# DeepSeek V4 Flash

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

DeepSeek

Canonical URL: https://benchize.com/models/deepseek-v4-flash
Last updated: Wed, 21 Oct 2026 18:52:20 GMT

Reproduction and quotation must name Benchize, link to the canonical HTML URL, and retain individual source citations.

DeepSeek

## Benchmarks

| Benchmark | Score | ± | Rank | Cost | Source |  |
| --- | --- | --- | --- | --- | --- | --- |
| [Arena text / multi turn](https://benchize.com/benchmarks/lmarena%3Atext%3Amulti_turn.md) | 1,448.71 | — | 46 / 151 | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1448.7122492686299 \| rating \| reported \| Higher is better \| ### Configuration category multi_turn config text ### Reported statistics lower 1441.4747767978783 rank 68 upper 1455.9497217393814 variance 13.63570721693216 votes 9346 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) Source Arena Original model label DeepSeek-V4-Flash Observed 2026-10-21T18:45:05.190Z Evidence SHA-256 `8e027ef69b8de06c4b2a8b217bfe816b1f1536269bb257fd295b4ef1ba8246ac` Source locator `/rows/9383/row` |  |  |  |  |  |  |
| [TubeLab Scriptwriting](https://benchize.com/benchmarks/tubelab%3Ascriptwriting.md) | 75.9% | — | 11 / 16 | 0.05ratio | [tubelab](https://tubelab.net/_next/static/chunks/pages/benchmark/scriptwriting-7ad7196ff3093ad4.js) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `quality` \| 75.9 \| percent \| source_reported \| Higher is better \| \| `craft` \| 77.7 \| percent \| source_reported \| Higher is better \| \| `relative_cost_per_script` \| 0.05 \| ratio \| source_reported \| Lower is better \| \| `script_time` \| 8.9 \| minutes \| source_reported \| Lower is better \| \| `hook` \| 7.9 \| score_out_of_10 \| craft_rubric \| Higher is better \| \| `retention` \| 7.6 \| score_out_of_10 \| craft_rubric \| Higher is better \| \| `storytelling` \| 7.3 \| score_out_of_10 \| craft_rubric \| Higher is better \| \| `voiceMatch` \| 7.2 \| score_out_of_10 \| craft_rubric \| Higher is better \| \| `pacing` \| 7.7 \| score_out_of_10 \| craft_rubric \| Higher is better \| \| `clarity` \| 8.9 \| score_out_of_10 \| craft_rubric \| Higher is better \| ### Configuration judgingProtocol blind_model_judges Reasoning effort unknown taskCount 12 ### Reported statistics confidence {"high":80.7,"low":70.1} headToHead {"losses":5,"ties":3,"winPercent":42,"wins":2} rank 16 ### Source [Original source](https://tubelab.net/_next/static/chunks/pages/benchmark/scriptwriting-7ad7196ff3093ad4.js) Source tubelab Original model label DeepSeek V4 Flash Observed 2026-10-21T16:34:03.856Z Evidence SHA-256 `72f9d867f388256af8fc6dca12e8c7b6f1ddcbb97f0712da339b73102686761f` Source locator `/rows/15` |  |  |  |  |  |  |
| [Arena text style control / creative writing](https://benchize.com/benchmarks/lmarena%3Atext_style_control%3Acreative_writing.md) | 1,408.13 | — | 56 / 151 | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1408.1267374993113 \| rating \| reported \| Higher is better \| ### Configuration category creative_writing config text_style_control ### Reported statistics lower 1400.6147159054726 rank 95 upper 1415.63875909315 variance 14.689853792602085 votes 8580 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label DeepSeek-V4-Flash Observed 2026-10-21T18:45:05.190Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/1316/row` |  |  |  |  |  |  |
| [Rapidata SVG generation — Alignment](https://benchize.com/benchmarks/rapidata%3Asvg%3Arlb_1MFkk9yZHssERh.md) | 783.83elo | CI 769.47–798.19 | 31 / 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` \| 783.8301151614864 \| elo \| rlb_1MFkk9yZHssERh \| Higher is better \| ### Configuration benchmarkId bmk_1MFkc3sXfbKCqf criterion rlb_1MFkk9yZHssERh participantId par_1MFlJRdB8cayLk sourceModelVersion deepseek-v4-flash weighted false ### Reported statistics Uncertainty Confidence interval: 769.47–798.19 confidenceIntervalLowerOffset 14.361952492437581 confidenceIntervalUpperOffset 14.361952492437467 totalMatches 13598 wins 6060.5 ### 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-flash Source version v1 Observed 2026-10-21T16:37:40.342Z Evidence SHA-256 `2f5c8d08728735790b500d930d71b66f04253f1209f7c1c3da0db0846c163fcf` Source locator `/items/55` |  |  |  |  |  |  |
| [Judgemark v4](https://benchize.com/benchmarks/eq-bench%3Ajudgemark-v4.md) | 36.79% | CI 34.08–45.05% | 30 / 38 | — | [eq bench · judgemark-v4](https://eqbench.com/judgemark-v4.js) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `score` \| 0.367862 \| score_fraction \| overall \| Higher is better \| ### Configuration interactiveAdjustments none protocol judgemark-v4 sourceModelVersion deepseek-ai/DeepSeek-V4-Flash ### Reported statistics Uncertainty Confidence interval: 34.08–45.05% confidenceIntervalHigh 0.450511 confidenceIntervalLow 0.340758 ### Source [Original source](https://eqbench.com/judgemark-v4.js) Source eq bench Original model label deepseek-ai/DeepSeek-V4-Flash Source version judgemark-v4 Observed 2026-10-21T16:35:03.901Z Evidence SHA-256 `2b0d42aef4f614dd199dc38399be7b88075a919db52020c3759f190defc92a4d` Source locator `/leaderboardDataJudgemarkV4/32` |  |  |  |  |  |  |
| [Arena text / chinese](https://benchize.com/benchmarks/lmarena%3Atext%3Achinese.md) | 1,462.92 | — | 63 / 146 | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1462.924407882446 \| rating \| reported \| Higher is better \| ### Configuration category chinese config text ### Reported statistics lower 1451.64635104496 rank 102 upper 1474.2024647199319 variance 33.11100599187983 votes 3008 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) Source Arena Original model label DeepSeek-V4-Flash Observed 2026-10-21T18:45:05.190Z Evidence SHA-256 `8e027ef69b8de06c4b2a8b217bfe816b1f1536269bb257fd295b4ef1ba8246ac` Source locator `/rows/518/row` |  |  |  |  |  |  |
| [Arena text / coding](https://benchize.com/benchmarks/lmarena%3Atext%3Acoding.md) | 1,456.84 | — | 56 / 151 | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1456.840610137647 \| rating \| reported \| Higher is better \| ### Configuration category coding config text ### Reported statistics lower 1450.677737528677 rank 89 upper 1463.0034827466172 variance 9.887128970324671 votes 15284 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) Source Arena Original model label DeepSeek-V4-Flash Observed 2026-10-21T18:45:05.190Z Evidence SHA-256 `8e027ef69b8de06c4b2a8b217bfe816b1f1536269bb257fd295b4ef1ba8246ac` Source locator `/rows/898/row` |  |  |  |  |  |  |
| [Rapidata SVG generation — Coherence](https://benchize.com/benchmarks/rapidata%3Asvg%3Arlb_1MFkkBzpuU8fTG.md) | 824.09elo | CI 810.15–838.02 | 30 / 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` \| 824.0854688156561 \| elo \| rlb_1MFkkBzpuU8fTG \| Higher is better \| ### Configuration benchmarkId bmk_1MFkc3sXfbKCqf criterion rlb_1MFkkBzpuU8fTG participantId par_1MFlJRdB8cayLk sourceModelVersion deepseek-v4-flash weighted false ### Reported statistics Uncertainty Confidence interval: 810.15–838.02 confidenceIntervalLowerOffset 13.936427696304122 confidenceIntervalUpperOffset 13.936427696304236 totalMatches 13316 wins 5490.5 ### 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-flash Source version v1 Observed 2026-10-21T16:37:39.715Z Evidence SHA-256 `aa3cb94ff16f544c58adeea35b9087d281c785058b8ce1ae0f98a7ff84920930` Source locator `/items/56` |  |  |  |  |  |  |
| [EQ-Bench 3](https://benchize.com/benchmarks/eq-bench%3Aeqbench3.md) | 1,491.3elo | CI 1,460–1,522.7 | 18 / 50 | — | [eq bench · eqbench3](https://eqbench.com/eqbench3.js) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `elo_norm` \| 1491.3 \| elo \| overall \| Higher is better \| \| `rubric_0_100` \| 72.5 \| percent \| overall \| Higher is better \| ### Configuration interactiveAdjustments none protocol eqbench3 sourceModelVersion deepseek-ai/DeepSeek-V4-Flash ### Reported statistics Uncertainty Confidence interval: 1,460–1,522.7 confidenceIntervalHigh 1522.7 confidenceIntervalLow 1460.0 ### Source [Original source](https://eqbench.com/eqbench3.js) Source eq bench Original model label deepseek-ai/DeepSeek-V4-Flash Source version eqbench3 Observed 2026-10-21T16:35:00.608Z Evidence SHA-256 `3672ff093e739f07ff664a2e6013bc38a6977a146e4092b4cef80ba1780542b2` Source locator `/leaderboardDataEQBench3/24` |  |  |  |  |  |  |
