardError Not reported winRate 46.8 wins 755 ### Source [Original source](https://www.designarena.ai/api/leaderboard#board=ui-components) Source designarena Original model label DeepSeek-V3.2 Source version public Observed 2026-10-21T16:37:57.993Z Evidence SHA-256 `46482ec1b4012638eace65493daea4750e2088098018fd9d5fc46126fc1f8557` Source locator `/data/106` |  |  |  |  |  |  |
| [Arena text style control / exclude ties](https://benchize.com/benchmarks/lmarena%3Atext_style_control%3Aexclude_ties.md) | 1,416.27 | — | 87 / 173 | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1416.2726008758125 \| rating \| reported \| Higher is better \| ### Configuration category exclude_ties config text_style_control ### Reported statistics lower 1411.3391225065784 rank 124 upper 1421.2060792450466 variance 6.335928603108523 votes 34019 ### 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 Observed 2026-10-22T06:45:03.380Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/2177/row` |  |  |  |  |  |  |
| [DesignArena Website generation](https://benchize.com/benchmarks/designarena%3Awebsite.md) | 1,175elo | — | 72 / 123 | — | [designarena · public](https://www.designarena.ai/api/leaderboard#board=website) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `elo` \| 1175 \| elo \| website \| Higher is better \| ### Configuration arenaType models category website inputModality text sourceModelVersion deepseek-v3p2 variationName public ### Reported statistics averageGenerationTimeMs 202360 battles 17922 losses 8918 standardError Not reported winRate 50.2 wins 9004 ### Source [Original source](https://www.designarena.ai/api/leaderboard#board=website) Source designarena Original model label DeepSeek-V3.2 Source version public Observed 2026-10-21T16:37:57.757Z Evidence SHA-256 `51873e97776a3c5ae706b24cc2c60384793dd18398df970e213a8e7c276d8ac0` Source locator `/data/106` |  |  |  |  |  |  |
| [Arena webdev / overall](https://benchize.com/benchmarks/lmarena%3Awebdev%3Aoverall.md) | 1,326 | — | 93 / 107 | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/webdev/latest) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1325.998861617185 \| rating \| reported \| Higher is better \| ### Configuration category overall config webdev ### Reported statistics lower 1318.0304743645875 rank 125 upper 1333.9672488697825 variance 16.528927777464816 votes 9382 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/webdev/latest) Source Arena Original model label DeepSeek-V3.2 Observed 2026-10-22T06:45:03.380Z Evidence SHA-256 `f82507859808110820a4ab6df15561b8864137ddefc1f6fb0c552af2e58ea738` Source locator `/rows/124/row` |  |  |  |  |  |  |
| [Arena text style control / hard prompts](https://benchize.com/benchmarks/lmarena%3Atext_style_control%3Ahard_prompts.md) | 1,447.27 | — | 85 / 173 | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1447.2686069376955 \| rating \| reported \| Higher is better \| ### Configuration category hard_prompts config text_style_control ### Reported statistics lower 1442.813300960376 rank 117 upper 1451.723912915015 variance 5.167243039182764 votes 27069 ### 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 Observed 2026-10-22T06:45:03.380Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/3567/row` |  |  |  |  |  |  |
| [Longform Creative Writing](https://benchize.com/benchmarks/eq-bench%3Alongform-writing.md) | 66.8% | — | 42 / 93 | — | [eq bench · longform-writing](https://eqbench.com/creative_writing_longform.js) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `overall_score_100` \| 66.8 \| percent \| overall \| Higher is better \| \| `chapter1_avg` \| 14.94 \| rubric_score \| overall \| Higher is better \| \| `chapter2_avg` \| 14.58 \| rubric_score \| overall \| Higher is better \| \| `chapter3_avg` \| 14.58 \| rubric_score \| overall \| Higher is better \| \| `chapter4_avg` \| 14.63 \| rubric_score \| overall \| Higher is better \| \| `chapter5_avg` \| 14.37 \| rubric_score \| overall \| Higher is better \| \| `chapter6_avg` \| 13.79 \| rubric_score \| overall \| Higher is better \| \| `chapter7_avg` \| 13.88 \| rubric_score \| overall \| Higher is better \| \| `chapter8_avg` \| 13.96 \| rubric_score \| overall \| Higher is better \| \| `final_judgement_avg` \| 13.15 \| rubric_score \| overall \| Higher is better \| ### Configuration interactiveAdjustments none protocol longform-writing sourceModelVersion deepseek-ai/DeepSeek-V3.2 ### Source [Original source](https://eqbench.com/creative_writing_longform.js) Source eq bench Original model label deepseek-ai/DeepSeek-V3.2 Source version longform-writing Observed 2026-10-22T05:10:05.903Z Evidence SHA-256 `3ba283ce357ac7620e16db640a961879c30fe3ddc50a27de9a8ed4290784825c` Source locator `/leaderboardDataLongformV3/15` |  |  |  |  |  |  |
| [Arena text / hard prompts english](https://benchize.com/benchmarks/lmarena%3Atext%3Ahard_prompts_english.md) | 1,445.51 | — | 71 / 173 | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1445.510231085943 \| rating \| reported \| Higher is better \| ### Configuration category hard_prompts_english config text ### Reported statistics lower 1439.2988823204537 rank 96 upper 1451.7215798514321 variance 10.043281807085075 votes 11106 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) Source Arena Original model label DeepSeek-V3.2 Observed 2026-10-22T06:45:03.380Z Evidence SHA-256 `8e027ef69b8de06c4b2a8b217bfe816b1f1536269bb257fd295b4ef1ba8246ac` Source locator `/rows/3963/row` |  |  |  |  |  |  |
