# DeepSeek V4 Pro

> Source: Benchize (https://benchize.com) — https://benchize.com/models/deepseek-v4-pro. When citing or reusing this content, credit "Benchize" and link to https://benchize.com/models/deepseek-v4-pro.

DeepSeek

Canonical URL: https://benchize.com/models/deepseek-v4-pro
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 |  |
| --- | --- | --- | --- | --- | --- | --- |
| [Arena text style control / overall](https://benchize.com/benchmarks/lmarena%3Atext_style_control%3Aoverall.md) | 1,457.98 | — | 51 / 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` \| 1457.9792038397177 \| rating \| reported \| Higher is better \| ### Configuration category overall config text_style_control ### Reported statistics lower 1454.0815430572516 rank 64 upper 1461.876864622184 variance 3.95468499970288 votes 57564 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label DeepSeek-V4-Pro Observed 2026-10-22T06:45:03.380Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/63/row` |  |  |  |  |  |  |
| [DesignArena SVG generation](https://benchize.com/benchmarks/designarena%3Asvgs.md) | 1,140elo | — | 40 / 77 | — | [designarena · public](https://www.designarena.ai/api/leaderboard#board=svgs) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `elo` \| 1140 \| elo \| svgs \| Higher is better \| ### Configuration arenaType models category svg inputModality Not reported sourceModelVersion deepseek-v4-pro variationName public ### Reported statistics averageGenerationTimeMs 244853 battles 2058 losses 1123 standardError Not reported winRate 45.4 wins 935 ### Source [Original source](https://www.designarena.ai/api/leaderboard#board=svgs) Source designarena Original model label DeepSeek-V4-Pro Source version public Observed 2026-10-21T16:38:03.249Z Evidence SHA-256 `8cbc34a474a66ef5c64f3ffe557df9b55bf7e13368c07c0214223e3ed8f3f21e` Source locator `/data/70` |  |  |  |  |  |  |
| [Arena text style control / german](https://benchize.com/benchmarks/lmarena%3Atext_style_control%3Agerman.md) | 1,469.28 | — | 36 / 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` \| 1469.2773680193404 \| rating \| reported \| Higher is better \| ### Configuration category german config text_style_control ### Reported statistics lower 1449.8575483754125 rank 45 upper 1488.6971876632683 variance 98.1734837221403 votes 997 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label DeepSeek-V4-Pro Observed 2026-10-22T06:45:03.380Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/3181/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) | 1,451.5 | — | 44 / 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` \| 1451.49989483313 \| rating \| reported \| Higher is better \| ### Configuration category industry_writing_and_literature_and_language config text_style_control ### Reported statistics lower 1445.1868014039105 rank 54 upper 1457.812988262349 variance 10.37500348340328 votes 14134 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label DeepSeek-V4-Pro Observed 2026-10-22T06:45:03.380Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/7171/row` |  |  |  |  |  |  |
| [Creative Writing v3](https://benchize.com/benchmarks/eq-bench%3Acreative-writing-v3.md) | 1,553.2elo | — | 46 / 90 | — | [eq bench · creative-writing-v3](https://eqbench.com/creative_writing.js) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `elo_score` \| 1553.2 \| elo \| overall \| Higher is better \| \| `creative_writing_score` \| 16.45 \| rubric_score \| overall \| Higher is better \| ### Configuration interactiveAdjustments none protocol creative-writing-v3 sourceModelVersion deepseek-ai/DeepSeek-V4-Pro ### Source [Original source](https://eqbench.com/creative_writing.js) Source eq bench Original model label deepseek-ai/DeepSeek-V4-Pro Source version creative-writing-v3 Observed 2026-10-22T05:10:05.433Z Evidence SHA-256 `722ddb132e8d3a5e5c39b8d445f8475f3f7e24893a007260c6f3e3cce5c1ee18` Source locator `/leaderboardDataCreativeWritingV3/56` |  |  |  |  |  |  |
| [Rapidata SVG generation — Coherence](https://benchize.com/benchmarks/rapidata%3Asvg%3Arlb_1MFkkBzpuU8fTG.md) | 704.78elo | CI 687.01–722.54 | 36 / 37 | — | [rapidata · v1](https://api.rapidata.ai/benchmark/bmk_1MFkc3sXfbKCqf/standings/query?leaderboard_id%5Beq%5D=rlb_1MFkkBzpuU8fTG) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `elo` \| 704.7768181384093 \| elo \| rlb_1MFkkBzpuU8fTG \| Higher is better \| ### Configuration benchmarkId bmk_1MFkc3sXfbKCqf criterion rlb_1MFkkBzpuU8fTG participantId par_1MFlMvFnF7SJTw sourceModelVersion deepseek-v4-pro weighted false ### Reported statistics Uncertainty Confidence interval: 687.01–722.54 confidenceIntervalLowerOffset 17.761890441738956 confidenceIntervalUpperOffset 17.761890441738956 totalMatches 8893 wins 2937 ### Source [Original source](https://api.rapidata.ai/benchmark/bmk_1MFkc3sXfbKCqf/standings/query?leaderboard_id%5Beq%5D=rlb_1MFkkBzpuU8fTG) Source rapidata Original model label deepseek-v4-pro Source version v1 Observed 2026-10-21T16:37:39.715Z Evidence SHA-256 `aa3cb94ff16f544c58adeea35b9087d281c785058b8ce1ae0f98a7ff84920930` Source locator `/items/66` |  |  |  |  |  |  |
| [Arena text style control / creative writing](https://benchize.com/benchmarks/lmarena%3Atext_style_control%3Acreative_writing.md) | 1,446.34 | — | 37 / 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` \| 1446.3350418536338 \| rating \| reported \| Higher is better \| ### Configuration category creative_writing config text_style_control ### Reported statistics lower 1439.0759164959659 rank 45 upper 1453.5941672113017 variance 13.717419193579936 votes 9724 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label DeepSeek-V4-Pro Observed 2026-10-22T06:45:03.380Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/1266/row` |  |  |  |  |  |  |
| [Arena text style control / french](https://benchize.com/benchmarks/lmarena%3Atext_style_control%3Afrench.md) | 1,486.65 | — | 38 / 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` \| 1486.6463993134766 \| rating \| reported \| Higher is better \| ### Configuration category french config text_style_control ### Reported statistics lower 1472.1627983442713 rank 47 upper 1501.1300002826815 variance 54.608081675923046 votes 2210 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label DeepSeek-V4-Pro Observed 2026-10-22T06:45:03.380Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/2884/row` |  |  |  |  |  |  |
| [Arena text / english](https://benchize.com/benchmarks/lmarena%3Atext%3Aenglish.md) | 1,459.22 | — | 41 / 173 | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1459.2237881213969 \| rating \| reported \| Higher is better \| ### Configuration category english config text ### Reported statistics lower 1454.1373908522194 rank 46 upper 1464.3101853905744 variance 6.734794875458631 votes 25275 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) Source Arena Original model label DeepSeek-V4-Pro Observed 2026-10-22T06:45:03.380Z Evidence SHA-256 `8e027ef69b8de06c4b2a8b217bfe816b1f1536269bb257fd295b4ef1ba8246ac` Source locator `/rows/1682/row` |  |  |  |  |  |  |
| [DesignArena UI component generation](https://benchize.com/benchmarks/designarena%3Aui-components.md) | 1,222elo | — | 44 / 112 | — | [designarena · public](https://www.designarena.ai/api/leaderboard#board=ui-components) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `elo` \| 1222 \| elo \| ui-components \| Higher is better \| ### Configuration arenaType models category uicomponent inputModality Not reported sourceModelVersion deepseek-v4-pro variationName public ### Reported statistics averageGenerationTimeMs 225996 battles 2145 losses 1060 standardError Not reported winRate 50.6 wins 1085 ### Source [Original source](https://www.designarena.ai/api/leaderboard#board=ui-components) Source designarena Original model label DeepSeek-V4-Pro Source version public Observed 2026-10-21T16:37:57.993Z Evidence SHA-256 `46482ec1b4012638eace65493daea4750e2088098018fd9d5fc46126fc1f8557` Source locator `/data/68` |  |  |  |  |  |  |
| [DesignArena Overall frontend coding](https://benchize.com/benchmarks/designarena%3Acode.md) | 1,240elo | SE ±2.26 | 37 / 116 | — | [designarena · public](https://www.designarena.ai/api/leaderboard#board=code) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `elo` \| 1240 \| elo \| code \| Higher is better \| ### Configuration arenaType models category allcategories inputModality text sourceModelVersion deepseek-v4-pro variationName public ### Reported statistics Uncertainty Standard error: ±2.26 averageGenerationTimeMs 284736 battles 27276 losses 13122 standardError 2.2621 winRate 51.9 wins 14154 ### Source [Original source](https://www.designarena.ai/api/leaderboard#board=code) Source designarena Original model label DeepSeek-V4-Pro Source version public Observed 2026-10-21T16:37:57.301Z Evidence SHA-256 `0c897b58670f5e352bd123db999a40c0d1781a443964c502b90774a76a3a7758` Source locator `/data/60` |  |  |  |  |  |  |
| [Arena text style control / exclude ties](https://benchize.com/benchmarks/lmarena%3Atext_style_control%3Aexclude_ties.md) | 1,461.82 | — | 51 / 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` \| 1461.8212943999977 \| rating \| reported \| Higher is better \| ### Configuration category exclude_ties config text_style_control ### Reported statistics lower 1456.698289956756 rank 64 upper 1466.944298843239 variance 6.832085348432792 votes 43590 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label DeepSeek-V4-Pro Observed 2026-10-22T06:45:03.380Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/2117/row` |  |  |  |  |  |  |