| [Arena text / polish](https://benchize.com/benchmarks/lmarena%3Atext%3Apolish.md) | 1,435.61 | — | 43 / 117 | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1435.6095734591763 \| rating \| reported \| Higher is better \| ### Configuration category polish config text ### Reported statistics lower 1416.968907783026 rank 70 upper 1454.2502391353264 variance 90.45376589178696 votes 1026 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) Source Arena Original model label DeepSeek-V4-Flash Observed 2026-10-21T18:45:05.190Z Evidence SHA-256 `8e027ef69b8de06c4b2a8b217bfe816b1f1536269bb257fd295b4ef1ba8246ac` Source locator `/rows/10217/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) | 1,415.73 | — | 61 / 151 | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1415.7279693352928 \| rating \| reported \| Higher is better \| ### Configuration category industry_writing_and_literature_and_language config text_style_control ### Reported statistics lower 1409.1939442891576 rank 100 upper 1422.2619943814277 variance 11.113872436567457 votes 12606 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label DeepSeek-V4-Flash Observed 2026-10-21T18:45:05.190Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/7217/row` |  |  |  |  |  |  |
| [DesignArena Website generation](https://benchize.com/benchmarks/designarena%3Awebsite.md) | 1,208elo | — | 49 / 123 | — | [designarena · public](https://www.designarena.ai/api/leaderboard#board=website) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `elo` \| 1208 \| elo \| website \| Higher is better \| ### Configuration arenaType models category website inputModality text sourceModelVersion deepseek-v4-flash variationName public ### Reported statistics averageGenerationTimeMs 143731 battles 13462 losses 6854 standardError Not reported winRate 49.1 wins 6608 ### Source [Original source](https://www.designarena.ai/api/leaderboard#board=website) Source designarena Original model label DeepSeek-V4-Flash Source version public Observed 2026-10-21T16:37:57.757Z Evidence SHA-256 `51873e97776a3c5ae706b24cc2c60384793dd18398df970e213a8e7c276d8ac0` Source locator `/data/80` |  |  |  |  |  |  |
| [HiL-Bench (Human-in-Loop Benchmark)](https://benchize.com/benchmarks/scale%3Ahil.md) | 47.81source score | CI 42.14–53.48 | 9 / 22 | — | [scale](https://labs.scale.com/leaderboard/hil) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `score` \| 47.81 \| source_score \| reported \| Higher is better \| ### Configuration Reasoning effort unknown Model configuration DeepSeek V4 Flash sourceModelVersion Not reported thinkingEnabled Not reported ### Reported statistics Uncertainty Confidence interval: 42.14–53.48 contaminationWarning Not reported rank 12 reportedConfidenceHalfWidth 5.67 ### Source [Original source](https://labs.scale.com/leaderboard/hil) Source scale Original model label DeepSeek V4 Flash Observed 2026-10-21T16:35:30.082Z Evidence SHA-256 `043a333e27453edada150667c7f4439b2aab463f37928c2153c6aa79f33dd1b2` Source locator `/rows/11` |  |  |  |  |  |  |
| [Rapidata SVG generation — Overall preference](https://benchize.com/benchmarks/rapidata%3Asvg%3Aoverall.md) | 796.38elo | CI 788.31–804.46 | 32 / 37 | — | [rapidata · v1](https://api.rapidata.ai/benchmark/bmk_1MFkc3sXfbKCqf/standings/query) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `elo` \| 796.3821235455364 \| elo \| overall \| Higher is better \| ### Configuration benchmarkId bmk_1MFkc3sXfbKCqf criterion overall participantId par_1MFlJRdB8cayLk sourceModelVersion deepseek-v4-flash weighted false ### Reported statistics Uncertainty Confidence interval: 788.31–804.46 confidenceIntervalLowerOffset 8.076534550411907 confidenceIntervalUpperOffset 8.076534550411907 totalMatches 40519.70308336141 wins 17477.310681950374 ### Source [Original source](https://api.rapidata.ai/benchmark/bmk_1MFkc3sXfbKCqf/standings/query) Source rapidata Original model label deepseek-v4-flash Source version v1 Observed 2026-10-21T16:37:39.078Z Evidence SHA-256 `4b73ff7e4ca0ecfd64f7888c2d64f3398a058c945c4644acd54eddb330e16d66` Source locator `/items/56` |  |  |  |  |  |  |
| [Arena text / industry medicine and healthcare](https://benchize.com/benchmarks/lmarena%3Atext%3Aindustry_medicine_and_healthcare.md) | 1,448.1 | — | 46 / 151 | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1448.0992081536929 \| rating \| reported \| Higher is better \| ### Configuration category industry_medicine_and_healthcare config text ### Reported statistics lower 1437.7100608503574 rank 77 upper 1458.4883554570283 variance 28.097237723584744 votes 3677 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) Source Arena Original model label DeepSeek-V4-Flash Observed 2026-10-21T18:45:05.190Z Evidence SHA-256 `8e027ef69b8de06c4b2a8b217bfe816b1f1536269bb257fd295b4ef1ba8246ac` Source locator `/rows/6389/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) | 1,404.56 | — | 61 / 151 | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1404.564096256085 \| rating \| reported \| Higher is better \| ### Configuration category industry_entertainment_and_sports_and_media config text_style_control ### Reported statistics lower 1397.649288175479 rank 102 upper 1411.4789043366907 variance 12.446982519774425 votes 11209 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label DeepSeek-V4-Flash Observed 2026-10-21T18:45:05.190Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/4794/row` |  |  |  |  |  |  |
| [Arena text style control / spanish](https://benchize.com/benchmarks/lmarena%3Atext_style_control%3Aspanish.md) | 1,431.86 | — | 61 / 134 | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1431.8643490595873 \| rating \| reported \| Higher is better \| ### Configuration category spanish config text_style_control ### Reported statistics lower 1415.8253110591563 rank 102 upper 1447.9033870600183 variance 66.96693938080038 votes 1580 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label DeepSeek-V4-Flash Observed 2026-10-21T18:45:05.190Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/10866/row` |  |  |  |  |  |  |
| [Arena text / overall](https://benchize.com/benchmarks/lmarena%3Atext.md) | 1,432 | — | 56 / 151 | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1432.0007953071622 \| rating \| reported \| Higher is better \| ### Configuration category overall config text ### Reported statistics lower 1427.980895305358 rank 92 upper 1436.0206953089664 variance 4.20663002749192 votes 51959 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) Source Arena Original model label DeepSeek-V4-Flash Observed 2026-10-21T18:45:05.190Z Evidence SHA-256 `8e027ef69b8de06c4b2a8b217bfe816b1f1536269bb257fd295b4ef1ba8246ac` Source locator `/rows/91/row` |  |  |  |  |  |  |