| [Arena text / industry legal and government](https://benchize.com/benchmarks/lmarena%3Atext%3Aindustry_legal_and_government.md) | 1,425.23 | — | 84 / 173 | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1425.2262948420462 \| rating \| reported \| Higher is better \| ### Configuration category industry_legal_and_government config text ### Reported statistics lower 1415.0582227059779 rank 120 upper 1435.3943669781147 variance 26.91417396102881 votes 3487 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) Source Arena Original model label DeepSeek-V3.2 Observed 2026-10-22T06:45:03.380Z Evidence SHA-256 `8e027ef69b8de06c4b2a8b217bfe816b1f1536269bb257fd295b4ef1ba8246ac` Source locator `/rows/5227/row` |  |  |  |  |  |  |
| [Arena text style control / japanese](https://benchize.com/benchmarks/lmarena%3Atext_style_control%3Ajapanese.md) | 1,364.98 | — | 85 / 138 | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1364.9762934951766 \| rating \| reported \| Higher is better \| ### Configuration category japanese config text_style_control ### Reported statistics lower 1336.361986360123 rank 123 upper 1393.59060063023 variance 213.14261353222662 votes 452 ### 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 Observed 2026-10-22T06:45:03.380Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/8073/row` |  |  |  |  |  |  |
| [Arena text / overall](https://benchize.com/benchmarks/lmarena%3Atext.md) | 1,424.55 | — | 77 / 173 | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1424.5488232144774 \| rating \| reported \| Higher is better \| ### Configuration category overall config text ### Reported statistics lower 1421.0830890190744 rank 106 upper 1428.0145574098804 variance 3.12675836806573 votes 48095 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) Source Arena Original model label DeepSeek-V3.2 Observed 2026-10-22T06:45:03.380Z Evidence SHA-256 `8e027ef69b8de06c4b2a8b217bfe816b1f1536269bb257fd295b4ef1ba8246ac` Source locator `/rows/105/row` |  |  |  |  |  |  |
| [Arena text / hard prompts](https://benchize.com/benchmarks/lmarena%3Atext%3Ahard_prompts.md) | 1,433.75 | — | 76 / 173 | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1433.7528977642937 \| rating \| reported \| Higher is better \| ### Configuration category hard_prompts config text ### Reported statistics lower 1429.321307399156 rank 104 upper 1438.1844881294319 variance 5.11237893755048 votes 27069 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) Source Arena Original model label DeepSeek-V3.2 Observed 2026-10-22T06:45:03.380Z Evidence SHA-256 `8e027ef69b8de06c4b2a8b217bfe816b1f1536269bb257fd295b4ef1ba8246ac` Source locator `/rows/3554/row` |  |  |  |  |  |  |
| [DesignArena 3D design generation](https://benchize.com/benchmarks/designarena%3A3d-design.md) | 1,133elo | — | 58 / 110 | — | [designarena · public](https://www.designarena.ai/api/leaderboard#board=3d-design) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `elo` \| 1133 \| elo \| 3d-design \| Higher is better \| ### Configuration arenaType models category 3d inputModality Not reported sourceModelVersion deepseek-v3p2 variationName public ### Reported statistics averageGenerationTimeMs 132986 battles 4161 losses 2105 standardError Not reported winRate 49.4 wins 2056 ### Source [Original source](https://www.designarena.ai/api/leaderboard#board=3d-design) Source designarena Original model label DeepSeek-V3.2 Source version public Observed 2026-10-21T16:37:58.515Z Evidence SHA-256 `bcc0267f7bc7e9ec112306b3a35413cf78bbccbfaa838356232d5d5ed0b83d0f` Source locator `/data/90` |  |  |  |  |  |  |
| [Arena text / coding](https://benchize.com/benchmarks/lmarena%3Atext%3Acoding.md) | 1,448.92 | — | 75 / 173 | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1448.916502107074 \| rating \| reported \| Higher is better \| ### Configuration category coding config text ### Reported statistics lower 1442.6798475667763 rank 102 upper 1455.1531566473716 variance 10.125283562973749 votes 10916 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) Source Arena Original model label DeepSeek-V3.2 Observed 2026-10-22T06:45:03.380Z Evidence SHA-256 `8e027ef69b8de06c4b2a8b217bfe816b1f1536269bb257fd295b4ef1ba8246ac` Source locator `/rows/911/row` |  |  |  |  |  |  |
| [ARC-AGI-2](https://benchize.com/benchmarks/arc-prize%3Av2_Semi_Private.md) | 4.03% | — | 173 / 243 | 0.12usd per task | [arc prize · v2](https://arcprize.org/media/data/leaderboard/v2.json) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `score` \| 0.0403 \| score_fraction \| v2_Semi_Private \| Higher is better \| \| `cost_per_task` \| 0.12 \| usd_per_task \| v2_Semi_Private \| Lower is better \| ### Configuration evaluationSplit v2_Semi_Private harness Not reported modelGroup Not reported modelType Base LLM sourceModelVersion deepseek-v3.2 ### Source [Original source](https://arcprize.org/media/data/leaderboard/v2.json) Source arc prize Original model label Deepseek V3.2 Source version v2 Observed 2026-10-22T05:20:04.306Z Evidence SHA-256 `4351eb696e78113b0459e9bb5f0258318b905efef34f473dcea51ce641b0d94d` Source locator `/evaluations/128` |  |  |  |  |  |  |