| [Arena text style control / chinese](https://benchize.com/benchmarks/lmarena%3Atext_style_control%3Achinese.md) | 1,488.65 | — | 63 / 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` \| 1488.651451754298 \| rating \| reported \| Higher is better \| ### Configuration category chinese config text_style_control ### Reported statistics lower 1477.8961935146926 rank 80 upper 1499.4067099939032 variance 30.112409165352705 votes 3391 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label DeepSeek-V4-Pro Observed 2026-10-22T06:45:03.380Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/496/row` |  |  |  |  |  |  |
| [Vending-Bench 2](https://benchize.com/benchmarks/vendingbench%3Av2.md) | — | — | — | $3,284.52 | [vendingbench](https://andonlabs.com/_app/immutable/chunks/Cjn0_qj9.js) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `final_balance` \| 3284.519999999999 \| USD \| one_simulated_year \| Higher is better \| \| `geometric_mean_balance` \| 3014.569684982306 \| USD \| positive_final_balances \| Higher is better \| ### Configuration Reasoning effort unknown Model configuration Deepseek V4 Pro thinkingEnabled Not reported ### Reported statistics confidenceHalfWidth95 1118.5805152122584 positiveBalanceRuns 6 runCount 6 standardDeviation 1397.9344380048722 standardError 570.7043444960502 ### Source [Original source](https://andonlabs.com/_app/immutable/chunks/Cjn0_qj9.js) Source vendingbench Original model label Deepseek V4 Pro Observed 2026-10-21T16:36:40.592Z Evidence SHA-256 `1a0b043147050298c405bcb743d73e425d532464202231cd18c27f836fa5f223` Source locator `/rows/20` |  |  |  |  |  |  |
| [Arena webdev / webdev-html](https://benchize.com/benchmarks/lmarena%3Awebdev%3Awebdev-html.md) | 1,434.74 | — | 66 / 106 | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/webdev/latest) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1434.7414933435548 \| rating \| reported \| Higher is better \| ### Configuration category webdev-html config webdev ### Reported statistics lower 1418.8573571452293 rank 84 upper 1450.62562954188 variance 65.67967913850012 votes 1502 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/webdev/latest) Source Arena Original model label DeepSeek-V4-Pro Observed 2026-10-22T06:45:03.380Z Evidence SHA-256 `f82507859808110820a4ab6df15561b8864137ddefc1f6fb0c552af2e58ea738` Source locator `/rows/443/row` |  |  |  |  |  |  |
| [Arena text / japanese](https://benchize.com/benchmarks/lmarena%3Atext%3Ajapanese.md) | 1,446.32 | — | 32 / 138 | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1446.322479780653 \| rating \| reported \| Higher is better \| ### Configuration category japanese config text ### Reported statistics lower 1422.8633611295195 rank 34 upper 1469.7815984317867 variance 143.2607437891325 votes 721 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) Source Arena Original model label DeepSeek-V4-Pro Observed 2026-10-22T06:45:03.380Z Evidence SHA-256 `8e027ef69b8de06c4b2a8b217bfe816b1f1536269bb257fd295b4ef1ba8246ac` Source locator `/rows/7984/row` |  |  |  |  |  |  |
| [NC Bench](https://benchize.com/benchmarks/nc-bench%3Aoverall.md) | 82.05% | — | 118 / 144 | — | [nc bench](https://www.nc-bench.com/models) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `score` \| 82.05 \| percent \| reported \| Higher is better \| \| `tooling` \| 99.57 \| percent \| category \| Higher is better \| \| `creative_writing` \| 83.7 \| percent \| category \| Higher is better \| \| `language` \| 72.8 \| percent \| category \| Higher is better \| \| `utility` \| 77.57 \| percent \| category \| Higher is better \| \| `reasoning` \| 71.72 \| percent \| category \| Higher is better \| \| `text_editing` \| 97.98 \| percent \| category \| Higher is better \| \| `rule_following` \| 63.74 \| percent \| category \| Higher is better \| \| `hallucination` \| 89.36 \| percent \| category \| Higher is better \| ### Configuration Reasoning effort unknown Model configuration DeepSeek V4 Pro thinkingEnabled Not reported ### Source [Original source](https://www.nc-bench.com/models) Source nc bench Original model label DeepSeek V4 Pro Observed 2026-10-22T06:10:03.426Z Evidence SHA-256 `ec261022458543624b08a136d01f5a2f0666cd52ffb49c64d6ca983e8543d1b5` Source locator `/rows/153` |  |  |  |  |  |  |
| [Arena text style control / industry software and it services](https://benchize.com/benchmarks/lmarena%3Atext_style_control%3Aindustry_software_and_it_services.md) | 1,491.98 | — | 54 / 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` \| 1491.9790456888165 \| rating \| reported \| Higher is better \| ### Configuration category industry_software_and_it_services config text_style_control ### Reported statistics lower 1486.7140554174105 rank 69 upper 1497.2440359602226 variance 7.2160405335259075 votes 23641 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label DeepSeek-V4-Pro Observed 2026-10-22T06:45:03.380Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/6769/row` |  |  |  |  |  |  |
| [Arena text / non english](https://benchize.com/benchmarks/lmarena%3Atext%3Anon_english.md) | 1,439.15 | — | 45 / 173 | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1439.1477420586436 \| rating \| reported \| Higher is better \| ### Configuration category non_english config text ### Reported statistics lower 1434.449924841075 rank 53 upper 1443.845559276212 variance 5.7450795751847155 votes 32289 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) Source Arena Original model label DeepSeek-V4-Pro Observed 2026-10-22T06:45:03.380Z Evidence SHA-256 `8e027ef69b8de06c4b2a8b217bfe816b1f1536269bb257fd295b4ef1ba8246ac` Source locator `/rows/9783/row` |  |  |  |  |  |  |
| [TubeLab Scriptwriting](https://benchize.com/benchmarks/tubelab%3Ascriptwriting.md) | 76.4% | — | 10 / 16 | 0.05ratio | [tubelab](https://tubelab.net/_next/static/chunks/pages/benchmark/scriptwriting-7ad7196ff3093ad4.js) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `quality` \| 76.4 \| percent \| source_reported \| Higher is better \| \| `craft` \| 76.4 \| percent \| source_reported \| Higher is better \| \| `relative_cost_per_script` \| 0.05 \| ratio \| source_reported \| Lower is better \| \| `script_time` \| 10.6 \| minutes \| source_reported \| Lower is better \| \| `hook` \| 7.8 \| score_out_of_10 \| craft_rubric \| Higher is better \| \| `retention` \| 7.5 \| score_out_of_10 \| craft_rubric \| Higher is better \| \| `storytelling` \| 7 \| score_out_of_10 \| craft_rubric \| Higher is better \| \| `voiceMatch` \| 7.2 \| score_out_of_10 \| craft_rubric \| Higher is better \| \| `pacing` \| 7.6 \| score_out_of_10 \| craft_rubric \| Higher is better \| \| `clarity` \| 8.7 \| score_out_of_10 \| craft_rubric \| Higher is better \| ### Configuration judgingProtocol blind_model_judges Reasoning effort unknown taskCount 12 ### Reported statistics confidence {"high":81.4,"low":71.5} headToHead {"losses":6,"ties":1,"winPercent":42,"wins":4} rank 15 ### Source [Original source](https://tubelab.net/_next/static/chunks/pages/benchmark/scriptwriting-7ad7196ff3093ad4.js) Source tubelab Original model label DeepSeek V4 Pro Observed 2026-10-21T16:34:03.856Z Evidence SHA-256 `72f9d867f388256af8fc6dca12e8c7b6f1ddcbb97f0712da339b73102686761f` Source locator `/rows/14` |  |  |  |  |  |  |
| [Arena text / hard prompts](https://benchize.com/benchmarks/lmarena%3Atext%3Ahard_prompts.md) | 1,461.4 | — | 48 / 173 | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1461.4004417554825 \| rating \| reported \| Higher is better \| ### Configuration category hard_prompts config text ### Reported statistics lower 1456.847147515924 rank 56 upper 1465.953735995041 variance 5.3970351888999 votes 38504 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) Source Arena Original model label DeepSeek-V4-Pro Observed 2026-10-22T06:45:03.380Z Evidence SHA-256 `8e027ef69b8de06c4b2a8b217bfe816b1f1536269bb257fd295b4ef1ba8246ac` Source locator `/rows/3506/row` |  |  |  |  |  |  |
| [Arena text / korean](https://benchize.com/benchmarks/lmarena%3Atext%3Akorean.md) | 1,409.31 | — | 47 / 144 | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1409.3137397768762 \| rating \| reported \| Higher is better \| ### Configuration category korean config text ### Reported statistics lower 1390.4669833206606 rank 57 upper 1428.160496233092 variance 92.46493207383429 votes 1110 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) Source Arena Original model label DeepSeek-V4-Pro Observed 2026-10-22T06:45:03.380Z Evidence SHA-256 `8e027ef69b8de06c4b2a8b217bfe816b1f1536269bb257fd295b4ef1ba8246ac` Source locator `/rows/8290/row` |  |  |  |  |  |  |
| [Arena text style control / hard prompts](https://benchize.com/benchmarks/lmarena%3Atext_style_control%3Ahard_prompts.md) | 1,480.17 | — | 51 / 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` \| 1480.1746192495339 \| rating \| reported \| Higher is better \| ### Configuration category hard_prompts config text_style_control ### Reported statistics lower 1475.5981140150443 rank 65 upper 1484.7511244840234 variance 5.452199578056473 votes 38504 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label DeepSeek-V4-Pro Observed 2026-10-22T06:45:03.380Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/3515/row` |  |  |  |  |  |  |
| [Arena text / industry life and physical and social science](https://benchize.com/benchmarks/lmarena%3Atext%3Aindustry_life_and_physical_and_social_science.md) | 1,470.14 | — | 39 / 173 | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1470.138015382589 \| rating \| reported \| Higher is better \| ### Configuration category industry_life_and_physical_and_social_science config text ### Reported statistics lower 1463.0706475179124 rank 43 upper 1477.2053832472654 variance 13.002270977263072 votes 9159 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) Source Arena Original model label DeepSeek-V4-Pro Observed 2026-10-22T06:45:03.380Z Evidence SHA-256 `8e027ef69b8de06c4b2a8b217bfe816b1f1536269bb257fd295b4ef1ba8246ac` Source locator `/rows/5540/row` |  |  |  |  |  |  |