| [Longform Creative Writing](https://benchize.com/benchmarks/eq-bench%3Alongform-writing.md) | 66% | — | 43 / 93 | — | [eq bench · longform-writing](https://eqbench.com/creative_writing_longform.js) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `overall_score_100` \| 66.0 \| percent \| overall \| Higher is better \| \| `chapter1_avg` \| 15.23 \| rubric_score \| overall \| Higher is better \| \| `chapter2_avg` \| 14.63 \| rubric_score \| overall \| Higher is better \| \| `chapter3_avg` \| 13.71 \| rubric_score \| overall \| Higher is better \| \| `chapter4_avg` \| 13.27 \| rubric_score \| overall \| Higher is better \| \| `chapter5_avg` \| 12.98 \| rubric_score \| overall \| Higher is better \| \| `chapter6_avg` \| 12.25 \| rubric_score \| overall \| Higher is better \| \| `chapter7_avg` \| 11.95 \| rubric_score \| overall \| Higher is better \| \| `chapter8_avg` \| 12.78 \| rubric_score \| overall \| Higher is better \| \| `final_judgement_avg` \| 12.15 \| rubric_score \| overall \| Higher is better \| ### Configuration interactiveAdjustments none protocol longform-writing sourceModelVersion deepseek-ai/DeepSeek-V4-Flash ### Source [Original source](https://eqbench.com/creative_writing_longform.js) Source eq bench Original model label deepseek-ai/DeepSeek-V4-Flash Source version longform-writing Observed 2026-10-21T16:35:02.575Z Evidence SHA-256 `3ba283ce357ac7620e16db640a961879c30fe3ddc50a27de9a8ed4290784825c` Source locator `/leaderboardDataLongformV3/109` |  |  |  |  |  |  |
| [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) | 1,456.29 | — | 59 / 151 | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1456.286174643388 \| rating \| reported \| Higher is better \| ### Configuration category industry_life_and_physical_and_social_science config text_style_control ### Reported statistics lower 1448.917975620106 rank 97 upper 1463.6543736666702 variance 14.13274471516661 votes 8396 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label DeepSeek-V4-Flash Observed 2026-10-21T18:45:05.190Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/5594/row` |  |  |  |  |  |  |
| [Arena text style control / exclude ties](https://benchize.com/benchmarks/lmarena%3Atext_style_control%3Aexclude_ties.md) | 1,431.61 | — | 64 / 151 | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1431.611119698623 \| rating \| reported \| Higher is better \| ### Configuration category exclude_ties config text_style_control ### Reported statistics lower 1426.3166067359325 rank 105 upper 1436.9056326613133 variance 7.29719328529252 votes 39307 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label DeepSeek-V4-Flash Observed 2026-10-21T18:45:05.190Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/2158/row` |  |  |  |  |  |  |
| [Arena text style control / english](https://benchize.com/benchmarks/lmarena%3Atext_style_control%3Aenglish.md) | 1,445.23 | — | 64 / 151 | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1445.230840604225 \| rating \| reported \| Higher is better \| ### Configuration category english config text_style_control ### Reported statistics lower 1439.958908073838 rank 107 upper 1450.502773134612 variance 7.23508279074299 votes 23119 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label DeepSeek-V4-Flash Observed 2026-10-21T18:45:05.190Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/1743/row` |  |  |  |  |  |  |
| [Arena text style control / industry mathematical](https://benchize.com/benchmarks/lmarena%3Atext_style_control%3Aindustry_mathematical.md) | 1,434.23 | — | 72 / 148 | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1434.2257742131615 \| rating \| reported \| Higher is better \| ### Configuration category industry_mathematical config text_style_control ### Reported statistics lower 1422.8055414584028 rank 118 upper 1445.6460069679201 variance 33.95109052588893 votes 2972 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label DeepSeek-V4-Flash Observed 2026-10-21T18:45:05.190Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/6030/row` |  |  |  |  |  |  |
| [Arena text / industry entertainment and sports and media](https://benchize.com/benchmarks/lmarena%3Atext%3Aindustry_entertainment_and_sports_and_media.md) | 1,399.78 | — | 56 / 151 | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1399.7792125456067 \| rating \| reported \| Higher is better \| ### Configuration category industry_entertainment_and_sports_and_media config text ### Reported statistics lower 1392.9218785634214 rank 94 upper 1406.636546527792 variance 12.24093021378174 votes 11209 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) Source Arena Original model label DeepSeek-V4-Flash Observed 2026-10-21T18:45:05.190Z Evidence SHA-256 `8e027ef69b8de06c4b2a8b217bfe816b1f1536269bb257fd295b4ef1ba8246ac` Source locator `/rows/4786/row` |  |  |  |  |  |  |
| [Creative Writing v3](https://benchize.com/benchmarks/eq-bench%3Acreative-writing-v3.md) | 1,559.1elo | — | 44 / 90 | — | [eq bench · creative-writing-v3](https://eqbench.com/creative_writing.js) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `elo_score` \| 1559.1 \| elo \| overall \| Higher is better \| \| `creative_writing_score` \| 16.29 \| rubric_score \| overall \| Higher is better \| ### Configuration interactiveAdjustments none protocol creative-writing-v3 sourceModelVersion deepseek-ai/DeepSeek-V4-Flash ### Source [Original source](https://eqbench.com/creative_writing.js) Source eq bench Original model label deepseek-ai/DeepSeek-V4-Flash Source version creative-writing-v3 Observed 2026-10-21T16:35:01.421Z Evidence SHA-256 `722ddb132e8d3a5e5c39b8d445f8475f3f7e24893a007260c6f3e3cce5c1ee18` Source locator `/leaderboardDataCreativeWritingV3/54` |  |  |  |  |  |  |
| [Arena text / korean](https://benchize.com/benchmarks/lmarena%3Atext%3Akorean.md) | 1,383.34 | — | 53 / 124 | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1383.341165473292 \| rating \| reported \| Higher is better \| ### Configuration category korean config text ### Reported statistics lower 1362.4609102246477 rank 91 upper 1404.2214207219363 variance 113.49465908624705 votes 896 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) Source Arena Original model label DeepSeek-V4-Flash Observed 2026-10-21T18:45:05.190Z Evidence SHA-256 `8e027ef69b8de06c4b2a8b217bfe816b1f1536269bb257fd295b4ef1ba8246ac` Source locator `/rows/8324/row` |  |  |  |  |  |  |
| [Arena text style control / longer query](https://benchize.com/benchmarks/lmarena%3Atext_style_control%3Alonger_query.md) | 1,447.71 | — | 60 / 150 | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1447.7129913721803 \| rating \| reported \| Higher is better \| ### Configuration category longer_query config text_style_control ### Reported statistics lower 1442.1573206994776 rank 94 upper 1453.2686620448833 variance 8.034832094842669 votes 23342 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label DeepSeek-V4-Flash Observed 2026-10-21T18:45:05.190Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/8611/row` |  |  |  |  |  |  |
| [Arena text style control / german](https://benchize.com/benchmarks/lmarena%3Atext_style_control%3Agerman.md) | 1,425.57 | — | 58 / 129 | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1425.5709785779309 \| rating \| reported \| Higher is better \| ### Configuration category german config text_style_control ### Reported statistics lower 1404.3521514580343 rank 104 upper 1446.7898056978277 variance 117.20511538965502 votes 840 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label DeepSeek-V4-Flash Observed 2026-10-21T18:45:05.190Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/3240/row` |  |  |  |  |  |  |
| [Arena text / english](https://benchize.com/benchmarks/lmarena%3Atext%3Aenglish.md) | 1,440.85 | — | 56 / 151 | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1440.8471545530272 \| rating \| reported \| Higher is better \| ### Configuration category english config text ### Reported statistics lower 1435.5885314093714 rank 93 upper 1446.1057776966832 variance 7.19859789151599 votes 23119 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) Source Arena Original model label DeepSeek-V4-Flash Observed 2026-10-21T18:45:05.190Z Evidence SHA-256 `8e027ef69b8de06c4b2a8b217bfe816b1f1536269bb257fd295b4ef1ba8246ac` Source locator `/rows/1729/row` |  |  |  |  |  |  |