| [Creative Writing v3](https://benchize.com/benchmarks/eq-bench%3Acreative-writing-v3.md) | 1,515elo | — | 48 / 90 | — | [eq bench · creative-writing-v3](https://eqbench.com/creative_writing.js) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `elo_score` \| 1515.0 \| elo \| overall \| Higher is better \| \| `creative_writing_score` \| 16.28 \| rubric_score \| overall \| Higher is better \| ### Configuration interactiveAdjustments none protocol creative-writing-v3 sourceModelVersion deepseek-ai/DeepSeek-V3.2 ### Source [Original source](https://eqbench.com/creative_writing.js) Source eq bench Original model label deepseek-ai/DeepSeek-V3.2 Source version creative-writing-v3 Observed 2026-10-22T05:10:05.433Z Evidence SHA-256 `722ddb132e8d3a5e5c39b8d445f8475f3f7e24893a007260c6f3e3cce5c1ee18` Source locator `/leaderboardDataCreativeWritingV3/59` |  |  |  |  |  |  |
| [Arena text / longer query](https://benchize.com/benchmarks/lmarena%3Atext%3Alonger_query.md) | 1,428.24 | — | 73 / 172 | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1428.237285924479 \| rating \| reported \| Higher is better \| ### Configuration category longer_query config text ### Reported statistics lower 1422.5247351021114 rank 95 upper 1433.9498367468466 variance 8.495011510298019 votes 13730 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) Source Arena Original model label DeepSeek-V3.2 Observed 2026-10-22T06:45:03.380Z Evidence SHA-256 `8e027ef69b8de06c4b2a8b217bfe816b1f1536269bb257fd295b4ef1ba8246ac` Source locator `/rows/8612/row` |  |  |  |  |  |  |
| [Arena text / math](https://benchize.com/benchmarks/lmarena%3Atext%3Amath.md) | 1,435.19 | — | 69 / 170 | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1435.185235928572 \| rating \| reported \| Higher is better \| ### Configuration category math config text ### Reported statistics lower 1424.6067725348596 rank 91 upper 1445.7636993222843 variance 29.1305707012347 votes 3140 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) Source Arena Original model label DeepSeek-V3.2 Observed 2026-10-22T06:45:03.380Z Evidence SHA-256 `8e027ef69b8de06c4b2a8b217bfe816b1f1536269bb257fd295b4ef1ba8246ac` Source locator `/rows/9003/row` |  |  |  |  |  |  |
| [APEX-Agents](https://benchize.com/benchmarks/mercor%3Aapex-agents%3A1.1.md) | 21.3% | — | 37 / 38 | — | [mercor · 1.1](https://www.mercor.com/apex/apex-agents-leaderboard/) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `pass_1` \| 21.3 \| percent \| task_completion_pass_at_1 \| Higher is better \| \| `mean_score` \| 35.1 \| percent \| rubric_mean \| Higher is better \| ### Configuration datasetUrl https://huggingface.co/datasets/mercor/apex-agents-v1.1 datasetVersion 1.1 harness loop_truncated_tools_agent Reasoning effort Not reported ### Reported statistics reportedErrors {"mean_score":4.5,"pass_1":4.1} sampleSize 952 ### Source [Original source](https://www.mercor.com/apex/apex-agents-leaderboard/) Source mercor Original model label DeepSeek-V3.2 Source version 1.1 Observed 2026-10-22T03:20:05.238Z Evidence SHA-256 `9a5cc96c60cc0788561a54a64689121504d26058f7690c1106f2490706183370` Source locator `/__NEXT_DATA__/props/pageProps/leaderboardData/34` |  |  |  |  |  |  |
| [DesignArena SVG generation](https://benchize.com/benchmarks/designarena%3Asvgs.md) | 1,032elo | — | 66 / 77 | — | [designarena · public](https://www.designarena.ai/api/leaderboard#board=svgs) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `elo` \| 1032 \| elo \| svgs \| Higher is better \| ### Configuration arenaType models category svg inputModality Not reported sourceModelVersion deepseek-v3p2 variationName public ### Reported statistics averageGenerationTimeMs 47824 battles 4611 losses 2728 standardError Not reported winRate 40.8 wins 1883 ### Source [Original source](https://www.designarena.ai/api/leaderboard#board=svgs) Source designarena Original model label DeepSeek-V3.2 Source version public Observed 2026-10-21T16:38:03.249Z Evidence SHA-256 `8cbc34a474a66ef5c64f3ffe557df9b55bf7e13368c07c0214223e3ed8f3f21e` Source locator `/data/106` |  |  |  |  |  |  |
| [Arena text style control / german](https://benchize.com/benchmarks/lmarena%3Atext_style_control%3Agerman.md) | 1,413.62 | — | 78 / 149 | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1413.6178264286605 \| rating \| reported \| Higher is better \| ### Configuration category german config text_style_control ### Reported statistics lower 1393.1839331437757 rank 116 upper 1434.051719713545 variance 108.69412227686122 votes 901 ### 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 Observed 2026-10-22T06:45:03.380Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/3252/row` |  |  |  |  |  |  |
| [Arena text style control / instruction following](https://benchize.com/benchmarks/lmarena%3Atext_style_control%3Ainstruction_following.md) | 1,420.3 | — | 82 / 173 | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1420.3049158188471 \| rating \| reported \| Higher is better \| ### Configuration category instruction_following config text_style_control ### Reported statistics lower 1414.5984622461744 rank 112 upper 1426.0113693915196 variance 8.476887010123873 votes 13557 ### 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 Observed 2026-10-22T06:45:03.380Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/7645/row` |  |  |  |  |  |  |
| [Arena text / english](https://benchize.com/benchmarks/lmarena%3Atext%3Aenglish.md) | 1,436.74 | — | 77 / 173 | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1436.7383259623991 \| rating \| reported \| Higher is better \| ### Configuration category english config text ### Reported statistics lower 1431.7403726516714 rank 106 upper 1441.7362792731267 variance 6.502617485224021 votes 19609 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) Source Arena Original model label DeepSeek-V3.2 Observed 2026-10-22T06:45:03.380Z Evidence SHA-256 `8e027ef69b8de06c4b2a8b217bfe816b1f1536269bb257fd295b4ef1ba8246ac` Source locator `/rows/1742/row` |  |  |  |  |  |  |