| [Rapidata SVG generation — Alignment](https://benchize.com/benchmarks/rapidata%3Asvg%3Arlb_1MFkk9yZHssERh.md) | 802.52elo | CI 784.89–820.16 | 30 / 37 | — | [rapidata · v1](https://api.rapidata.ai/benchmark/bmk_1MFkc3sXfbKCqf/standings/query?leaderboard_id%5Beq%5D=rlb_1MFkk9yZHssERh) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `elo` \| 802.5236509655402 \| elo \| rlb_1MFkk9yZHssERh \| Higher is better \| ### Configuration benchmarkId bmk_1MFkc3sXfbKCqf criterion rlb_1MFkk9yZHssERh participantId par_1MFlMvFnF7SJTw sourceModelVersion deepseek-v4-pro weighted false ### Reported statistics Uncertainty Confidence interval: 784.89–820.16 confidenceIntervalLowerOffset 17.636901068273005 confidenceIntervalUpperOffset 17.636901068273005 totalMatches 8936 wins 3749 ### Source [Original source](https://api.rapidata.ai/benchmark/bmk_1MFkc3sXfbKCqf/standings/query?leaderboard_id%5Beq%5D=rlb_1MFkk9yZHssERh) Source rapidata Original model label deepseek-v4-pro Source version v1 Observed 2026-10-21T16:37:40.342Z Evidence SHA-256 `2f5c8d08728735790b500d930d71b66f04253f1209f7c1c3da0db0846c163fcf` Source locator `/items/54` |  |  |  |  |  |  |
| [Rapidata Text-to-3D with LLM code — Alignment](https://benchize.com/benchmarks/rapidata%3Atext-to-3d-code%3Arlb_1YVpXug2nDeUlV.md) | 354.16elo | CI 326–382.32 | 9 / 9 | — | [rapidata](https://api.rapidata.ai/benchmark/bmk_1YVpXgN69Mv8I9/standings/query?leaderboard_id%5Beq%5D=rlb_1YVpXug2nDeUlV) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `elo` \| 354.16216337505136 \| elo \| rlb_1YVpXug2nDeUlV \| Higher is better \| ### Configuration benchmarkId bmk_1YVpXgN69Mv8I9 criterion rlb_1YVpXug2nDeUlV participantId par_1YVpXvfRUxkGSG sourceModelVersion deepseek-v4-pro weighted false ### Reported statistics Uncertainty Confidence interval: 326–382.32 confidenceIntervalLowerOffset 28.158066988117525 confidenceIntervalUpperOffset 28.158066988117525 totalMatches 5231 wins 948 ### Source [Original source](https://api.rapidata.ai/benchmark/bmk_1YVpXgN69Mv8I9/standings/query?leaderboard_id%5Beq%5D=rlb_1YVpXug2nDeUlV) Source rapidata Original model label deepseek-v4-pro Source version Observed 2026-10-21T16:37:42.991Z Evidence SHA-256 `a2223beea99910879fd4c5ded70604d3d62dcff1f04a3b617d13f28f03a75948` Source locator `/items/13` |  |  |  |  |  |  |
| [DesignArena 3D design generation](https://benchize.com/benchmarks/designarena%3A3d-design.md) | 1,254elo | — | 27 / 110 | — | [designarena · public](https://www.designarena.ai/api/leaderboard#board=3d-design) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `elo` \| 1254 \| elo \| 3d-design \| Higher is better \| ### Configuration arenaType models category 3d inputModality Not reported sourceModelVersion deepseek-v4-pro variationName public ### Reported statistics averageGenerationTimeMs 304157 battles 4513 losses 1950 standardError Not reported winRate 56.8 wins 2563 ### Source [Original source](https://www.designarena.ai/api/leaderboard#board=3d-design) Source designarena Original model label DeepSeek-V4-Pro Source version public Observed 2026-10-21T16:37:58.515Z Evidence SHA-256 `bcc0267f7bc7e9ec112306b3a35413cf78bbccbfaa838356232d5d5ed0b83d0f` Source locator `/data/40` |  |  |  |  |  |  |
| [Arena text style control / japanese](https://benchize.com/benchmarks/lmarena%3Atext_style_control%3Ajapanese.md) | 1,456.28 | — | 32 / 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` \| 1456.2767248132443 \| rating \| reported \| Higher is better \| ### Configuration category japanese config text_style_control ### Reported statistics lower 1432.5504347223796 rank 35 upper 1480.0030149041088 variance 146.54246413974047 votes 721 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label DeepSeek-V4-Pro Observed 2026-10-22T06:45:03.380Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/7985/row` |  |  |  |  |  |  |
| [Arena text / spanish](https://benchize.com/benchmarks/lmarena%3Atext%3Aspanish.md) | 1,456.54 | — | 38 / 155 | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1456.5403312186509 \| rating \| reported \| Higher is better \| ### Configuration category spanish config text ### Reported statistics lower 1441.3973312847302 rank 47 upper 1471.683331152571 variance 59.69358457349731 votes 1732 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) Source Arena Original model label DeepSeek-V4-Pro Observed 2026-10-22T06:45:03.380Z Evidence SHA-256 `8e027ef69b8de06c4b2a8b217bfe816b1f1536269bb257fd295b4ef1ba8246ac` Source locator `/rows/10811/row` |  |  |  |  |  |  |
| [DesignArena ASCII art generation](https://benchize.com/benchmarks/designarena%3Aascii.md) | 1,149elo | — | 40 / 65 | — | [designarena · public](https://www.designarena.ai/api/leaderboard#board=ascii) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `elo` \| 1149 \| elo \| ascii \| Higher is better \| ### Configuration arenaType models category ascii inputModality Not reported sourceModelVersion deepseek-v4-pro variationName public ### Reported statistics averageGenerationTimeMs 276994 battles 679 losses 364 standardError Not reported winRate 46.4 wins 315 ### Source [Original source](https://www.designarena.ai/api/leaderboard#board=ascii) Source designarena Original model label DeepSeek-V4-Pro Source version public Observed 2026-10-21T16:38:03.513Z Evidence SHA-256 `0603b8c65b44ee887f5b566feb469465f59635137a6ac5c6d94c23bcf3776311` Source locator `/data/55` |  |  |  |  |  |  |
| [Arena text / french](https://benchize.com/benchmarks/lmarena%3Atext%3Afrench.md) | 1,473.31 | — | 35 / 152 | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1473.3085393015767 \| rating \| reported \| Higher is better \| ### Configuration category french config text ### Reported statistics lower 1458.890576966354 rank 40 upper 1487.7265016367996 variance 54.11424346918766 votes 2210 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) Source Arena Original model label DeepSeek-V4-Pro Observed 2026-10-22T06:45:03.380Z Evidence SHA-256 `8e027ef69b8de06c4b2a8b217bfe816b1f1536269bb257fd295b4ef1ba8246ac` Source locator `/rows/2877/row` |  |  |  |  |  |  |
| [Arena text / longer query](https://benchize.com/benchmarks/lmarena%3Atext%3Alonger_query.md) | 1,457.75 | — | 46 / 172 | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1457.7503078032023 \| rating \| reported \| Higher is better \| ### Configuration category longer_query config text ### Reported statistics lower 1452.4553528749834 rank 53 upper 1463.045262731421 variance 7.298411619261288 votes 25924 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) Source Arena Original model label DeepSeek-V4-Pro Observed 2026-10-22T06:45:03.380Z Evidence SHA-256 `8e027ef69b8de06c4b2a8b217bfe816b1f1536269bb257fd295b4ef1ba8246ac` Source locator `/rows/8570/row` |  |  |  |  |  |  |
| [Arena text / math](https://benchize.com/benchmarks/lmarena%3Atext%3Amath.md) | 1,442.67 | — | 62 / 170 | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1442.6702923789082 \| rating \| reported \| Higher is better \| ### Configuration category math config text ### Reported statistics lower 1431.6123058295302 rank 78 upper 1453.7282789282863 variance 31.831414114737363 votes 3068 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) Source Arena Original model label DeepSeek-V4-Pro Observed 2026-10-22T06:45:03.380Z Evidence SHA-256 `8e027ef69b8de06c4b2a8b217bfe816b1f1536269bb257fd295b4ef1ba8246ac` Source locator `/rows/8990/row` |  |  |  |  |  |  |
| [Arena text / chinese](https://benchize.com/benchmarks/lmarena%3Atext%3Achinese.md) | 1,481.11 | — | 60 / 168 | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1481.1120026844856 \| rating \| reported \| Higher is better \| ### Configuration category chinese config text ### Reported statistics lower 1470.395902654021 rank 73 upper 1491.8281027149499 variance 29.893539205548244 votes 3391 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) Source Arena Original model label DeepSeek-V4-Pro Observed 2026-10-22T06:45:03.380Z Evidence SHA-256 `8e027ef69b8de06c4b2a8b217bfe816b1f1536269bb257fd295b4ef1ba8246ac` Source locator `/rows/489/row` |  |  |  |  |  |  |
| [DesignArena Website generation](https://benchize.com/benchmarks/designarena%3Awebsite.md) | 1,235elo | — | 42 / 123 | — | [designarena · public](https://www.designarena.ai/api/leaderboard#board=website) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `elo` \| 1235 \| elo \| website \| Higher is better \| ### Configuration arenaType models category website inputModality text sourceModelVersion deepseek-v4-pro variationName public ### Reported statistics averageGenerationTimeMs 274978 battles 15533 losses 7683 standardError Not reported winRate 50.5 wins 7850 ### Source [Original source](https://www.designarena.ai/api/leaderboard#board=website) Source designarena Original model label DeepSeek-V4-Pro Source version public Observed 2026-10-21T16:37:57.757Z Evidence SHA-256 `51873e97776a3c5ae706b24cc2c60384793dd18398df970e213a8e7c276d8ac0` Source locator `/data/68` |  |  |  |  |  |  |
| [Arena text / exclude ties](https://benchize.com/benchmarks/lmarena%3Atext%3Aexclude_ties.md) | 1,450.03 | — | 44 / 173 | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1450.0346675030862 \| rating \| reported \| Higher is better \| ### Configuration category exclude_ties config text ### Reported statistics lower 1444.989216442416 rank 49 upper 1455.0801185637567 variance 6.626799243163544 votes 43590 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) Source Arena Original model label DeepSeek-V4-Pro Observed 2026-10-22T06:45:03.380Z Evidence SHA-256 `8e027ef69b8de06c4b2a8b217bfe816b1f1536269bb257fd295b4ef1ba8246ac` Source locator `/rows/2102/row` |  |  |  |  |  |  |