| [Arena text style control / non english](https://benchize.com/benchmarks/lmarena%3Atext_style_control%3Anon_english.md) | 1,422.75 | — | 65 / 151 | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1422.7509856375762 \| rating \| reported \| Higher is better \| ### Configuration category non_english config text_style_control ### Reported statistics lower 1417.8142039040988 rank 104 upper 1427.6877673710535 variance 6.344416280789831 votes 28839 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label DeepSeek-V4-Flash Observed 2026-10-21T18:45:05.190Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/9834/row` |  |  |  |  |  |  |
| [Arena text style control / multi turn](https://benchize.com/benchmarks/lmarena%3Atext_style_control%3Amulti_turn.md) | 1,453.01 | — | 52 / 151 | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1453.005962961207 \| rating \| reported \| Higher is better \| ### Configuration category multi_turn config text_style_control ### Reported statistics lower 1445.7324709482095 rank 82 upper 1460.2794549742043 variance 13.771769666810389 votes 9346 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label DeepSeek-V4-Flash Observed 2026-10-21T18:45:05.190Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/9397/row` |  |  |  |  |  |  |
| [Arena text style control / expert](https://benchize.com/benchmarks/lmarena%3Atext_style_control%3Aexpert.md) | 1,456.99 | — | 68 / 148 | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1456.9854047315857 \| rating \| reported \| Higher is better \| ### Configuration category expert config text_style_control ### Reported statistics lower 1448.2602836048575 rank 108 upper 1465.7105258583138 variance 19.817403291159447 votes 5408 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label DeepSeek-V4-Flash Observed 2026-10-21T18:45:05.190Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/2578/row` |  |  |  |  |  |  |
| [Arena text style control / instruction following](https://benchize.com/benchmarks/lmarena%3Atext_style_control%3Ainstruction_following.md) | 1,427.94 | — | 62 / 151 | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1427.9436863073252 \| rating \| reported \| Higher is better \| ### Configuration category instruction_following config text_style_control ### Reported statistics lower 1422.1512212160997 rank 98 upper 1433.7361513985509 variance 8.734351557360998 votes 17950 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label DeepSeek-V4-Flash Observed 2026-10-21T18:45:05.190Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/7631/row` |  |  |  |  |  |  |
| [Arena text / non english](https://benchize.com/benchmarks/lmarena%3Atext%3Anon_english.md) | 1,419.3 | — | 55 / 151 | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1419.3030369399864 \| rating \| reported \| Higher is better \| ### Configuration category non_english config text ### Reported statistics lower 1414.3965004852957 rank 92 upper 1424.209573394677 variance 6.266916061033678 votes 28839 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) Source Arena Original model label DeepSeek-V4-Flash Observed 2026-10-21T18:45:05.190Z Evidence SHA-256 `8e027ef69b8de06c4b2a8b217bfe816b1f1536269bb257fd295b4ef1ba8246ac` Source locator `/rows/9822/row` |  |  |  |  |  |  |
| [Arena text / hard prompts english](https://benchize.com/benchmarks/lmarena%3Atext%3Ahard_prompts_english.md) | 1,448.99 | — | 57 / 151 | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1448.9869899767773 \| rating \| reported \| Higher is better \| ### Configuration category hard_prompts_english config text ### Reported statistics lower 1442.9707256546667 rank 87 upper 1455.0032542988884 variance 9.42231534502351 votes 16217 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) Source Arena Original model label DeepSeek-V4-Flash Observed 2026-10-21T18:45:05.190Z Evidence SHA-256 `8e027ef69b8de06c4b2a8b217bfe816b1f1536269bb257fd295b4ef1ba8246ac` Source locator `/rows/3954/row` |  |  |  |  |  |  |
| [DesignArena 3D design generation](https://benchize.com/benchmarks/designarena%3A3d-design.md) | 1,189elo | — | 42 / 110 | — | [designarena · public](https://www.designarena.ai/api/leaderboard#board=3d-design) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `elo` \| 1189 \| elo \| 3d-design \| Higher is better \| ### Configuration arenaType models category 3d inputModality Not reported sourceModelVersion deepseek-v4-flash variationName public ### Reported statistics averageGenerationTimeMs 106981 battles 8028 losses 4068 standardError Not reported winRate 49.3 wins 3960 ### Source [Original source](https://www.designarena.ai/api/leaderboard#board=3d-design) Source designarena Original model label DeepSeek-V4-Flash Source version public Observed 2026-10-21T16:37:58.515Z Evidence SHA-256 `bcc0267f7bc7e9ec112306b3a35413cf78bbccbfaa838356232d5d5ed0b83d0f` Source locator `/data/70` |  |  |  |  |  |  |
| [DesignArena SVG generation](https://benchize.com/benchmarks/designarena%3Asvgs.md) | 1,155elo | — | 35 / 77 | — | [designarena · public](https://www.designarena.ai/api/leaderboard#board=svgs) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `elo` \| 1155 \| elo \| svgs \| Higher is better \| ### Configuration arenaType models category svg inputModality Not reported sourceModelVersion deepseek-v4-flash variationName public ### Reported statistics averageGenerationTimeMs 111945 battles 1990 losses 1027 standardError Not reported winRate 48.4 wins 963 ### Source [Original source](https://www.designarena.ai/api/leaderboard#board=svgs) Source designarena Original model label DeepSeek-V4-Flash Source version public Observed 2026-10-21T16:38:03.249Z Evidence SHA-256 `8cbc34a474a66ef5c64f3ffe557df9b55bf7e13368c07c0214223e3ed8f3f21e` Source locator `/data/62` |  |  |  |  |  |  |
| [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` \| 65.217 \| percent \| reported \| Higher is better \| \| `code_generation` \| 73.239 \| percent \| reported \| Higher is better \| \| `connections` \| 89.5 \| percent \| reported \| Higher is better \| \| `consecutive_events` \| 59.915 \| percent \| reported \| Higher is better \| \| `integrals_with_game` \| 37 \| percent \| reported \| Higher is better \| \| `javascript` \| 54.545 \| percent \| reported \| Higher is better \| \| `logic_with_navigation` \| 64 \| percent \| reported \| Higher is better \| \| `math_comp` \| 97.059 \| percent \| reported \| Higher is better \| \| `olympiad` \| 86.531 \| percent \| reported \| Higher is better \| \| `paraphrase` \| 62.383 \| percent \| reported \| Higher is better \| \| `plot_unscrambling` \| 46.872 \| percent \| reported \| Higher is better \| \| `python` \| 35 \| percent \| reported \| Higher is better \| \| `simplify` \| 54.05 \| percent \| reported \| Higher is better \| \| `spatial` \| 96 \| percent \| reported \| Higher is better \| \| `story_generation` \| 67.267 \| percent \| reported \| Higher is better \| \| `summarize` \| 68.85 \| percent \| reported \| Higher is better \| \| `tablejoin` \| 46.115 \| percent \| reported \| Higher is better \| \| `tablereformat` \| 98.039 \| percent \| reported \| Higher is better \| \| `theory_of_mind` \| 73.077 \| percent \| reported \| Higher is better \| \| `typescript` \| 23.333 \| percent \| reported \| Higher is better \| \| `typos` \| 74 \| percent \| reported \| Higher is better \| \| `zebra_puzzle` \| 49.25 \| percent \| reported \| Higher is better \| ### Configuration Model configuration deepseek-v4-flash 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-flash Observed 2026-10-21T16:40:05.068Z Evidence SHA-256 `f0330164423abf9803631fc5b2f2b5427f17c0161c12e15021bb0f9781d2afa8` Source locator `/rows/7` |  |  |  |  |  |  |
| [Arena text / hard prompts](https://benchize.com/benchmarks/lmarena%3Atext%3Ahard_prompts.md) | 1,443.6 | — | 56 / 151 | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1443.5970856749295 \| rating \| reported \| Higher is better \| ### Configuration category hard_prompts config text ### Reported statistics lower 1438.8717675682287 rank 87 upper 1448.3224037816303 variance 5.812539519942203 votes 34751 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) Source Arena Original model label DeepSeek-V4-Flash Observed 2026-10-21T18:45:05.190Z Evidence SHA-256 `8e027ef69b8de06c4b2a8b217bfe816b1f1536269bb257fd295b4ef1ba8246ac` Source locator `/rows/3537/row` |  |  |  |  |  |  |