| [Arena text style control / russian](https://benchize.com/benchmarks/lmarena%3Atext_style_control%3Arussian.md) | 1,422.16 | — | 83 / 172 | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1422.1558331106771 \| rating \| reported \| Higher is better \| ### Configuration category russian config text_style_control ### Reported statistics lower 1414.4033735791709 rank 117 upper 1429.9082926421834 variance 15.645261759381112 votes 6097 ### 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 Observed 2026-10-22T06:45:03.380Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/10500/row` |  |  |  |  |  |  |
| [Arena text style control / creative writing](https://benchize.com/benchmarks/lmarena%3Atext_style_control%3Acreative_writing.md) | 1,400.53 | — | 78 / 173 | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1400.5310500007704 \| rating \| reported \| Higher is better \| ### Configuration category creative_writing config text_style_control ### Reported statistics lower 1392.9014242214757 rank 109 upper 1408.1606757800646 variance 15.153407142747332 votes 6885 ### 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 Observed 2026-10-22T06:45:03.380Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/1330/row` |  |  |  |  |  |  |
| [Arena text / korean](https://benchize.com/benchmarks/lmarena%3Atext%3Akorean.md) | 1,369.85 | — | 76 / 144 | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1369.8542231814106 \| rating \| reported \| Higher is better \| ### Configuration category korean config text ### Reported statistics lower 1348.5977636978291 rank 111 upper 1391.1106826649918 variance 117.62121914286044 votes 795 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) Source Arena Original model label DeepSeek-V3.2 Observed 2026-10-22T06:45:03.380Z Evidence SHA-256 `8e027ef69b8de06c4b2a8b217bfe816b1f1536269bb257fd295b4ef1ba8246ac` Source locator `/rows/8344/row` |  |  |  |  |  |  |
| [Arena webdev / webdev](https://benchize.com/benchmarks/lmarena%3Awebdev%3Awebdev.md) | 1,326 | — | 93 / 107 | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/webdev/latest) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1325.998861617185 \| rating \| reported \| Higher is better \| ### Configuration category webdev config webdev ### Reported statistics lower 1318.0304743645875 rank 125 upper 1333.9672488697825 variance 16.528927777464816 votes 9382 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/webdev/latest) Source Arena Original model label DeepSeek-V3.2 Observed 2026-10-22T06:45:03.380Z Evidence SHA-256 `f82507859808110820a4ab6df15561b8864137ddefc1f6fb0c552af2e58ea738` Source locator `/rows/336/row` |  |  |  |  |  |  |
| [Arena text / non english](https://benchize.com/benchmarks/lmarena%3Atext%3Anon_english.md) | 1,408.95 | — | 79 / 173 | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1408.9541524160966 \| rating \| reported \| Higher is better \| ### Configuration category non_english config text ### Reported statistics lower 1404.6436911737997 rank 110 upper 1413.2646136583935 variance 4.836724012568409 votes 28481 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) Source Arena Original model label DeepSeek-V3.2 Observed 2026-10-22T06:45:03.380Z Evidence SHA-256 `8e027ef69b8de06c4b2a8b217bfe816b1f1536269bb257fd295b4ef1ba8246ac` Source locator `/rows/9840/row` |  |  |  |  |  |  |
| [Arena text / multi turn](https://benchize.com/benchmarks/lmarena%3Atext%3Amulti_turn.md) | 1,426.97 | — | 77 / 173 | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1426.9716569650004 \| rating \| reported \| Higher is better \| ### Configuration category multi_turn config text ### Reported statistics lower 1419.9186850709482 rank 108 upper 1434.0246288590529 variance 12.949354622863005 votes 8335 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) Source Arena Original model label DeepSeek-V3.2 Observed 2026-10-22T06:45:03.380Z Evidence SHA-256 `8e027ef69b8de06c4b2a8b217bfe816b1f1536269bb257fd295b4ef1ba8246ac` Source locator `/rows/9423/row` |  |  |  |  |  |  |
| [Arena text style control / french](https://benchize.com/benchmarks/lmarena%3Atext_style_control%3Afrench.md) | 1,438.81 | — | 91 / 152 | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1438.8096440042682 \| rating \| reported \| Higher is better \| ### Configuration category french config text_style_control ### Reported statistics lower 1421.1673853096445 rank 124 upper 1456.451902698892 variance 81.02372207436181 votes 1243 ### 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 Observed 2026-10-22T06:45:03.380Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/2961/row` |  |  |  |  |  |  |
| [Arena text style control / hard prompts english](https://benchize.com/benchmarks/lmarena%3Atext_style_control%3Ahard_prompts_english.md) | 1,458.85 | — | 81 / 173 | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1458.85089586825 \| rating \| reported \| Higher is better \| ### Configuration category hard_prompts_english config text_style_control ### Reported statistics lower 1452.5975913339998 rank 111 upper 1465.1042004025007 variance 10.179418659240456 votes 11106 ### 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 Observed 2026-10-22T06:45:03.380Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/3978/row` |  |  |  |  |  |  |