| [Arena text style control / instruction following](https://benchize.com/benchmarks/lmarena%3Atext_style_control%3Ainstruction_following.md) | 1,452.73 | — | 49 / 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` \| 1452.731140148001 \| rating \| reported \| Higher is better \| ### Configuration category instruction_following config text_style_control ### Reported statistics lower 1447.1579173652374 rank 60 upper 1458.3043629307647 variance 8.085681413266911 votes 20026 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label DeepSeek-V4-Pro Observed 2026-10-22T06:45:03.380Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/7593/row` |  |  |  |  |  |  |
| [Arena text / industry legal and government](https://benchize.com/benchmarks/lmarena%3Atext%3Aindustry_legal_and_government.md) | 1,463.94 | — | 41 / 173 | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1463.9446181514977 \| rating \| reported \| Higher is better \| ### Configuration category industry_legal_and_government config text ### Reported statistics lower 1454.4960682896087 rank 46 upper 1473.3931680133865 variance 23.239893660103967 votes 4496 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) Source Arena Original model label DeepSeek-V4-Pro Observed 2026-10-22T06:45:03.380Z Evidence SHA-256 `8e027ef69b8de06c4b2a8b217bfe816b1f1536269bb257fd295b4ef1ba8246ac` Source locator `/rows/5153/row` |  |  |  |  |  |  |
| [Arena text / industry writing and literature and language](https://benchize.com/benchmarks/lmarena%3Atext%3Aindustry_writing_and_literature_and_language.md) | 1,447.31 | — | 41 / 173 | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1447.3071597330218 \| rating \| reported \| Higher is better \| ### Configuration category industry_writing_and_literature_and_language config text ### Reported statistics lower 1441.0244498971617 rank 46 upper 1453.5898695688818 variance 10.275378371615481 votes 14134 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) Source Arena Original model label DeepSeek-V4-Pro Observed 2026-10-22T06:45:03.380Z Evidence SHA-256 `8e027ef69b8de06c4b2a8b217bfe816b1f1536269bb257fd295b4ef1ba8246ac` Source locator `/rows/7163/row` |  |  |  |  |  |  |
| [Arena text style control / math](https://benchize.com/benchmarks/lmarena%3Atext_style_control%3Amath.md) | 1,444.33 | — | 66 / 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` \| 1444.3286940497446 \| rating \| reported \| Higher is better \| ### Configuration category math config text_style_control ### Reported statistics lower 1433.2647379749624 rank 87 upper 1455.3926501245267 variance 31.865791028469236 votes 3068 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label DeepSeek-V4-Pro Observed 2026-10-22T06:45:03.380Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/8999/row` |  |  |  |  |  |  |
| [Arena text / industry mathematical](https://benchize.com/benchmarks/lmarena%3Atext%3Aindustry_mathematical.md) | 1,455.29 | — | 59 / 169 | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1455.285079248293 \| rating \| reported \| Higher is better \| ### Configuration category industry_mathematical config text ### Reported statistics lower 1444.4197826726406 rank 70 upper 1466.1503758239455 variance 30.731728540448966 votes 3288 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) Source Arena Original model label DeepSeek-V4-Pro Observed 2026-10-22T06:45:03.380Z Evidence SHA-256 `8e027ef69b8de06c4b2a8b217bfe816b1f1536269bb257fd295b4ef1ba8246ac` Source locator `/rows/5982/row` |  |  |  |  |  |  |
| [Arena text / industry entertainment and sports and media](https://benchize.com/benchmarks/lmarena%3Atext%3Aindustry_entertainment_and_sports_and_media.md) | 1,430.79 | — | 41 / 173 | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1430.7893021177001 \| rating \| reported \| Higher is better \| ### Configuration category industry_entertainment_and_sports_and_media config text ### Reported statistics lower 1424.2355810820593 rank 46 upper 1437.3430231533407 variance 11.180976138965482 votes 12793 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) Source Arena Original model label DeepSeek-V4-Pro Observed 2026-10-22T06:45:03.380Z Evidence SHA-256 `8e027ef69b8de06c4b2a8b217bfe816b1f1536269bb257fd295b4ef1ba8246ac` Source locator `/rows/4738/row` |  |  |  |  |  |  |
| [FinanceBenchmark v2](https://benchize.com/benchmarks/financebenchmark%3Av2.md) | 89.04% | CI 80.82–95.89% | 8 / 21 | — | [financebenchmark](https://finbenchmark.ai/) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `pass_at_1` \| 0.890411 \| score_fraction \| reported \| Higher is better \| \| `accuracy` \| 0.881279 \| score_fraction \| reported \| Higher is better \| \| `knowledge` \| 1 \| score_fraction \| category \| Higher is better \| \| `analysis` \| 1 \| score_fraction \| category \| Higher is better \| \| `quant` \| 0.533333 \| score_fraction \| category \| Higher is better \| \| `portfolio_mgmt` \| 0.833333 \| score_fraction \| category \| Higher is better \| \| `credit_underwriting` \| 1 \| score_fraction \| category \| Higher is better \| \| `banking_regulation` \| 1 \| score_fraction \| category \| Higher is better \| \| `derivatives_structuring` \| 1 \| score_fraction \| category \| Higher is better \| \| `corporate_finance` \| 1 \| score_fraction \| category \| Higher is better \| ### Configuration harnessVersion 0.2.0 Reasoning effort unknown sourceRunId 75d557a3-fd82-4cc0-960e-a57bb260a786 taskSetVersion v2 ### Reported statistics Uncertainty Confidence interval: 80.82–95.89% confidenceInterval [0.8082,0.9589] confidenceMethod percentile bootstrap over tasks, n=5000, alpha=0.05 sampleSize 73 ### Source [Original source](https://finbenchmark.ai/) Source financebenchmark Original model label deepseek-v4-pro Evaluated 2026-07-13T13:08:15.589429+00:00 Observed 2026-10-22T04:10:04.512Z Evidence SHA-256 `f9e7dab8846b092fc0befeca8c5cd02a8187c0f5b6b10c32ab2c7ab60f7af575` Source locator `/rows/8` |  |  |  |  |  |  |
| [Arena text style control / spanish](https://benchize.com/benchmarks/lmarena%3Atext_style_control%3Aspanish.md) | 1,456.72 | — | 45 / 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` \| 1456.724155576684 \| rating \| reported \| Higher is better \| ### Configuration category spanish config text_style_control ### Reported statistics lower 1441.4484498327465 rank 61 upper 1471.9998613206217 variance 60.74441946854071 votes 1732 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label DeepSeek-V4-Pro Observed 2026-10-22T06:45:03.380Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/10825/row` |  |  |  |  |  |  |
| [Arena text style control / polish](https://benchize.com/benchmarks/lmarena%3Atext_style_control%3Apolish.md) | 1,465.38 | — | 35 / 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` \| 1465.384475711231 \| rating \| reported \| Higher is better \| ### Configuration category polish config text_style_control ### Reported statistics lower 1447.2990324760042 rank 47 upper 1483.469918946458 variance 85.14558460254838 votes 1125 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label DeepSeek-V4-Pro Observed 2026-10-22T06:45:03.380Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/10194/row` |  |  |  |  |  |  |
| [Arena text / multi turn](https://benchize.com/benchmarks/lmarena%3Atext%3Amulti_turn.md) | 1,467.62 | — | 35 / 173 | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1467.6208574782954 \| rating \| reported \| Higher is better \| ### Configuration category multi_turn config text ### Reported statistics lower 1460.639141362739 rank 39 upper 1474.6025735938515 variance 12.689023153294746 votes 10355 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) Source Arena Original model label DeepSeek-V4-Pro Observed 2026-10-22T06:45:03.380Z Evidence SHA-256 `8e027ef69b8de06c4b2a8b217bfe816b1f1536269bb257fd295b4ef1ba8246ac` Source locator `/rows/9354/row` |  |  |  |  |  |  |
| [Arena text / industry software and it services](https://benchize.com/benchmarks/lmarena%3Atext%3Aindustry_software_and_it_services.md) | 1,469.07 | — | 51 / 173 | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1469.0737052435993 \| rating \| reported \| Higher is better \| ### Configuration category industry_software_and_it_services config text ### Reported statistics lower 1463.8342494435387 rank 63 upper 1474.3131610436599 variance 7.146216675004871 votes 23641 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) Source Arena Original model label DeepSeek-V4-Pro Observed 2026-10-22T06:45:03.380Z Evidence SHA-256 `8e027ef69b8de06c4b2a8b217bfe816b1f1536269bb257fd295b4ef1ba8246ac` Source locator `/rows/6763/row` |  |  |  |  |  |  |
| [HiL-Bench (Human-in-Loop Benchmark)](https://benchize.com/benchmarks/scale%3Ahil.md) | 38.46source score | CI 32.83–44.09 | 13 / 22 | — | [scale](https://labs.scale.com/leaderboard/hil) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `score` \| 38.46 \| source_score \| reported \| Higher is better \| ### Configuration Reasoning effort unknown Model configuration DeepSeek V4 Pro sourceModelVersion Not reported thinkingEnabled Not reported ### Reported statistics Uncertainty Confidence interval: 32.83–44.09 contaminationWarning Not reported rank 19 reportedConfidenceHalfWidth 5.63 ### Source [Original source](https://labs.scale.com/leaderboard/hil) Source scale Original model label DeepSeek V4 Pro Observed 2026-10-22T03:30:07.512Z Evidence SHA-256 `fb954dc9c4a01e066526b773b8a269f2c27e73cfb0f1a943ec328ecd5be154c1` Source locator `/rows/18` |  |  |  |  |  |  |