| [Arena text style control / polish](https://benchize.com/benchmarks/lmarena%3Atext_style_control%3Apolish.md) | 1,436.94 | — | 54 / 117 | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1436.9424332306005 \| rating \| reported \| Higher is better \| ### Configuration category polish config text_style_control ### Reported statistics lower 1418.2173287880444 rank 92 upper 1455.6675376731569 variance 91.2750995782597 votes 1026 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label DeepSeek-V4-Flash Observed 2026-10-21T18:45:05.190Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/10239/row` |  |  |  |  |  |  |
| [Arena text style control / chinese](https://benchize.com/benchmarks/lmarena%3Atext_style_control%3Achinese.md) | 1,469.11 | — | 67 / 146 | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1469.1057863373344 \| rating \| reported \| Higher is better \| ### Configuration category chinese config text_style_control ### Reported statistics lower 1457.740707490284 rank 110 upper 1480.4708651843848 variance 33.623949449582454 votes 3008 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label DeepSeek-V4-Flash Observed 2026-10-21T18:45:05.190Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/526/row` |  |  |  |  |  |  |
| [DesignArena Data visualization generation](https://benchize.com/benchmarks/designarena%3Adata-viz.md) | 1,127elo | — | 79 / 99 | — | [designarena · public](https://www.designarena.ai/api/leaderboard#board=data-viz) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `elo` \| 1127 \| elo \| data-viz \| Higher is better \| ### Configuration arenaType models category dataviz inputModality Not reported sourceModelVersion deepseek-v4-flash variationName public ### Reported statistics averageGenerationTimeMs 95349 battles 1106 losses 656 standardError Not reported winRate 40.7 wins 450 ### Source [Original source](https://www.designarena.ai/api/leaderboard#board=data-viz) Source designarena Original model label DeepSeek-V4-Flash Source version public Observed 2026-10-21T16:37:58.264Z Evidence SHA-256 `a895f6f1a25fa8eb01f821c2097ddec4f884de7bd22f1b8a22e82e6679b71849` Source locator `/data/116` |  |  |  |  |  |  |
| [Arena text style control / russian](https://benchize.com/benchmarks/lmarena%3Atext_style_control%3Arussian.md) | 1,433.21 | — | 61 / 150 | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1433.2072486029992 \| rating \| reported \| Higher is better \| ### Configuration category russian config text_style_control ### Reported statistics lower 1424.718508730331 rank 101 upper 1441.695988475668 variance 18.758161414524448 votes 5742 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label DeepSeek-V4-Flash Observed 2026-10-21T18:45:05.190Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/10484/row` |  |  |  |  |  |  |
| [Arena text / exclude ties](https://benchize.com/benchmarks/lmarena%3Atext%3Aexclude_ties.md) | 1,424.36 | — | 56 / 151 | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1424.355305387603 \| rating \| reported \| Higher is better \| ### Configuration category exclude_ties config text ### Reported statistics lower 1419.1422553891487 rank 92 upper 1429.5683553860574 variance 7.07436720133172 votes 39307 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) Source Arena Original model label DeepSeek-V4-Flash Observed 2026-10-21T18:45:05.190Z Evidence SHA-256 `8e027ef69b8de06c4b2a8b217bfe816b1f1536269bb257fd295b4ef1ba8246ac` Source locator `/rows/2145/row` |  |  |  |  |  |  |
| [Arena text style control / industry medicine and healthcare](https://benchize.com/benchmarks/lmarena%3Atext_style_control%3Aindustry_medicine_and_healthcare.md) | 1,459.47 | — | 56 / 151 | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1459.4667777231648 \| rating \| reported \| Higher is better \| ### Configuration category industry_medicine_and_healthcare config text_style_control ### Reported statistics lower 1448.9756526031185 rank 93 upper 1469.9579028432108 variance 28.651538756980823 votes 3677 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label DeepSeek-V4-Flash Observed 2026-10-21T18:45:05.190Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/6405/row` |  |  |  |  |  |  |
| [Arena text / expert](https://benchize.com/benchmarks/lmarena%3Atext%3Aexpert.md) | 1,441.08 | — | 65 / 148 | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1441.079061063774 \| rating \| reported \| Higher is better \| ### Configuration category expert config text ### Reported statistics lower 1432.4330431227504 rank 98 upper 1449.7250790047972 variance 19.459697402923094 votes 5408 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) Source Arena Original model label DeepSeek-V4-Flash Observed 2026-10-21T18:45:05.190Z Evidence SHA-256 `8e027ef69b8de06c4b2a8b217bfe816b1f1536269bb257fd295b4ef1ba8246ac` Source locator `/rows/2568/row` |  |  |  |  |  |  |
| [Arena text style control / overall](https://benchize.com/benchmarks/lmarena%3Atext_style_control%3Aoverall.md) | 1,435.83 | — | 64 / 151 | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1435.8262804106807 \| rating \| reported \| Higher is better \| ### Configuration category overall config text_style_control ### Reported statistics lower 1431.7885193774046 rank 105 upper 1439.8640414439571 variance 4.244094476300582 votes 51959 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label DeepSeek-V4-Flash Observed 2026-10-21T18:45:05.190Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/104/row` |  |  |  |  |  |  |
| [Arena text style control / math](https://benchize.com/benchmarks/lmarena%3Atext_style_control%3Amath.md) | 1,424.08 | — | 73 / 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` \| 1424.0755584922495 \| rating \| reported \| Higher is better \| ### Configuration category math config text_style_control ### Reported statistics lower 1412.3453681383232 rank 121 upper 1435.8057488461754 variance 35.81903963101121 votes 2699 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label DeepSeek-V4-Flash Observed 2026-10-21T18:45:05.190Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/9033/row` |  |  |  |  |  |  |
| [SimpleBench](https://benchize.com/benchmarks/simplebench%3Aavg-at-5.md) | 61.1% | — | 24 / 62 | — | [simplebench](https://simple-bench.com/static/js/leaderboard-data.js) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 61.1 \| percent \| average_at_5 \| Higher is better \| ### Configuration Reasoning effort unknown Model configuration DeepSeek V4 Flash thinkingEnabled Not reported ### Reported statistics rank 34th ### Source [Original source](https://simple-bench.com/static/js/leaderboard-data.js) Source simplebench Original model label DeepSeek V4 Flash Observed 2026-10-21T16:32:13.183Z Evidence SHA-256 `b2d0285ad3e4e15750ed20d39897e7558d1c05e8962e90c861b06f93c8019dc9` Source locator `/rows/35` |  |  |  |  |  |  |
| [Arena text style control / japanese](https://benchize.com/benchmarks/lmarena%3Atext_style_control%3Ajapanese.md) | 1,398.49 | — | 53 / 120 | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1398.4866318056895 \| rating \| reported \| Higher is better \| ### Configuration category japanese config text_style_control ### Reported statistics lower 1373.7812050353925 rank 90 upper 1423.1920585759867 variance 158.8870635849286 votes 653 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label DeepSeek-V4-Flash Observed 2026-10-21T18:45:05.190Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/8040/row` |  |  |  |  |  |  |