| [DesignArena ASCII art generation](https://benchize.com/benchmarks/designarena%3Aascii.md) | 1,083elo | — | 59 / 65 | — | [designarena · public](https://www.designarena.ai/api/leaderboard#board=ascii) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `elo` \| 1083 \| elo \| ascii \| Higher is better \| ### Configuration arenaType models category ascii inputModality Not reported sourceModelVersion deepseek-v3p2 variationName public ### Reported statistics averageGenerationTimeMs 118233 battles 259 losses 154 standardError Not reported winRate 40.5 wins 105 ### Source [Original source](https://www.designarena.ai/api/leaderboard#board=ascii) Source designarena Original model label DeepSeek-V3.2 Source version public Observed 2026-10-21T16:38:03.513Z Evidence SHA-256 `0603b8c65b44ee887f5b566feb469465f59635137a6ac5c6d94c23bcf3776311` Source locator `/data/84` |  |  |  |  |  |  |
| [Arena text style control / overall](https://benchize.com/benchmarks/lmarena%3Atext_style_control%3Aoverall.md) | 1,424.76 | — | 88 / 173 | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1424.7570977242474 \| rating \| reported \| Higher is better \| ### Configuration category overall config text_style_control ### Reported statistics lower 1421.2665953649998 rank 125 upper 1428.247600083495 variance 3.171609351707494 votes 48095 ### 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 Observed 2026-10-22T06:45:03.380Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/124/row` |  |  |  |  |  |  |
| [Arena text / industry writing and literature and language](https://benchize.com/benchmarks/lmarena%3Atext%3Aindustry_writing_and_literature_and_language.md) | 1,407.03 | — | 75 / 173 | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1407.028150134667 \| rating \| reported \| Higher is better \| ### Configuration category industry_writing_and_literature_and_language config text ### Reported statistics lower 1400.7474145972237 rank 102 upper 1413.3088856721104 variance 10.268921452130972 votes 10687 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) Source Arena Original model label DeepSeek-V3.2 Observed 2026-10-22T06:45:03.380Z Evidence SHA-256 `8e027ef69b8de06c4b2a8b217bfe816b1f1536269bb257fd295b4ef1ba8246ac` Source locator `/rows/7219/row` |  |  |  |  |  |  |
| [Arena text style control / industry legal and government](https://benchize.com/benchmarks/lmarena%3Atext_style_control%3Aindustry_legal_and_government.md) | 1,432.14 | — | 89 / 173 | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1432.1421795937906 \| rating \| reported \| Higher is better \| ### Configuration category industry_legal_and_government config text_style_control ### Reported statistics lower 1421.9072215869542 rank 124 upper 1442.377137600627 variance 27.26942296957281 votes 3487 ### 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 Observed 2026-10-22T06:45:03.380Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/5231/row` |  |  |  |  |  |  |
| [Arena text / expert](https://benchize.com/benchmarks/lmarena%3Atext%3Aexpert.md) | 1,436.23 | — | 80 / 170 | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1436.2263644205016 \| rating \| reported \| Higher is better \| ### Configuration category expert config text ### Reported statistics lower 1426.0094536410834 rank 108 upper 1446.4432751999198 variance 27.173339803165817 votes 3427 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) Source Arena Original model label DeepSeek-V3.2 Observed 2026-10-22T06:45:03.380Z Evidence SHA-256 `8e027ef69b8de06c4b2a8b217bfe816b1f1536269bb257fd295b4ef1ba8246ac` Source locator `/rows/2578/row` |  |  |  |  |  |  |
| [Arena text / french](https://benchize.com/benchmarks/lmarena%3Atext%3Afrench.md) | 1,428.97 | — | 86 / 152 | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1428.9722725816484 \| rating \| reported \| Higher is better \| ### Configuration category french config text ### Reported statistics lower 1411.313943167513 rank 120 upper 1446.630601995784 variance 81.17140186909013 votes 1243 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) Source Arena Original model label DeepSeek-V3.2 Observed 2026-10-22T06:45:03.380Z Evidence SHA-256 `8e027ef69b8de06c4b2a8b217bfe816b1f1536269bb257fd295b4ef1ba8246ac` Source locator `/rows/2957/row` |  |  |  |  |  |  |
| [Arena text / industry entertainment and sports and media](https://benchize.com/benchmarks/lmarena%3Atext%3Aindustry_entertainment_and_sports_and_media.md) | 1,394.95 | — | 77 / 173 | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1394.9467599479585 \| rating \| reported \| Higher is better \| ### Configuration category industry_entertainment_and_sports_and_media config text ### Reported statistics lower 1388.1445850086764 rank 108 upper 1401.7489348872407 variance 12.044794976153609 votes 8782 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) Source Arena Original model label DeepSeek-V3.2 Observed 2026-10-22T06:45:03.380Z Evidence SHA-256 `8e027ef69b8de06c4b2a8b217bfe816b1f1536269bb257fd295b4ef1ba8246ac` Source locator `/rows/4800/row` |  |  |  |  |  |  |