| [Arena text style control / english](https://benchize.com/benchmarks/lmarena%3Atext_style_control%3Aenglish.md) | 1,467.23 | — | 51 / 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` \| 1467.2344311596094 \| rating \| reported \| Higher is better \| ### Configuration category english config text_style_control ### Reported statistics lower 1462.1198221007942 rank 65 upper 1472.3490402184245 variance 6.809711374124985 votes 25275 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label DeepSeek-V4-Pro Observed 2026-10-22T06:45:03.380Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/1701/row` |  |  |  |  |  |  |
| [Arena text / russian](https://benchize.com/benchmarks/lmarena%3Atext%3Arussian.md) | 1,452.74 | — | 43 / 172 | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1452.7377990597743 \| rating \| reported \| Higher is better \| ### Configuration category russian config text ### Reported statistics lower 1444.5721154220926 rank 50 upper 1460.903482697456 variance 17.357569710627413 votes 6319 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) Source Arena Original model label DeepSeek-V4-Pro Observed 2026-10-22T06:45:03.380Z Evidence SHA-256 `8e027ef69b8de06c4b2a8b217bfe816b1f1536269bb257fd295b4ef1ba8246ac` Source locator `/rows/10433/row` |  |  |  |  |  |  |
| [Rapidata SVG generation — Preference](https://benchize.com/benchmarks/rapidata%3Asvg%3Arlb_1MFkkEMFnCNyKl.md) | 759.56elo | CI 741.84–777.27 | 31 / 37 | — | [rapidata · v1](https://api.rapidata.ai/benchmark/bmk_1MFkc3sXfbKCqf/standings/query?leaderboard_id%5Beq%5D=rlb_1MFkkEMFnCNyKl) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `elo` \| 759.5564448248992 \| elo \| rlb_1MFkkEMFnCNyKl \| Higher is better \| ### Configuration benchmarkId bmk_1MFkc3sXfbKCqf criterion rlb_1MFkkEMFnCNyKl participantId par_1MFlMvFnF7SJTw sourceModelVersion deepseek-v4-pro weighted false ### Reported statistics Uncertainty Confidence interval: 741.84–777.27 confidenceIntervalLowerOffset 17.713425544243933 confidenceIntervalUpperOffset 17.713425544243933 totalMatches 8986 wins 3610.5 ### Source [Original source](https://api.rapidata.ai/benchmark/bmk_1MFkc3sXfbKCqf/standings/query?leaderboard_id%5Beq%5D=rlb_1MFkkEMFnCNyKl) Source rapidata Original model label deepseek-v4-pro Source version v1 Observed 2026-10-21T16:37:40.980Z Evidence SHA-256 `b70f07a4924c82499996aba613ca8ec2d0aee9ec9ebd404e45c8bf250206cf40` Source locator `/items/55` |  |  |  |  |  |  |
| [Short Story Writing — Pairwise Comparison](https://benchize.com/benchmarks/lechmazur-short-story%3Apairwise.md) | -0.54 | 95% CI -0.65–-0.42 | 35 / 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` \| -0.5411854791095495 \| index \| pooled_observed_panel \| Higher is better \| \| `win_probability` \| 0.417394212854644 \| score_fraction \| comparison_pool \| Higher is better \| ### Configuration benchmarkScope data/writing_gemini_argon_20261013 ### Reported statistics Uncertainty 95% confidence interval: -0.65–-0.42 bootstrapSamples 300 confidenceInterval95 ["-0.6511833537397125","-0.4168640401380341"] sourceRank 35 ### 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 V4 Pro Preview Source version 8ba548d1cffefa5c472d3832e05f64e119a88fa4 Observed 2026-10-22T07:10:06.634Z Evidence SHA-256 `c36baebed9f302ff7ad8fe97907d72e1757a015a39b6a3b23437597cf8e3bff6` Source locator `/rows/34` |  |  |  |  |  |  |
| [Arena text / polish](https://benchize.com/benchmarks/lmarena%3Atext%3Apolish.md) | 1,460.81 | — | 26 / 137 | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1460.8088273487385 \| rating \| reported \| Higher is better \| ### Configuration category polish config text ### Reported statistics lower 1442.9549507620948 rank 32 upper 1478.662703935382 variance 82.97912955721937 votes 1125 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) Source Arena Original model label DeepSeek-V4-Pro Observed 2026-10-22T06:45:03.380Z Evidence SHA-256 `8e027ef69b8de06c4b2a8b217bfe816b1f1536269bb257fd295b4ef1ba8246ac` Source locator `/rows/10179/row` |  |  |  |  |  |  |
| [Long-Horizon Terminal-Bench](https://benchize.com/benchmarks/lhtb%3Aoverall.md) | 30.7% | — | 12 / 19 | $6.32 | [lhtb](https://zli12321.github.io/LHTB/script.js) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `mean_reward` \| 0.307 \| score_fraction \| reported \| Higher is better \| \| `solved_count` \| 3 \| tasks \| reward_gte_0_95 \| Higher is better \| \| `cost_per_task` \| 6.32 \| USD \| per_task \| Lower is better \| ### Configuration harness official_common_harness Reasoning effort unknown reportOrigin paper ### Reported statistics sampleSize 46 sourceThresholdCounts Not reported ### Source [Original source](https://zli12321.github.io/LHTB/script.js) Source lhtb Original model label DeepSeek V4 Pro Observed 2026-10-22T05:00:05.057Z Evidence SHA-256 `8b9c27664cc6298fa234c607ca27c953ec91b2eb9d116b8530cfaaa6722fa39e` Source locator `/rows/11` |  |  |  |  |  |  |
| [Arena text style control / industry medicine and healthcare](https://benchize.com/benchmarks/lmarena%3Atext_style_control%3Aindustry_medicine_and_healthcare.md) | 1,478.54 | — | 46 / 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` \| 1478.5410574706966 \| rating \| reported \| Higher is better \| ### Configuration category industry_medicine_and_healthcare config text_style_control ### Reported statistics lower 1468.4459814194954 rank 63 upper 1488.6361335218976 variance 26.5291300092916 votes 4058 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label DeepSeek-V4-Pro Observed 2026-10-22T06:45:03.380Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/6375/row` |  |  |  |  |  |  |
| [Arena text / instruction following](https://benchize.com/benchmarks/lmarena%3Atext%3Ainstruction_following.md) | 1,445.34 | — | 47 / 173 | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1445.3355978799682 \| rating \| reported \| Higher is better \| ### Configuration category instruction_following config text ### Reported statistics lower 1439.768441369149 rank 54 upper 1450.902754390787 variance 8.068088989785101 votes 20026 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) Source Arena Original model label DeepSeek-V4-Pro Observed 2026-10-22T06:45:03.380Z Evidence SHA-256 `8e027ef69b8de06c4b2a8b217bfe816b1f1536269bb257fd295b4ef1ba8246ac` Source locator `/rows/7587/row` |  |  |  |  |  |  |
| [Arena text / industry medicine and healthcare](https://benchize.com/benchmarks/lmarena%3Atext%3Aindustry_medicine_and_healthcare.md) | 1,465.83 | — | 35 / 173 | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1465.8273053793573 \| rating \| reported \| Higher is better \| ### Configuration category industry_medicine_and_healthcare config text ### Reported statistics lower 1455.8578120961242 rank 44 upper 1475.79679866259 variance 25.873190619408923 votes 4058 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) Source Arena Original model label DeepSeek-V4-Pro Observed 2026-10-22T06:45:03.380Z Evidence SHA-256 `8e027ef69b8de06c4b2a8b217bfe816b1f1536269bb257fd295b4ef1ba8246ac` Source locator `/rows/6356/row` |  |  |  |  |  |  |
| [DesignArena Data visualization generation](https://benchize.com/benchmarks/designarena%3Adata-viz.md) | 1,203elo | — | 48 / 99 | — | [designarena · public](https://www.designarena.ai/api/leaderboard#board=data-viz) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `elo` \| 1203 \| elo \| data-viz \| Higher is better \| ### Configuration arenaType models category dataviz inputModality Not reported sourceModelVersion deepseek-v4-pro variationName public ### Reported statistics averageGenerationTimeMs 238529 battles 1172 losses 601 standardError Not reported winRate 48.7 wins 571 ### Source [Original source](https://www.designarena.ai/api/leaderboard#board=data-viz) Source designarena Original model label DeepSeek-V4-Pro Source version public Observed 2026-10-21T16:37:58.264Z Evidence SHA-256 `a895f6f1a25fa8eb01f821c2097ddec4f884de7bd22f1b8a22e82e6679b71849` Source locator `/data/72` |  |  |  |  |  |  |
| [Arena text / hard prompts english](https://benchize.com/benchmarks/lmarena%3Atext%3Ahard_prompts_english.md) | 1,465.87 | — | 42 / 173 | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1465.8715356240104 \| rating \| reported \| Higher is better \| ### Configuration category hard_prompts_english config text ### Reported statistics lower 1460.0571728845534 rank 50 upper 1471.6858983634675 variance 8.800514503466152 votes 17839 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) Source Arena Original model label DeepSeek-V4-Pro Observed 2026-10-22T06:45:03.380Z Evidence SHA-256 `8e027ef69b8de06c4b2a8b217bfe816b1f1536269bb257fd295b4ef1ba8246ac` Source locator `/rows/3917/row` |  |  |  |  |  |  |
| [Arena text style control / industry legal and government](https://benchize.com/benchmarks/lmarena%3Atext_style_control%3Aindustry_legal_and_government.md) | 1,473.95 | — | 43 / 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` \| 1473.9481333871618 \| rating \| reported \| Higher is better \| ### Configuration category industry_legal_and_government config text_style_control ### Reported statistics lower 1464.424880850015 rank 51 upper 1483.4713859243084 variance 23.6088275625154 votes 4496 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label DeepSeek-V4-Pro Observed 2026-10-22T06:45:03.380Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/5158/row` |  |  |  |  |  |  |