| [Arena text / japanese](https://benchize.com/benchmarks/lmarena%3Atext%3Ajapanese.md) | 1,389.02 | — | 53 / 120 | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1389.0183791951426 \| rating \| reported \| Higher is better \| ### Configuration category japanese config text ### Reported statistics lower 1364.3611184871195 rank 90 upper 1413.675639903166 variance 158.2681304165508 votes 653 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) Source Arena Original model label DeepSeek-V4-Flash Observed 2026-10-21T18:45:05.190Z Evidence SHA-256 `8e027ef69b8de06c4b2a8b217bfe816b1f1536269bb257fd295b4ef1ba8246ac` Source locator `/rows/8040/row` |  |  |  |  |  |  |
| [DesignArena Browser game generation](https://benchize.com/benchmarks/designarena%3Agame-dev.md) | 1,197elo | — | 46 / 117 | — | [designarena · public](https://www.designarena.ai/api/leaderboard#board=game-dev) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `elo` \| 1197 \| elo \| game-dev \| Higher is better \| ### Configuration arenaType models category gamedev inputModality Not reported sourceModelVersion deepseek-v4-flash variationName public ### Reported statistics averageGenerationTimeMs 172955 battles 4371 losses 2177 standardError Not reported winRate 50.2 wins 2194 ### Source [Original source](https://www.designarena.ai/api/leaderboard#board=game-dev) Source designarena Original model label DeepSeek-V4-Flash Source version public Observed 2026-10-21T16:38:01.100Z Evidence SHA-256 `53db6a89112ce8cdf644568c666d4b8309aece764cfcedb291ffd52ae3934e30` Source locator `/data/72` |  |  |  |  |  |  |
| [Arena text style control / hard prompts](https://benchize.com/benchmarks/lmarena%3Atext_style_control%3Ahard_prompts.md) | 1,459.06 | — | 64 / 151 | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1459.0556798846048 \| rating \| reported \| Higher is better \| ### Configuration category hard_prompts config text_style_control ### Reported statistics lower 1454.302809775571 rank 102 upper 1463.8085499936387 variance 5.8805197003949825 votes 34751 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label DeepSeek-V4-Flash Observed 2026-10-21T18:45:05.190Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/3552/row` |  |  |  |  |  |  |
| [Arena text style control / coding](https://benchize.com/benchmarks/lmarena%3Atext_style_control%3Acoding.md) | 1,484.39 | — | 63 / 151 | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1484.3885373797705 \| rating \| reported \| Higher is better \| ### Configuration category coding config text_style_control ### Reported statistics lower 1478.1796711627326 rank 105 upper 1490.5974035968081 variance 10.035255224760368 votes 15284 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label DeepSeek-V4-Flash Observed 2026-10-21T18:45:05.190Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/914/row` |  |  |  |  |  |  |
| [Arena text / instruction following](https://benchize.com/benchmarks/lmarena%3Atext%3Ainstruction_following.md) | 1,420.83 | — | 57 / 151 | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1420.8331979636603 \| rating \| reported \| Higher is better \| ### Configuration category instruction_following config text ### Reported statistics lower 1415.0562596602529 rank 85 upper 1426.610136267068 variance 8.687589199601957 votes 17950 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) Source Arena Original model label DeepSeek-V4-Flash Observed 2026-10-21T18:45:05.190Z Evidence SHA-256 `8e027ef69b8de06c4b2a8b217bfe816b1f1536269bb257fd295b4ef1ba8246ac` Source locator `/rows/7618/row` |  |  |  |  |  |  |
| [Arena text / spanish](https://benchize.com/benchmarks/lmarena%3Atext%3Aspanish.md) | 1,435.5 | — | 52 / 134 | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1435.502168190677 \| rating \| reported \| Higher is better \| ### Configuration category spanish config text ### Reported statistics lower 1419.5704911391776 rank 89 upper 1451.4338452421757 variance 66.07342301990265 votes 1580 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) Source Arena Original model label DeepSeek-V4-Flash Observed 2026-10-21T18:45:05.190Z Evidence SHA-256 `8e027ef69b8de06c4b2a8b217bfe816b1f1536269bb257fd295b4ef1ba8246ac` Source locator `/rows/10853/row` |  |  |  |  |  |  |
| [Arena text style control / industry legal and government](https://benchize.com/benchmarks/lmarena%3Atext_style_control%3Aindustry_legal_and_government.md) | 1,448.55 | — | 59 / 151 | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1448.5477853228424 \| rating \| reported \| Higher is better \| ### Configuration category industry_legal_and_government config text_style_control ### Reported statistics lower 1438.715608464646 rank 96 upper 1458.379962181039 variance 25.165361984379572 votes 4146 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label DeepSeek-V4-Flash Observed 2026-10-21T18:45:05.190Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/5203/row` |  |  |  |  |  |  |
| [DesignArena Overall frontend coding](https://benchize.com/benchmarks/designarena%3Acode.md) | 1,205elo | SE ±2.23 | 48 / 116 | — | [designarena · public](https://www.designarena.ai/api/leaderboard#board=code) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `elo` \| 1205 \| elo \| code \| Higher is better \| ### Configuration arenaType models category allcategories inputModality text sourceModelVersion deepseek-v4-flash variationName public ### Reported statistics Uncertainty Standard error: ±2.23 averageGenerationTimeMs 134460 battles 28103 losses 14350 standardError 2.2303 winRate 48.9 wins 13753 ### Source [Original source](https://www.designarena.ai/api/leaderboard#board=code) Source designarena Original model label DeepSeek-V4-Flash Source version public Observed 2026-10-21T16:37:57.301Z Evidence SHA-256 `0c897b58670f5e352bd123db999a40c0d1781a443964c502b90774a76a3a7758` Source locator `/data/78` |  |  |  |  |  |  |
| [DesignArena UI component generation](https://benchize.com/benchmarks/designarena%3Aui-components.md) | 1,165elo | — | 61 / 112 | — | [designarena · public](https://www.designarena.ai/api/leaderboard#board=ui-components) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `elo` \| 1165 \| elo \| ui-components \| Higher is better \| ### Configuration arenaType models category uicomponent inputModality Not reported sourceModelVersion deepseek-v4-flash variationName public ### Reported statistics averageGenerationTimeMs 104900 battles 1577 losses 872 standardError Not reported winRate 44.7 wins 705 ### Source [Original source](https://www.designarena.ai/api/leaderboard#board=ui-components) Source designarena Original model label DeepSeek-V4-Flash Source version public Observed 2026-10-21T16:37:57.993Z Evidence SHA-256 `46482ec1b4012638eace65493daea4750e2088098018fd9d5fc46126fc1f8557` Source locator `/data/94` |  |  |  |  |  |  |
| [Arena text style control / hard prompts english](https://benchize.com/benchmarks/lmarena%3Atext_style_control%3Ahard_prompts_english.md) | 1,463.89 | — | 62 / 151 | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1463.8860995291839 \| rating \| reported \| Higher is better \| ### Configuration category hard_prompts_english config text_style_control ### Reported statistics lower 1457.8467019596378 rank 101 upper 1469.9254970987304 variance 9.494914485755599 votes 16217 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label DeepSeek-V4-Flash Observed 2026-10-21T18:45:05.190Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/3968/row` |  |  |  |  |  |  |
| [Arena text style control / french](https://benchize.com/benchmarks/lmarena%3Atext_style_control%3Afrench.md) | 1,449.47 | — | 67 / 132 | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1449.4676545677785 \| rating \| reported \| Higher is better \| ### Configuration category french config text_style_control ### Reported statistics lower 1434.6056238570445 rank 108 upper 1464.3296852785124 variance 57.49897816342792 votes 2002 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label DeepSeek-V4-Flash Observed 2026-10-21T18:45:05.190Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/2945/row` |  |  |  |  |  |  |