| [Arena text / german](https://benchize.com/benchmarks/lmarena%3Atext%3Agerman.md) | 1,407.86 | — | 79 / 149 | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1407.8579575402077 \| rating \| reported \| Higher is better \| ### Configuration category german config text ### Reported statistics lower 1387.6827205334657 rank 114 upper 1428.0331945469497 variance 105.95979477521955 votes 901 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) Source Arena Original model label DeepSeek-V3.2 Observed 2026-10-22T06:45:03.380Z Evidence SHA-256 `8e027ef69b8de06c4b2a8b217bfe816b1f1536269bb257fd295b4ef1ba8246ac` Source locator `/rows/3250/row` |  |  |  |  |  |  |
| [Arena text style control / industry software and it services](https://benchize.com/benchmarks/lmarena%3Atext_style_control%3Aindustry_software_and_it_services.md) | 1,457.84 | — | 88 / 173 | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1457.8381298825982 \| rating \| reported \| Higher is better \| ### Configuration category industry_software_and_it_services config text_style_control ### Reported statistics lower 1452.580636485638 rank 127 upper 1463.0956232795581 variance 7.195505173756862 votes 17247 ### 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 Observed 2026-10-22T06:45:03.380Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/6827/row` |  |  |  |  |  |  |
| [Arena text style control / coding](https://benchize.com/benchmarks/lmarena%3Atext_style_control%3Acoding.md) | 1,469.43 | — | 89 / 173 | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1469.429735230613 \| rating \| reported \| Higher is better \| ### Configuration category coding config text_style_control ### Reported statistics lower 1463.1601769212334 rank 128 upper 1475.6992935399928 variance 10.232404726808875 votes 10916 ### 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 Observed 2026-10-22T06:45:03.380Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/937/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) | 1,452.09 | — | 80 / 173 | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1452.085185010803 \| rating \| reported \| Higher is better \| ### Configuration category industry_life_and_physical_and_social_science config text_style_control ### Reported statistics lower 1444.8523697145756 rank 111 upper 1459.31800030703 variance 13.618164231651116 votes 7628 ### 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 Observed 2026-10-22T06:45:03.380Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/5608/row` |  |  |  |  |  |  |
| [Arena text style control / math](https://benchize.com/benchmarks/lmarena%3Atext_style_control%3Amath.md) | 1,426.45 | — | 85 / 170 | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1426.4522521926617 \| rating \| reported \| Higher is better \| ### Configuration category math config text_style_control ### Reported statistics lower 1415.8177478364871 rank 116 upper 1437.0867565488365 variance 29.4400352002374 votes 3140 ### 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 Observed 2026-10-22T06:45:03.380Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/9028/row` |  |  |  |  |  |  |
| [Short Story Writing — Pairwise Comparison](https://benchize.com/benchmarks/lechmazur-short-story%3Apairwise.md) | -2.88 | 95% CI -3.14–-2.63 | 45 / 50 | — | [lechmazur short story · 8ba548d1cffefa5c472d3832e05f64e119a88fa4](https://api.github.com/repos/lechmazur/writing/contents/data/writing_gemini_argon_20261013/ratings.csv?ref=8ba548d1cffefa5c472d3832e05f64e119a88fa4) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `thurstone_rating` \| -2.8769381221964996 \| index \| pooled_observed_panel \| Higher is better \| \| `win_probability` \| 0.12874783306808807 \| score_fraction \| comparison_pool \| Higher is better \| ### Configuration benchmarkScope data/writing_gemini_argon_20261013 ### Reported statistics Uncertainty 95% confidence interval: -3.14–-2.63 bootstrapSamples 300 confidenceInterval95 ["-3.1423481035149323","-2.6315448071315264"] sourceRank 54 ### Source [Original source](https://api.github.com/repos/lechmazur/writing/contents/data/writing_gemini_argon_20261013/ratings.csv?ref=8ba548d1cffefa5c472d3832e05f64e119a88fa4) Source lechmazur short story Original model label DeepSeek V3.2 Source version 8ba548d1cffefa5c472d3832e05f64e119a88fa4 Observed 2026-10-22T07:10:06.634Z Evidence SHA-256 `c36baebed9f302ff7ad8fe97907d72e1757a015a39b6a3b23437597cf8e3bff6` Source locator `/rows/53` |  |  |  |  |  |  |
| [Arena text / industry medicine and healthcare](https://benchize.com/benchmarks/lmarena%3Atext%3Aindustry_medicine_and_healthcare.md) | 1,439.89 | — | 67 / 173 | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1439.8874492957802 \| rating \| reported \| Higher is better \| ### Configuration category industry_medicine_and_healthcare config text ### Reported statistics lower 1429.0289939719733 rank 96 upper 1450.7459046195877 variance 30.69304072295525 votes 3116 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) Source Arena Original model label DeepSeek-V3.2 Observed 2026-10-22T06:45:03.380Z Evidence SHA-256 `8e027ef69b8de06c4b2a8b217bfe816b1f1536269bb257fd295b4ef1ba8246ac` Source locator `/rows/6408/row` |  |  |  |  |  |  |