| [Longform Creative Writing](https://benchize.com/benchmarks/eq-bench%3Alongform-writing.md) | 75.6% | — | 24 / 93 | — | [eq bench · longform-writing](https://eqbench.com/creative_writing_longform.js) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `overall_score_100` \| 75.6 \| percent \| overall \| Higher is better \| \| `chapter1_avg` \| 16.05 \| rubric_score \| overall \| Higher is better \| \| `chapter2_avg` \| 15.92 \| rubric_score \| overall \| Higher is better \| \| `chapter3_avg` \| 15.63 \| rubric_score \| overall \| Higher is better \| \| `chapter4_avg` \| 15.77 \| rubric_score \| overall \| Higher is better \| \| `chapter5_avg` \| 15.81 \| rubric_score \| overall \| Higher is better \| \| `chapter6_avg` \| 15.45 \| rubric_score \| overall \| Higher is better \| \| `chapter7_avg` \| 15.09 \| rubric_score \| overall \| Higher is better \| \| `chapter8_avg` \| 15.30 \| rubric_score \| overall \| Higher is better \| \| `final_judgement_avg` \| 14.88 \| rubric_score \| overall \| Higher is better \| ### Configuration interactiveAdjustments none protocol longform-writing sourceModelVersion deepseek-ai/DeepSeek-V4-Pro ### Source [Original source](https://eqbench.com/creative_writing_longform.js) Source eq bench Original model label deepseek-ai/DeepSeek-V4-Pro Source version longform-writing Observed 2026-10-22T05:10:05.903Z Evidence SHA-256 `3ba283ce357ac7620e16db640a961879c30fe3ddc50a27de9a8ed4290784825c` Source locator `/leaderboardDataLongformV3/107` |  |  |  |  |  |  |
| [Arena text style control / korean](https://benchize.com/benchmarks/lmarena%3Atext_style_control%3Akorean.md) | 1,417.06 | — | 50 / 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` \| 1417.0645393775067 \| rating \| reported \| Higher is better \| ### Configuration category korean config text_style_control ### Reported statistics lower 1398.2089834998142 rank 65 upper 1435.9200952551992 variance 92.5512947168708 votes 1110 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label DeepSeek-V4-Pro Observed 2026-10-22T06:45:03.380Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/8298/row` |  |  |  |  |  |  |
| [Arena text style control / non english](https://benchize.com/benchmarks/lmarena%3Atext_style_control%3Anon_english.md) | 1,445.06 | — | 52 / 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` \| 1445.0649064911884 \| rating \| reported \| Higher is better \| ### Configuration category non_english config text_style_control ### Reported statistics lower 1440.3485397040504 rank 65 upper 1449.7812732783264 variance 5.790538623240544 votes 32289 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label DeepSeek-V4-Pro Observed 2026-10-22T06:45:03.380Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/9795/row` |  |  |  |  |  |  |
| [Arena text / coding](https://benchize.com/benchmarks/lmarena%3Atext%3Acoding.md) | 1,469.5 | — | 54 / 173 | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1469.5031364867862 \| rating \| reported \| Higher is better \| ### Configuration category coding config text ### Reported statistics lower 1463.615623779706 rank 70 upper 1475.3906491938662 variance 9.023344383987464 votes 17137 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) Source Arena Original model label DeepSeek-V4-Pro Observed 2026-10-22T06:45:03.380Z Evidence SHA-256 `8e027ef69b8de06c4b2a8b217bfe816b1f1536269bb257fd295b4ef1ba8246ac` Source locator `/rows/879/row` |  |  |  |  |  |  |
| [DistressBench](https://benchize.com/benchmarks/scale%3Adistressbench.md) | 69.19source score | CI 67.95–70.43 | 17 / 27 | — | [scale](https://labs.scale.com/leaderboard/distressbench) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `score` \| 69.19 \| source_score \| reported \| Higher is better \| ### Configuration Reasoning effort unknown Model configuration deepseek-v4-pro sourceModelVersion deepseek-v4-pro thinkingEnabled Not reported ### Reported statistics Uncertainty Confidence interval: 67.95–70.43 contaminationWarning Not reported rank 22 reportedConfidenceHalfWidth 1.24 ### Source [Original source](https://labs.scale.com/leaderboard/distressbench) Source scale Original model label deepseek-v4-pro Observed 2026-10-22T03:30:05.896Z Evidence SHA-256 `6454425cf2678fa1119e99bffcdc827763d2b9c485395cb7aba2ef2e1f0cafbd` Source locator `/rows/21` |  |  |  |  |  |  |
| [Arena text / german](https://benchize.com/benchmarks/lmarena%3Atext%3Agerman.md) | 1,457.86 | — | 37 / 149 | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1457.8637993304724 \| rating \| reported \| Higher is better \| ### Configuration category german config text ### Reported statistics lower 1438.5706289846921 rank 45 upper 1477.156969676253 variance 96.89715271347143 votes 997 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) Source Arena Original model label DeepSeek-V4-Pro Observed 2026-10-22T06:45:03.380Z Evidence SHA-256 `8e027ef69b8de06c4b2a8b217bfe816b1f1536269bb257fd295b4ef1ba8246ac` Source locator `/rows/3181/row` |  |  |  |  |  |  |
| [Arena webdev / overall](https://benchize.com/benchmarks/lmarena%3Awebdev%3Aoverall.md) | 1,447.34 | — | 58 / 107 | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/webdev/latest) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1447.3420829340432 \| rating \| reported \| Higher is better \| ### Configuration category overall config webdev ### Reported statistics lower 1441.018615094857 rank 75 upper 1453.6655507732294 variance 10.409130327732337 votes 13979 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/webdev/latest) Source Arena Original model label DeepSeek-V4-Pro Observed 2026-10-22T06:45:03.380Z Evidence SHA-256 `f82507859808110820a4ab6df15561b8864137ddefc1f6fb0c552af2e58ea738` Source locator `/rows/74/row` |  |  |  |  |  |  |
| [Arena text / expert](https://benchize.com/benchmarks/lmarena%3Atext%3Aexpert.md) | 1,462.93 | — | 57 / 170 | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1462.934059941431 \| rating \| reported \| Higher is better \| ### Configuration category expert config text ### Reported statistics lower 1454.5636893341034 rank 68 upper 1471.3044305487585 variance 18.238671133627772 votes 5911 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) Source Arena Original model label DeepSeek-V4-Pro Observed 2026-10-22T06:45:03.380Z Evidence SHA-256 `8e027ef69b8de06c4b2a8b217bfe816b1f1536269bb257fd295b4ef1ba8246ac` Source locator `/rows/2538/row` |  |  |  |  |  |  |
| [Arena webdev / webdev](https://benchize.com/benchmarks/lmarena%3Awebdev%3Awebdev.md) | 1,447.34 | — | 58 / 107 | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/webdev/latest) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1447.3420829340432 \| rating \| reported \| Higher is better \| ### Configuration category webdev config webdev ### Reported statistics lower 1441.018615094857 rank 75 upper 1453.6655507732294 variance 10.409130327732337 votes 13979 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/webdev/latest) Source Arena Original model label DeepSeek-V4-Pro Observed 2026-10-22T06:45:03.380Z Evidence SHA-256 `f82507859808110820a4ab6df15561b8864137ddefc1f6fb0c552af2e58ea738` Source locator `/rows/286/row` |  |  |  |  |  |  |
| [DesignArena Browser game generation](https://benchize.com/benchmarks/designarena%3Agame-dev.md) | 1,229elo | — | 37 / 117 | — | [designarena · public](https://www.designarena.ai/api/leaderboard#board=game-dev) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `elo` \| 1229 \| elo \| game-dev \| Higher is better \| ### Configuration arenaType models category gamedev inputModality Not reported sourceModelVersion deepseek-v4-pro variationName public ### Reported statistics averageGenerationTimeMs 331369 battles 4413 losses 2104 standardError Not reported winRate 52.3 wins 2309 ### Source [Original source](https://www.designarena.ai/api/leaderboard#board=game-dev) Source designarena Original model label DeepSeek-V4-Pro Source version public Observed 2026-10-21T16:38:01.100Z Evidence SHA-256 `53db6a89112ce8cdf644568c666d4b8309aece764cfcedb291ffd52ae3934e30` Source locator `/data/57` |  |  |  |  |  |  |
| [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) | 1,459.67 | — | 49 / 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` \| 1459.6669113207602 \| rating \| reported \| Higher is better \| ### Configuration category industry_business_and_management_and_financial_operations config text_style_control ### Reported statistics lower 1452.9566060098398 rank 61 upper 1466.3772166316808 variance 11.721639998637498 votes 11383 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label DeepSeek-V4-Pro Observed 2026-10-22T06:45:03.380Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/4343/row` |  |  |  |  |  |  |
| [Rapidata Text-to-3D with LLM code — Overall preference](https://benchize.com/benchmarks/rapidata%3Atext-to-3d-code%3Aoverall.md) | 366.31elo | CI 352.19–380.44 | 9 / 9 | — | [rapidata](https://api.rapidata.ai/benchmark/bmk_1YVpXgN69Mv8I9/standings/query) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `elo` \| 366.31123591389337 \| elo \| overall \| Higher is better \| ### Configuration benchmarkId bmk_1YVpXgN69Mv8I9 criterion overall participantId par_1YVpXvfRUxkGSG sourceModelVersion deepseek-v4-pro weighted false ### Reported statistics Uncertainty Confidence interval: 352.19–380.44 confidenceIntervalLowerOffset 14.126113947418503 confidenceIntervalUpperOffset 14.126113947418503 totalMatches 20531.140406172453 wins 3814.0576819249895 ### Source [Original source](https://api.rapidata.ai/benchmark/bmk_1YVpXgN69Mv8I9/standings/query) Source rapidata Original model label deepseek-v4-pro Source version Observed 2026-10-21T16:37:41.757Z Evidence SHA-256 `048d6dec5a711f63fb70b09a6495cf440b0bf6f34f80156b97832c611e7a2913` Source locator `/items/13` |  |  |  |  |  |  |
| [Arena text style control / coding](https://benchize.com/benchmarks/lmarena%3Atext_style_control%3Acoding.md) | 1,500.78 | — | 61 / 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` \| 1500.7820032798056 \| rating \| reported \| Higher is better \| ### Configuration category coding config text_style_control ### Reported statistics lower 1494.8618874893477 rank 79 upper 1506.7021190702633 variance 9.123557640036111 votes 17137 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label DeepSeek-V4-Pro Observed 2026-10-22T06:45:03.380Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/888/row` |  |  |  |  |  |  |