| [Arena text / industry software and it services](https://benchize.com/benchmarks/lmarena%3Atext%3Aindustry_software_and_it_services.md) | 1,453.06 | — | 59 / 151 | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1453.059240872018 \| rating \| reported \| Higher is better \| ### Configuration category industry_software_and_it_services config text ### Reported statistics lower 1447.6011455431944 rank 97 upper 1458.5173362008418 variance 7.755075873270335 votes 21372 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) Source Arena Original model label DeepSeek-V4-Flash Observed 2026-10-21T18:45:05.190Z Evidence SHA-256 `8e027ef69b8de06c4b2a8b217bfe816b1f1536269bb257fd295b4ef1ba8246ac` Source locator `/rows/6797/row` |  |  |  |  |  |  |
| [Rapidata SVG generation — Preference](https://benchize.com/benchmarks/rapidata%3Asvg%3Arlb_1MFkkEMFnCNyKl.md) | 755.01elo | CI 740.66–769.36 | 32 / 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` \| 755.0098901542219 \| elo \| rlb_1MFkkEMFnCNyKl \| Higher is better \| ### Configuration benchmarkId bmk_1MFkc3sXfbKCqf criterion rlb_1MFkkEMFnCNyKl participantId par_1MFlJRdB8cayLk sourceModelVersion deepseek-v4-flash weighted false ### Reported statistics Uncertainty Confidence interval: 740.66–769.36 confidenceIntervalLowerOffset 14.347686568107747 confidenceIntervalUpperOffset 14.347686568107747 totalMatches 13603 wins 5922.5 ### 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-flash Source version v1 Observed 2026-10-21T16:37:40.980Z Evidence SHA-256 `b70f07a4924c82499996aba613ca8ec2d0aee9ec9ebd404e45c8bf250206cf40` Source locator `/items/56` |  |  |  |  |  |  |
| [DistressBench](https://benchize.com/benchmarks/scale%3Adistressbench.md) | 69.66source score | CI 68.44–70.88 | 15 / 27 | — | [scale](https://labs.scale.com/leaderboard/distressbench) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `score` \| 69.66 \| source_score \| reported \| Higher is better \| ### Configuration Reasoning effort unknown Model configuration deepseek-v4-flash sourceModelVersion deepseek-v4-flash thinkingEnabled Not reported ### Reported statistics Uncertainty Confidence interval: 68.44–70.88 contaminationWarning Not reported rank 20 reportedConfidenceHalfWidth 1.22 ### Source [Original source](https://labs.scale.com/leaderboard/distressbench) Source scale Original model label deepseek-v4-flash Observed 2026-10-21T16:35:27.403Z Evidence SHA-256 `6ca6a76569e51fde037c8e2610bdf7bc39d99b54c69b6b4dc0dba9ec2a4e24da` Source locator `/rows/19` |  |  |  |  |  |  |
| [Arena text / math](https://benchize.com/benchmarks/lmarena%3Atext%3Amath.md) | 1,425.85 | — | 68 / 149 | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1425.854443813179 \| rating \| reported \| Higher is better \| ### Configuration category math config text ### Reported statistics lower 1414.1380082541807 rank 110 upper 1437.5708793721772 variance 35.73508623043187 votes 2699 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) Source Arena Original model label DeepSeek-V4-Flash Observed 2026-10-21T18:45:05.190Z Evidence SHA-256 `8e027ef69b8de06c4b2a8b217bfe816b1f1536269bb257fd295b4ef1ba8246ac` Source locator `/rows/9022/row` |  |  |  |  |  |  |
| [Arena text style control / industry software and it services](https://benchize.com/benchmarks/lmarena%3Atext_style_control%3Aindustry_software_and_it_services.md) | 1,471.21 | — | 65 / 151 | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1471.2131180021267 \| rating \| reported \| Higher is better \| ### Configuration category industry_software_and_it_services config text_style_control ### Reported statistics lower 1465.7199997553225 rank 109 upper 1476.7062362489307 variance 7.854919050757884 votes 21372 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label DeepSeek-V4-Flash Observed 2026-10-21T18:45:05.190Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/6809/row` |  |  |  |  |  |  |
| [FinanceBenchmark v2](https://benchize.com/benchmarks/financebenchmark%3Av2.md) | 93.15% | CI 87.67–98.63% | 1 / 21 | — | [financebenchmark](https://finbenchmark.ai/) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `pass_at_1` \| 0.931507 \| score_fraction \| reported \| Higher is better \| \| `accuracy` \| 0.849315 \| score_fraction \| reported \| Higher is better \| \| `knowledge` \| 1 \| score_fraction \| category \| Higher is better \| \| `analysis` \| 1 \| score_fraction \| category \| Higher is better \| \| `quant` \| 0.666667 \| score_fraction \| category \| Higher is better \| \| `portfolio_mgmt` \| 1 \| 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 7dcf50c3-917a-4845-b920-574bcae2c67c taskSetVersion v2 ### Reported statistics Uncertainty Confidence interval: 87.67–98.63% confidenceInterval [0.8767,0.9863] 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-flash Evaluated 2026-07-13T14:17:55.586025+00:00 Observed 2026-10-21T16:30:44.281Z Evidence SHA-256 `f9e7dab8846b092fc0befeca8c5cd02a8187c0f5b6b10c32ab2c7ab60f7af575` Source locator `/rows/1` |  |  |  |  |  |  |
| [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) | 1,438.58 | — | 67 / 151 | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1438.5752196900853 \| rating \| reported \| Higher is better \| ### Configuration category industry_business_and_management_and_financial_operations config text_style_control ### Reported statistics lower 1431.6205532621786 rank 108 upper 1445.529886117992 variance 12.590889914762164 votes 10438 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label DeepSeek-V4-Flash Observed 2026-10-21T18:45:05.190Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/4390/row` |  |  |  |  |  |  |
| [Arena text / russian](https://benchize.com/benchmarks/lmarena%3Atext%3Arussian.md) | 1,427.42 | — | 53 / 150 | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1427.420729786494 \| rating \| reported \| Higher is better \| ### Configuration category russian config text ### Reported statistics lower 1418.9699544824061 rank 85 upper 1435.8715050905816 variance 18.59075069488185 votes 5742 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) Source Arena Original model label DeepSeek-V4-Flash Observed 2026-10-21T18:45:05.190Z Evidence SHA-256 `8e027ef69b8de06c4b2a8b217bfe816b1f1536269bb257fd295b4ef1ba8246ac` Source locator `/rows/10468/row` |  |  |  |  |  |  |
| [Arena text / longer query](https://benchize.com/benchmarks/lmarena%3Atext%3Alonger_query.md) | 1,434.37 | — | 57 / 150 | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1434.370198356563 \| rating \| reported \| Higher is better \| ### Configuration category longer_query config text ### Reported statistics lower 1428.8506498303245 rank 88 upper 1439.8897468828015 variance 7.930689187499126 votes 23342 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) Source Arena Original model label DeepSeek-V4-Flash Observed 2026-10-21T18:45:05.190Z Evidence SHA-256 `8e027ef69b8de06c4b2a8b217bfe816b1f1536269bb257fd295b4ef1ba8246ac` Source locator `/rows/8605/row` |  |  |  |  |  |  |
| [Arena text / industry business and management and financial operations](https://benchize.com/benchmarks/lmarena%3Atext%3Aindustry_business_and_management_and_financial_operations.md) | 1,425.24 | — | 59 / 151 | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1425.2410781145477 \| rating \| reported \| Higher is better \| ### Configuration category industry_business_and_management_and_financial_operations config text ### Reported statistics lower 1418.3446220128326 rank 92 upper 1432.1375342162626 variance 12.381001328627537 votes 10438 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) Source Arena Original model label DeepSeek-V4-Flash Observed 2026-10-21T18:45:05.190Z Evidence SHA-256 `8e027ef69b8de06c4b2a8b217bfe816b1f1536269bb257fd295b4ef1ba8246ac` Source locator `/rows/4374/row` |  |  |  |  |  |  |