| [τ-bench airline (legacy)](https://benchize.com/benchmarks/sierra%3Alegacy%3Aairline.md) | 63.8% | — | 5 / 14 | — | [sierra](https://sierra-tau-bench-public.s3.us-west-2.amazonaws.com/submissions/deepseek-v3.2_deepseek_2025-12-01/submission.json) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `pass_1` \| 63.8 \| percent \| consistent_success_across_k_trials \| Higher is better \| ### Configuration benchmarkVersion v0.1.3 harness tau-bench methodology {"evaluation_date":"2025-12-01","notes":"","tau2_bench_version":"v0.1.3","user_simulator":"DeepSeek-V3.2","verification":{"details":"Unverified submission - results from technical report, no trajectory data available, exact evaluation methodology not specified","modified_prompts":null,"omitted_questions":null}} modality text Reasoning effort unknown retrieval Not reported sourceSubmission deepseek-v3.2_deepseek_2025-12-01 ### Source [Original source](https://sierra-tau-bench-public.s3.us-west-2.amazonaws.com/submissions/deepseek-v3.2_deepseek_2025-12-01/submission.json) Source sierra Original model label DeepSeek-V3.2 Evaluated 2025-12-01 Observed 2026-10-21T16:55:03.526Z Evidence SHA-256 `ea902585a8aa18933efd69bfcaee7a0d6f7134084f274c81b5ded67cab3fd35f` Source locator `/results/airline` |  |  |  |  |  |  |
| [SVGBench Arena](https://benchize.com/benchmarks/svgbench%3Aarena.md) | 1,510 | — | 64 / 191 | — | [svgbench](https://svgbench.ai/api/leaderboard?shape=2) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1510 \| rating \| reported \| Higher is better \| ### Configuration Reasoning effort unknown sourceModelId model_deepseekv32 ### Reported statistics coverageCount 27 draws 6 judged 173 losses 80 rank 80 ratingDeviation 28 wins 87 ### Source [Original source](https://svgbench.ai/api/leaderboard?shape=2) Source svgbench Original model label DeepSeek V3.2 Observed 2026-10-22T04:30:04.538Z Evidence SHA-256 `5c0a9c869593820d57d2c05f6d416e1b44a740b4835e66c66e9ad8b8edc59e2c` Source locator `/rows/77` |  |  |  |  |  |  |
| [Arena text style control / longer query](https://benchize.com/benchmarks/lmarena%3Atext_style_control%3Alonger_query.md) | 1,440.69 | — | 84 / 172 | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1440.6929888986415 \| rating \| reported \| Higher is better \| ### Configuration category longer_query config text_style_control ### Reported statistics lower 1434.9556855710384 rank 112 upper 1446.4302922262443 variance 8.56878884021891 votes 13730 ### 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 Observed 2026-10-22T06:45:03.380Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/8629/row` |  |  |  |  |  |  |
| [SWE-bench Multilingual](https://benchize.com/benchmarks/swe-bench%3Amultilingual.md) | 59% | — | 8 / 9 | — | [SWE-bench](https://www.swebench.com/) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `resolved` \| 59 \| percent \| multilingual \| Higher is better \| ### Configuration agent mini-SWE-agent agentOrganization SWE-agent models ["deepseek-v3.2"] Reasoning effort Not reported sourceSubmission 20260213_mini-v2.0.0a0_deepseek-3-2 subset Multilingual system ["System: Attempts - 1"] ### Reported statistics instanceCalls 82.65666666666667 instanceCost 0.3838255249 sourceWarning Not reported ### Source [Original source](https://www.swebench.com/) Source SWE-bench Original model label DeepSeek V3.2 Observed 2026-10-22T02:30:05.773Z Evidence SHA-256 `c862011a4ee1d1a7199fad6ca0905fa5c64f58216f7217ac1eddf37f28788433` Source locator `/leaderboard-data/0/results/11` |  |  |  |  |  |  |
| [Arena text / polish](https://benchize.com/benchmarks/lmarena%3Atext%3Apolish.md) | 1,408.96 | — | 80 / 137 | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1408.9593409883907 \| rating \| reported \| Higher is better \| ### Configuration category polish config text ### Reported statistics lower 1392.833385000982 rank 113 upper 1425.0852969757993 variance 67.69471407762097 votes 1338 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) Source Arena Original model label DeepSeek-V3.2 Observed 2026-10-22T06:45:03.380Z Evidence SHA-256 `8e027ef69b8de06c4b2a8b217bfe816b1f1536269bb257fd295b4ef1ba8246ac` Source locator `/rows/10260/row` |  |  |  |  |  |  |
| [Arena text / instruction following](https://benchize.com/benchmarks/lmarena%3Atext%3Ainstruction_following.md) | 1,412.93 | — | 75 / 173 | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1412.9330856073339 \| rating \| reported \| Higher is better \| ### Configuration category instruction_following config text ### Reported statistics lower 1407.2455554863977 rank 102 upper 1418.62061572827 variance 8.420758984137768 votes 13557 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) Source Arena Original model label DeepSeek-V3.2 Observed 2026-10-22T06:45:03.380Z Evidence SHA-256 `8e027ef69b8de06c4b2a8b217bfe816b1f1536269bb257fd295b4ef1ba8246ac` Source locator `/rows/7635/row` |  |  |  |  |  |  |
| [Judgemark v2.1](https://benchize.com/benchmarks/eq-bench%3Ajudgemark-v2.md) | 66.28% | — | 23 / 39 | — | [eq bench · judgemark-v2](https://eqbench.com/judgemark-v2.js) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `judgemark_score` \| 66.28 \| percent \| overall \| Higher is better \| \| `stability` \| 0.514 \| score_fraction \| overall \| Higher is better \| \| `separability` \| 0.679 \| score_fraction \| overall \| Higher is better \| \| `human_corr` \| 0.747 \| correlation \| overall \| Higher is better \| ### Configuration interactiveAdjustments none protocol judgemark-v2 sourceModelVersion deepseek-ai/DeepSeek-V3.2 ### Source [Original source](https://eqbench.com/judgemark-v2.js) Source eq bench Original model label deepseek-ai/DeepSeek-V3.2 Source version judgemark-v2 Observed 2026-10-22T05:10:06.632Z Evidence SHA-256 `070cc3fbd6f0333dde2b52bec4329ea3fba7eccbf016bbbbef95e0f8b2197781` Source locator `/leaderboardDataV2/26` |  |  |  |  |  |  |