| [EQ-Bench 4](https://benchize.com/benchmarks/eq-bench%3Aeqbench4.md) | 1,165.7elo | CI 1,157–1,175.1 | 18 / 26 | — | [eq bench · eqbench4](https://eqbench.com/eqbench4/eqbench4_data.js) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `elo` \| 1165.7 \| elo \| overall \| Higher is better \| ### Configuration protocol eqbench4 ### Reported statistics Uncertainty Confidence interval: 1,157–1,175.1 confidenceIntervalHigh 1175.1 confidenceIntervalLow 1157 scenarios 120 ### Source [Original source](https://eqbench.com/eqbench4/eqbench4_data.js) Source eq bench Original model label deepseek-v4-pro Source version eqbench4 Observed 2026-10-22T05:10:04.699Z Evidence SHA-256 `188d8ea4a393978063a6c24dff6c92ce185169827038bfa558091212a68c29d8` Source locator `/models/17` |  |  |  |  |  |  |
| [Judgemark v4](https://benchize.com/benchmarks/eq-bench%3Ajudgemark-v4.md) | 47.12% | CI 41.68–56.31% | 25 / 38 | — | [eq bench · judgemark-v4](https://eqbench.com/judgemark-v4.js) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `score` \| 0.471182 \| score_fraction \| overall \| Higher is better \| ### Configuration interactiveAdjustments none protocol judgemark-v4 sourceModelVersion deepseek-ai/DeepSeek-V4-Pro ### Reported statistics Uncertainty Confidence interval: 41.68–56.31% confidenceIntervalHigh 0.563053 confidenceIntervalLow 0.416774 ### Source [Original source](https://eqbench.com/judgemark-v4.js) Source eq bench Original model label deepseek-ai/DeepSeek-V4-Pro Source version judgemark-v4 Observed 2026-10-22T05:10:06.884Z Evidence SHA-256 `2b0d42aef4f614dd199dc38399be7b88075a919db52020c3759f190defc92a4d` Source locator `/leaderboardDataJudgemarkV4/27` |  |  |  |  |  |  |
| [Arena text / overall](https://benchize.com/benchmarks/lmarena%3Atext.md) | 1,451.35 | — | 44 / 173 | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1451.3452341889415 \| rating \| reported \| Higher is better \| ### Configuration category overall config text ### Reported statistics lower 1447.4644927405855 rank 49 upper 1455.2259756372978 variance 3.920425778836791 votes 57564 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) Source Arena Original model label DeepSeek-V4-Pro Observed 2026-10-22T06:45:03.380Z Evidence SHA-256 `8e027ef69b8de06c4b2a8b217bfe816b1f1536269bb257fd295b4ef1ba8246ac` Source locator `/rows/48/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) | 1,435.24 | — | 46 / 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` \| 1435.2412132974112 \| rating \| reported \| Higher is better \| ### Configuration category industry_entertainment_and_sports_and_media config text_style_control ### Reported statistics lower 1428.6402328640497 rank 59 upper 1441.8421937307724 variance 11.342811342110156 votes 12793 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label DeepSeek-V4-Pro Observed 2026-10-22T06:45:03.380Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/4751/row` |  |  |  |  |  |  |
| [Arena webdev / webdev-react](https://benchize.com/benchmarks/lmarena%3Awebdev%3Awebdev-react.md) | 1,440.65 | — | 59 / 97 | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/webdev/latest) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1440.6480853372093 \| rating \| reported \| Higher is better \| ### Configuration category webdev-react config webdev ### Reported statistics lower 1433.5481197067204 rank 76 upper 1447.7480509676982 variance 13.122491820702454 votes 9622 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/webdev/latest) Source Arena Original model label DeepSeek-V4-Pro Observed 2026-10-22T06:45:03.380Z Evidence SHA-256 `f82507859808110820a4ab6df15561b8864137ddefc1f6fb0c552af2e58ea738` Source locator `/rows/582/row` |  |  |  |  |  |  |
| [Rapidata Text-to-3D with LLM code — Creativity](https://benchize.com/benchmarks/rapidata%3Atext-to-3d-code%3Arlb_1YVqTDVUylKrUp.md) | 322.29elo | CI 292.4–352.18 | 9 / 9 | — | [rapidata](https://api.rapidata.ai/benchmark/bmk_1YVpXgN69Mv8I9/standings/query?leaderboard_id%5Beq%5D=rlb_1YVqTDVUylKrUp) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `elo` \| 322.2941725325677 \| elo \| rlb_1YVqTDVUylKrUp \| Higher is better \| ### Configuration benchmarkId bmk_1YVpXgN69Mv8I9 criterion rlb_1YVqTDVUylKrUp participantId par_1YVpXvfRUxkGSG sourceModelVersion deepseek-v4-pro weighted false ### Reported statistics Uncertainty Confidence interval: 292.4–352.18 confidenceIntervalLowerOffset 29.88980354798275 confidenceIntervalUpperOffset 29.889803547982865 totalMatches 4838 wins 832 ### Source [Original source](https://api.rapidata.ai/benchmark/bmk_1YVpXgN69Mv8I9/standings/query?leaderboard_id%5Beq%5D=rlb_1YVqTDVUylKrUp) Source rapidata Original model label deepseek-v4-pro Source version Observed 2026-10-21T16:37:42.177Z Evidence SHA-256 `4ce251bc655221de3fef117b85e05f775323a39098049de2bbfd4835ca2c6293` Source locator `/items/13` |  |  |  |  |  |  |
| [Arena text style control / hard prompts english](https://benchize.com/benchmarks/lmarena%3Atext_style_control%3Ahard_prompts_english.md) | 1,484.71 | — | 54 / 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` \| 1484.7122318374181 \| rating \| reported \| Higher is better \| ### Configuration category hard_prompts_english config text_style_control ### Reported statistics lower 1478.8681157276965 rank 67 upper 1490.5563479471393 variance 8.890813281641266 votes 17839 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label DeepSeek-V4-Pro Observed 2026-10-22T06:45:03.380Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/3934/row` |  |  |  |  |  |  |
| [Arena text style control / industry mathematical](https://benchize.com/benchmarks/lmarena%3Atext_style_control%3Aindustry_mathematical.md) | 1,459.8 | — | 63 / 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` \| 1459.800764898222 \| rating \| reported \| Higher is better \| ### Configuration category industry_mathematical config text_style_control ### Reported statistics lower 1448.943259656749 rank 76 upper 1470.6582701396956 variance 30.687669859575898 votes 3288 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label DeepSeek-V4-Pro Observed 2026-10-22T06:45:03.380Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/5988/row` |  |  |  |  |  |  |
| [Arena text style control / russian](https://benchize.com/benchmarks/lmarena%3Atext_style_control%3Arussian.md) | 1,460.03 | — | 47 / 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` \| 1460.030146951463 \| rating \| reported \| Higher is better \| ### Configuration category russian config text_style_control ### Reported statistics lower 1451.8298714566413 rank 59 upper 1468.2304224462841 variance 17.504943129604804 votes 6319 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label DeepSeek-V4-Pro Observed 2026-10-22T06:45:03.380Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/10442/row` |  |  |  |  |  |  |
| [Arena text style control / multi turn](https://benchize.com/benchmarks/lmarena%3Atext_style_control%3Amulti_turn.md) | 1,475.19 | — | 39 / 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` \| 1475.1903023824084 \| rating \| reported \| Higher is better \| ### Configuration category multi_turn config text_style_control ### Reported statistics lower 1468.1823552162527 rank 49 upper 1482.198249548564 variance 12.784550290911268 votes 10355 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label DeepSeek-V4-Pro Observed 2026-10-22T06:45:03.380Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/9364/row` |  |  |  |  |  |  |
| [Rapidata Text-to-3D with LLM code — Preference](https://benchize.com/benchmarks/rapidata%3Atext-to-3d-code%3Arlb_1YVpXugYHlm63x.md) | 197.27elo | CI 166–228.55 | 9 / 9 | — | [rapidata](https://api.rapidata.ai/benchmark/bmk_1YVpXgN69Mv8I9/standings/query?leaderboard_id%5Beq%5D=rlb_1YVpXugYHlm63x) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `elo` \| 197.2734708208584 \| elo \| rlb_1YVpXugYHlm63x \| Higher is better \| ### Configuration benchmarkId bmk_1YVpXgN69Mv8I9 criterion rlb_1YVpXugYHlm63x participantId par_1YVpXvfRUxkGSG sourceModelVersion deepseek-v4-pro weighted false ### Reported statistics Uncertainty Confidence interval: 166–228.55 confidenceIntervalLowerOffset 31.273349898582865 confidenceIntervalUpperOffset 31.27334989858298 totalMatches 5231 wins 756 ### Source [Original source](https://api.rapidata.ai/benchmark/bmk_1YVpXgN69Mv8I9/standings/query?leaderboard_id%5Beq%5D=rlb_1YVpXugYHlm63x) Source rapidata Original model label deepseek-v4-pro Source version Observed 2026-10-21T16:37:43.410Z Evidence SHA-256 `a30cb5e42eb353cd3fadbb4c6519873ad22d3f0528a4e569fbbe40160928d934` Source locator `/items/13` |  |  |  |  |  |  |
| [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) | 1,481.66 | — | 47 / 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` \| 1481.6602429548907 \| rating \| reported \| Higher is better \| ### Configuration category industry_life_and_physical_and_social_science config text_style_control ### Reported statistics lower 1474.5297130766003 rank 56 upper 1488.790772833181 variance 13.23571557536724 votes 9159 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label DeepSeek-V4-Pro Observed 2026-10-22T06:45:03.380Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/5553/row` |  |  |  |  |  |  |
| [Arena text / industry business and management and financial operations](https://benchize.com/benchmarks/lmarena%3Atext%3Aindustry_business_and_management_and_financial_operations.md) | 1,443.23 | — | 45 / 173 | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1443.2295923844001 \| rating \| reported \| Higher is better \| ### Configuration category industry_business_and_management_and_financial_operations config text ### Reported statistics lower 1436.570749085618 rank 51 upper 1449.8884356831825 variance 11.542540515825344 votes 11383 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) Source Arena Original model label DeepSeek-V4-Pro Observed 2026-10-22T06:45:03.380Z Evidence SHA-256 `8e027ef69b8de06c4b2a8b217bfe816b1f1536269bb257fd295b4ef1ba8246ac` Source locator `/rows/4333/row` |  |  |  |  |  |  |