| [Arena text / industry mathematical](https://benchize.com/benchmarks/lmarena%3Atext%3Aindustry_mathematical.md) | 1,432.04 | — | 71 / 148 | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1432.0400958404105 \| rating \| reported \| Higher is better \| ### Configuration category industry_mathematical config text ### Reported statistics lower 1420.6453507046547 rank 113 upper 1443.434840976166 variance 33.799715881208876 votes 2972 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) Source Arena Original model label DeepSeek-V4-Flash Observed 2026-10-21T18:45:05.190Z Evidence SHA-256 `8e027ef69b8de06c4b2a8b217bfe816b1f1536269bb257fd295b4ef1ba8246ac` Source locator `/rows/6025/row` |  |  |  |  |  |  |
| [Arena text / industry writing and literature and language](https://benchize.com/benchmarks/lmarena%3Atext%3Aindustry_writing_and_literature_and_language.md) | 1,409.97 | — | 56 / 151 | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1409.9695461178947 \| rating \| reported \| Higher is better \| ### Configuration category industry_writing_and_literature_and_language config text ### Reported statistics lower 1403.474899481233 rank 92 upper 1416.4641927545563 variance 10.980316828563273 votes 12606 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) Source Arena Original model label DeepSeek-V4-Flash Observed 2026-10-21T18:45:05.190Z Evidence SHA-256 `8e027ef69b8de06c4b2a8b217bfe816b1f1536269bb257fd295b4ef1ba8246ac` Source locator `/rows/7209/row` |  |  |  |  |  |  |
| [Arena text / industry legal and government](https://benchize.com/benchmarks/lmarena%3Atext%3Aindustry_legal_and_government.md) | 1,438.69 | — | 55 / 151 | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1438.6861944911327 \| rating \| reported \| Higher is better \| ### Configuration category industry_legal_and_government config text ### Reported statistics lower 1428.9544709009087 rank 89 upper 1448.4179180813564 variance 24.65377047030453 votes 4146 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) Source Arena Original model label DeepSeek-V4-Flash Observed 2026-10-21T18:45:05.190Z Evidence SHA-256 `8e027ef69b8de06c4b2a8b217bfe816b1f1536269bb257fd295b4ef1ba8246ac` Source locator `/rows/5196/row` |  |  |  |  |  |  |
| [Arena text / french](https://benchize.com/benchmarks/lmarena%3Atext%3Afrench.md) | 1,439.35 | — | 63 / 132 | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1439.3541669090291 \| rating \| reported \| Higher is better \| ### Configuration category french config text ### Reported statistics lower 1424.5544500062201 rank 102 upper 1454.1538838118383 variance 57.01782333923784 votes 2002 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) Source Arena Original model label DeepSeek-V4-Flash Observed 2026-10-21T18:45:05.190Z Evidence SHA-256 `8e027ef69b8de06c4b2a8b217bfe816b1f1536269bb257fd295b4ef1ba8246ac` Source locator `/rows/2939/row` |  |  |  |  |  |  |
| [Arena text / german](https://benchize.com/benchmarks/lmarena%3Atext%3Agerman.md) | 1,418.83 | — | 55 / 129 | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1418.8331805815124 \| rating \| reported \| Higher is better \| ### Configuration category german config text ### Reported statistics lower 1397.5169893094453 rank 97 upper 1440.1493718535794 variance 118.28319176547524 votes 840 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) Source Arena Original model label DeepSeek-V4-Flash Observed 2026-10-21T18:45:05.190Z Evidence SHA-256 `8e027ef69b8de06c4b2a8b217bfe816b1f1536269bb257fd295b4ef1ba8246ac` Source locator `/rows/3233/row` |  |  |  |  |  |  |
| [Arena text / creative writing](https://benchize.com/benchmarks/lmarena%3Atext%3Acreative_writing.md) | 1,403.08 | — | 55 / 151 | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1403.075601811308 \| rating \| reported \| Higher is better \| ### Configuration category creative_writing config text ### Reported statistics lower 1395.6018128077608 rank 92 upper 1410.549390814855 variance 14.540705673749487 votes 8580 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) Source Arena Original model label DeepSeek-V4-Flash Observed 2026-10-21T18:45:05.190Z Evidence SHA-256 `8e027ef69b8de06c4b2a8b217bfe816b1f1536269bb257fd295b4ef1ba8246ac` Source locator `/rows/1313/row` |  |  |  |  |  |  |
| [DesignArena ASCII art generation](https://benchize.com/benchmarks/designarena%3Aascii.md) | 1,109elo | — | 52 / 65 | — | [designarena · public](https://www.designarena.ai/api/leaderboard#board=ascii) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `elo` \| 1109 \| elo \| ascii \| Higher is better \| ### Configuration arenaType models category ascii inputModality Not reported sourceModelVersion deepseek-v4-flash variationName public ### Reported statistics averageGenerationTimeMs 112013 battles 300 losses 172 standardError Not reported winRate 42.7 wins 128 ### Source [Original source](https://www.designarena.ai/api/leaderboard#board=ascii) Source designarena Original model label DeepSeek-V4-Flash Source version public Observed 2026-10-21T16:38:03.513Z Evidence SHA-256 `0603b8c65b44ee887f5b566feb469465f59635137a6ac5c6d94c23bcf3776311` Source locator `/data/74` |  |  |  |  |  |  |
| [Arena text / industry life and physical and social science](https://benchize.com/benchmarks/lmarena%3Atext%3Aindustry_life_and_physical_and_social_science.md) | 1,446.39 | — | 55 / 151 | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1446.3899291481785 \| rating \| reported \| Higher is better \| ### Configuration category industry_life_and_physical_and_social_science config text ### Reported statistics lower 1439.0722317146733 rank 86 upper 1453.7076265816834 variance 13.939677145530144 votes 8396 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) Source Arena Original model label DeepSeek-V4-Flash Observed 2026-10-21T18:45:05.190Z Evidence SHA-256 `8e027ef69b8de06c4b2a8b217bfe816b1f1536269bb257fd295b4ef1ba8246ac` Source locator `/rows/5583/row` |  |  |  |  |  |  |
| [Arena text style control / korean](https://benchize.com/benchmarks/lmarena%3Atext_style_control%3Akorean.md) | 1,394.15 | — | 50 / 124 | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1394.1476562311236 \| rating \| reported \| Higher is better \| ### Configuration category korean config text_style_control ### Reported statistics lower 1373.233880798417 rank 86 upper 1415.0614316638298 variance 113.85934960267028 votes 896 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label DeepSeek-V4-Flash Observed 2026-10-21T18:45:05.190Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/8319/row` |  |  |  |  |  |  |
| [NC Bench](https://benchize.com/benchmarks/nc-bench%3Aoverall.md) | 82.02% | — | 119 / 144 | — | [nc bench](https://www.nc-bench.com/models) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `score` \| 82.02 \| percent \| reported \| Higher is better \| \| `tooling` \| 94 \| percent \| category \| Higher is better \| \| `creative_writing` \| 83.42 \| percent \| category \| Higher is better \| \| `language` \| 88.5 \| percent \| category \| Higher is better \| \| `utility` \| 83.26 \| percent \| category \| Higher is better \| \| `reasoning` \| 68.68 \| percent \| category \| Higher is better \| \| `text_editing` \| 93.25 \| percent \| category \| Higher is better \| \| `rule_following` \| 57.32 \| percent \| category \| Higher is better \| \| `hallucination` \| 87.73 \| percent \| category \| Higher is better \| ### Configuration Reasoning effort unknown Model configuration DeepSeek V4 Flash thinkingEnabled Not reported ### Source [Original source](https://www.nc-bench.com/models) Source nc bench Original model label DeepSeek V4 Flash Observed 2026-10-21T16:31:48.370Z Evidence SHA-256 `ec261022458543624b08a136d01f5a2f0666cd52ffb49c64d6ca983e8543d1b5` Source locator `/rows/154` |  |  |  |  |  |  |

---
Cite as: DeepSeek V4 Flash — Benchize, https://benchize.com/models/deepseek-v4-flash (retrieved 2026-10-21)