| [DesignArena Browser game generation](https://benchize.com/benchmarks/designarena%3Agame-dev.md) | 1,131elo | — | 77 / 117 | — | [designarena · public](https://www.designarena.ai/api/leaderboard#board=game-dev) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `elo` \| 1131 \| elo \| game-dev \| Higher is better \| ### Configuration arenaType models category gamedev inputModality Not reported sourceModelVersion deepseek-v3p2 variationName public ### Reported statistics averageGenerationTimeMs 182991 battles 4509 losses 2410 standardError Not reported winRate 46.5 wins 2099 ### Source [Original source](https://www.designarena.ai/api/leaderboard#board=game-dev) Source designarena Original model label DeepSeek-V3.2 Source version public Observed 2026-10-21T16:38:01.100Z Evidence SHA-256 `53db6a89112ce8cdf644568c666d4b8309aece764cfcedb291ffd52ae3934e30` Source locator `/data/116` |  |  |  |  |  |  |
| [Arena text style control / non english](https://benchize.com/benchmarks/lmarena%3Atext_style_control%3Anon_english.md) | 1,408.24 | — | 87 / 173 | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1408.2412887018033 \| rating \| reported \| Higher is better \| ### Configuration category non_english config text_style_control ### Reported statistics lower 1403.9087377439118 rank 126 upper 1412.5738396596946 variance 4.8864243192209855 votes 28481 ### 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 Observed 2026-10-22T06:45:03.380Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/9856/row` |  |  |  |  |  |  |
| [Arena text / japanese](https://benchize.com/benchmarks/lmarena%3Atext%3Ajapanese.md) | 1,358.18 | — | 85 / 138 | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1358.1763184342096 \| rating \| reported \| Higher is better \| ### Configuration category japanese config text ### Reported statistics lower 1329.8832981670296 rank 122 upper 1386.46933870139 variance 208.3830735153954 votes 452 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) Source Arena Original model label DeepSeek-V3.2 Observed 2026-10-22T06:45:03.380Z Evidence SHA-256 `8e027ef69b8de06c4b2a8b217bfe816b1f1536269bb257fd295b4ef1ba8246ac` Source locator `/rows/8072/row` |  |  |  |  |  |  |
| [NC Bench](https://benchize.com/benchmarks/nc-bench%3Aoverall.md) | 82.22% | — | 116 / 144 | — | [nc bench](https://www.nc-bench.com/models) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `score` \| 82.22 \| percent \| reported \| Higher is better \| \| `tooling` \| 99.99 \| percent \| category \| Higher is better \| \| `creative_writing` \| 79.95 \| percent \| category \| Higher is better \| \| `language` \| 85.01 \| percent \| category \| Higher is better \| \| `utility` \| 81.58 \| percent \| category \| Higher is better \| \| `reasoning` \| 75.48 \| percent \| category \| Higher is better \| \| `text_editing` \| 95.78 \| percent \| category \| Higher is better \| \| `rule_following` \| 53.75 \| percent \| category \| Higher is better \| \| `hallucination` \| 86.25 \| percent \| category \| Higher is better \| ### Configuration Reasoning effort unknown Model configuration DeepSeek V3.2 thinkingEnabled Not reported ### Source [Original source](https://www.nc-bench.com/models) Source nc bench Original model label DeepSeek V3.2 Observed 2026-10-22T06:10:03.426Z Evidence SHA-256 `ec261022458543624b08a136d01f5a2f0666cd52ffb49c64d6ca983e8543d1b5` Source locator `/rows/150` |  |  |  |  |  |  |
| [ARC-AGI-1](https://benchize.com/benchmarks/arc-prize%3Av1_Semi_Private.md) | 57% | — | 156 / 245 | 0.08usd per task | [arc prize · v1](https://arcprize.org/media/data/leaderboard/v1.json) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `score` \| 0.57 \| score_fraction \| v1_Semi_Private \| Higher is better \| \| `cost_per_task` \| 0.08 \| usd_per_task \| v1_Semi_Private \| Lower is better \| ### Configuration evaluationSplit v1_Semi_Private harness Not reported modelGroup Not reported modelType Base LLM sourceModelVersion deepseek-v3.2 ### Source [Original source](https://arcprize.org/media/data/leaderboard/v1.json) Source arc prize Original model label Deepseek V3.2 Source version v1 Observed 2026-10-22T05:20:04.066Z Evidence SHA-256 `2bf68d22dafba37047d07ad833ebc0e8199c9aa2f9eeaed50c75c1b704462836` Source locator `/evaluations/127` |  |  |  |  |  |  |
| [Arena text style control / korean](https://benchize.com/benchmarks/lmarena%3Atext_style_control%3Akorean.md) | 1,368.3 | — | 81 / 144 | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1368.3016652436645 \| rating \| reported \| Higher is better \| ### Configuration category korean config text_style_control ### Reported statistics lower 1347.0259753239561 rank 119 upper 1389.5773551633724 variance 117.83413611544972 votes 795 ### 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 Observed 2026-10-22T06:45:03.380Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/8352/row` |  |  |  |  |  |  |
| [Arena text style control / polish](https://benchize.com/benchmarks/lmarena%3Atext_style_control%3Apolish.md) | 1,403.5 | — | 84 / 137 | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1403.4974043310087 \| rating \| reported \| Higher is better \| ### Configuration category polish config text_style_control ### Reported statistics lower 1387.0765074860144 rank 124 upper 1419.9183011760028 variance 70.19360763190936 votes 1338 ### 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 Observed 2026-10-22T06:45:03.380Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/10271/row` |  |  |  |  |  |  |

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