| [Humanity's Last Exam (Diamond)](https://benchize.com/benchmarks/scale%3Ahle-diamond.md) | 13.4source score | CI 11.3–15.5 | 12 / 12 | — | [scale](https://labs.scale.com/leaderboard/hle-diamond) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `score` \| 13.4 \| source_score \| reported \| Higher is better \| ### Configuration Reasoning effort unknown Model configuration deepseek-v4-pro sourceModelVersion Not reported thinkingEnabled Not reported ### Reported statistics Uncertainty Confidence interval: 11.3–15.5 contaminationWarning Potential contamination warning: This model was evaluated after the public release of HLE, allowing model builder access to the prompts and solutions. rank 16 reportedConfidenceHalfWidth 2.1 ### Source [Original source](https://labs.scale.com/leaderboard/hle-diamond) Source scale Original model label deepseek-v4-pro Observed 2026-10-22T03:30:06.135Z Evidence SHA-256 `725a028d7a2253d81e4e8eaa384d73b97c6deb0fbfdb0627f1b5411d3b278a2d` Source locator `/rows/15` |  |  |  |  |  |  |
| [Arena text / creative writing](https://benchize.com/benchmarks/lmarena%3Atext%3Acreative_writing.md) | 1,446.24 | — | 34 / 173 | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1446.240952175531 \| rating \| reported \| Higher is better \| ### Configuration category creative_writing config text ### Reported statistics lower 1439.0344119859205 rank 37 upper 1453.4474923651417 variance 13.51940081322783 votes 9724 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) Source Arena Original model label DeepSeek-V4-Pro Observed 2026-10-22T06:45:03.380Z Evidence SHA-256 `8e027ef69b8de06c4b2a8b217bfe816b1f1536269bb257fd295b4ef1ba8246ac` Source locator `/rows/1258/row` |  |  |  |  |  |  |
| [LiveBench](https://benchize.com/benchmarks/livebench%3Atasks.md) | 98% | — | 1 / 10 | — | [LiveBench](https://api.github.com/repos/LiveBench/livebench.github.io/contents/public/table_2026_06_25.csv?ref=19e766a5de4de07d672ed5bf9f0a69ceed1d39bf) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `AMPS_Hard` \| 98 \| percent \| reported \| Higher is better \| \| `code_completion` \| 69.565 \| percent \| reported \| Higher is better \| \| `code_generation` \| 70.423 \| percent \| reported \| Higher is better \| \| `connections` \| 98 \| percent \| reported \| Higher is better \| \| `consecutive_events` \| 75.421 \| percent \| reported \| Higher is better \| \| `integrals_with_game` \| 78 \| percent \| reported \| Higher is better \| \| `javascript` \| 54.545 \| percent \| reported \| Higher is better \| \| `logic_with_navigation` \| 64 \| percent \| reported \| Higher is better \| \| `math_comp` \| 96.078 \| percent \| reported \| Higher is better \| \| `olympiad` \| 90.624 \| percent \| reported \| Higher is better \| \| `paraphrase` \| 56.217 \| percent \| reported \| Higher is better \| \| `plot_unscrambling` \| 56.391 \| percent \| reported \| Higher is better \| \| `python` \| 50 \| percent \| reported \| Higher is better \| \| `simplify` \| 55.933 \| percent \| reported \| Higher is better \| \| `spatial` \| 94 \| percent \| reported \| Higher is better \| \| `story_generation` \| 67.75 \| percent \| reported \| Higher is better \| \| `summarize` \| 69.5 \| percent \| reported \| Higher is better \| \| `tablejoin` \| 48.192 \| percent \| reported \| Higher is better \| \| `tablereformat` \| 100 \| percent \| reported \| Higher is better \| \| `theory_of_mind` \| 80.769 \| percent \| reported \| Higher is better \| \| `typescript` \| 23.333 \| percent \| reported \| Higher is better \| \| `typos` \| 80 \| percent \| reported \| Higher is better \| \| `zebra_puzzle` \| 92 \| percent \| reported \| Higher is better \| ### Configuration Model configuration deepseek-v4-pro sourceRelease 2026_06_25 ### Source [Original source](https://api.github.com/repos/LiveBench/livebench.github.io/contents/public/table_2026_06_25.csv?ref=19e766a5de4de07d672ed5bf9f0a69ceed1d39bf) Source LiveBench Original model label deepseek-v4-pro Observed 2026-10-21T16:40:05.068Z Evidence SHA-256 `f0330164423abf9803631fc5b2f2b5427f17c0161c12e15021bb0f9781d2afa8` Source locator `/rows/8` |  |  |  |  |  |  |
| [Arena text style control / expert](https://benchize.com/benchmarks/lmarena%3Atext_style_control%3Aexpert.md) | 1,479.4 | — | 63 / 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` \| 1479.3953864167943 \| rating \| reported \| Higher is better \| ### Configuration category expert config text_style_control ### Reported statistics lower 1470.9909339385072 rank 76 upper 1487.7998388950812 variance 18.387499321682903 votes 5911 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label DeepSeek-V4-Pro Observed 2026-10-22T06:45:03.380Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/2546/row` |  |  |  |  |  |  |
| [Rapidata Text-to-3D with LLM code — Coherence](https://benchize.com/benchmarks/rapidata%3Atext-to-3d-code%3Arlb_1YVpXufudyOLlc.md) | 526.1elo | CI 500.85–551.35 | 9 / 9 | — | [rapidata](https://api.rapidata.ai/benchmark/bmk_1YVpXgN69Mv8I9/standings/query?leaderboard_id%5Beq%5D=rlb_1YVpXufudyOLlc) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `elo` \| 526.100778957634 \| elo \| rlb_1YVpXufudyOLlc \| Higher is better \| ### Configuration benchmarkId bmk_1YVpXgN69Mv8I9 criterion rlb_1YVpXufudyOLlc participantId par_1YVpXvfRUxkGSG sourceModelVersion deepseek-v4-pro weighted false ### Reported statistics Uncertainty Confidence interval: 500.85–551.35 confidenceIntervalLowerOffset 25.253522009176947 confidenceIntervalUpperOffset 25.253522009177004 totalMatches 5231 wins 1278 ### Source [Original source](https://api.rapidata.ai/benchmark/bmk_1YVpXgN69Mv8I9/standings/query?leaderboard_id%5Beq%5D=rlb_1YVpXufudyOLlc) Source rapidata Original model label deepseek-v4-pro Source version Observed 2026-10-21T16:37:42.585Z Evidence SHA-256 `59243752590bb5f22389edbe87b8cc11b00e9a6fc49b5b94753544fc8780e58d` Source locator `/items/13` |  |  |  |  |  |  |
| [Arena text style control / longer query](https://benchize.com/benchmarks/lmarena%3Atext_style_control%3Alonger_query.md) | 1,471.98 | — | 49 / 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` \| 1471.982395188158 \| rating \| reported \| Higher is better \| ### Configuration category longer_query config text_style_control ### Reported statistics lower 1466.660884635109 rank 58 upper 1477.3039057412072 variance 7.371802194952772 votes 25924 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label DeepSeek-V4-Pro Observed 2026-10-22T06:45:03.380Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/8575/row` |  |  |  |  |  |  |
| [Rapidata SVG generation — Overall preference](https://benchize.com/benchmarks/rapidata%3Asvg%3Aoverall.md) | 758.15elo | CI 748.08–768.21 | 34 / 37 | — | [rapidata · v1](https://api.rapidata.ai/benchmark/bmk_1MFkc3sXfbKCqf/standings/query) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `elo` \| 758.1477366049747 \| elo \| overall \| Higher is better \| ### Configuration benchmarkId bmk_1MFkc3sXfbKCqf criterion overall participantId par_1MFlMvFnF7SJTw sourceModelVersion deepseek-v4-pro weighted false ### Reported statistics Uncertainty Confidence interval: 748.08–768.21 confidenceIntervalLowerOffset 10.06421537601284 confidenceIntervalUpperOffset 10.06421537601284 totalMatches 26815.936043033085 wins 10301.265691544846 ### Source [Original source](https://api.rapidata.ai/benchmark/bmk_1MFkc3sXfbKCqf/standings/query) Source rapidata Original model label deepseek-v4-pro Source version v1 Observed 2026-10-21T16:37:39.078Z Evidence SHA-256 `4b73ff7e4ca0ecfd64f7888c2d64f3398a058c945c4644acd54eddb330e16d66` Source locator `/items/58` |  |  |  |  |  |  |
| [SimpleBench](https://benchize.com/benchmarks/simplebench%3Aavg-at-5.md) | 50.9% | — | 33 / 62 | — | [simplebench](https://simple-bench.com/static/js/leaderboard-data.js) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 50.9 \| percent \| average_at_5 \| Higher is better \| ### Configuration Reasoning effort unknown Model configuration DeepSeek V4 Pro thinkingEnabled Not reported ### Reported statistics rank 54th ### Source [Original source](https://simple-bench.com/static/js/leaderboard-data.js) Source simplebench Original model label DeepSeek V4 Pro Observed 2026-10-22T03:40:04.693Z Evidence SHA-256 `b2d0285ad3e4e15750ed20d39897e7558d1c05e8962e90c861b06f93c8019dc9` Source locator `/rows/55` |  |  |  |  |  |  |
| [EQ-Bench 3](https://benchize.com/benchmarks/eq-bench%3Aeqbench3.md) | 1,570.2elo | CI 1,540.2–1,600.3 | 7 / 50 | — | [eq bench · eqbench3](https://eqbench.com/eqbench3.js) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `elo_norm` \| 1570.2 \| elo \| overall \| Higher is better \| \| `rubric_0_100` \| 77.6 \| percent \| overall \| Higher is better \| ### Configuration interactiveAdjustments none protocol eqbench3 sourceModelVersion deepseek-ai/DeepSeek-V4-Pro ### Reported statistics Uncertainty Confidence interval: 1,540.2–1,600.3 confidenceIntervalHigh 1600.3 confidenceIntervalLow 1540.2 ### Source [Original source](https://eqbench.com/eqbench3.js) Source eq bench Original model label deepseek-ai/DeepSeek-V4-Pro Source version eqbench3 Observed 2026-10-22T05:10:04.922Z Evidence SHA-256 `3672ff093e739f07ff664a2e6013bc38a6977a146e4092b4cef80ba1780542b2` Source locator `/leaderboardDataEQBench3/8` |  |  |  |  |  |  |

---
Cite as: DeepSeek V4 Pro — Benchize, https://benchize.com/models/deepseek-v4-pro (retrieved 2026-10-22)