# Hy3 > Source: Benchize (https://benchize.com) — https://benchize.com/models/hy3. When citing or reusing this content, credit "Benchize" and link to https://benchize.com/models/hy3. Tencent Canonical URL: https://benchize.com/models/hy3 Last updated: Thu, 22 Oct 2026 06:20:09 GMT Reproduction and quotation must name Benchize, link to the canonical HTML URL, and retain individual source citations. Tencent ## Benchmarks | Benchmark | Score | ± | Rank | Cost | Source | | | --- | --- | --- | --- | --- | --- | --- | | [DesignArena Website generation](https://benchize.com/benchmarks/designarena%3Awebsite.md) | 1,182elo | — | 65 / 123 | — | [designarena · public](https://www.designarena.ai/api/leaderboard#board=website) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `elo` \| 1182 \| elo \| website \| Higher is better \| ### Configuration arenaType models category website inputModality text sourceModelVersion hy3 variationName public ### Reported statistics averageGenerationTimeMs 146435 battles 2409 losses 1414 standardError Not reported winRate 41.3 wins 995 ### Source [Original source](https://www.designarena.ai/api/leaderboard#board=website) Source designarena Original model label Hy3 Low Source version public Observed 2026-10-21T16:37:57.757Z Evidence SHA-256 `51873e97776a3c5ae706b24cc2c60384793dd18398df970e213a8e7c276d8ac0` Source locator `/data/100` | | | | | | | | [Arena webdev / webdev](https://benchize.com/benchmarks/lmarena%3Awebdev%3Awebdev.md) | 1,507.1 | — | 42 / 90 | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/webdev/latest) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1507.103908462265 \| rating \| reported \| Higher is better \| ### Configuration category webdev config webdev ### Reported statistics lower 1498.7377982117869 rank 61 upper 1515.4700187127432 variance 18.220109596413074 votes 6256 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/webdev/latest) Source Arena Original model label Hy3 Observed 2026-10-22T00:45:04.817Z Evidence SHA-256 `f82507859808110820a4ab6df15561b8864137ddefc1f6fb0c552af2e58ea738` Source locator `/rows/272/row` | | | | | | | | [Arena text style control / expert](https://benchize.com/benchmarks/lmarena%3Atext_style_control%3Aexpert.md) | 1,489.87 | — | 46 / 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` \| 1489.8715157039906 \| rating \| reported \| Higher is better \| ### Configuration category expert config text_style_control ### Reported statistics lower 1473.8949169317186 rank 62 upper 1505.8481144762627 variance 66.4465559164949 votes 1358 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label Hy3 Observed 2026-10-22T00:45:04.817Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/2532/row` | | | | | | | | [Arena text / industry writing and literature and language](https://benchize.com/benchmarks/lmarena%3Atext%3Aindustry_writing_and_literature_and_language.md) | 1,414.35 | — | 54 / 151 | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1414.3469700863657 \| rating \| reported \| Higher is better \| ### Configuration category industry_writing_and_literature_and_language config text ### Reported statistics lower 1403.9295416604243 rank 86 upper 1424.764398512307 variance 28.2504173739918 votes 3435 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) Source Arena Original model label Hy3 Observed 2026-10-22T00:45:04.817Z Evidence SHA-256 `8e027ef69b8de06c4b2a8b217bfe816b1f1536269bb257fd295b4ef1ba8246ac` Source locator `/rows/7203/row` | | | | | | | | [Arena text / industry life and physical and social science](https://benchize.com/benchmarks/lmarena%3Atext%3Aindustry_life_and_physical_and_social_science.md) | 1,456.74 | — | 43 / 151 | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1456.7370253627641 \| rating \| reported \| Higher is better \| ### Configuration category industry_life_and_physical_and_social_science config text ### Reported statistics lower 1443.5920217381843 rank 63 upper 1469.8820289873438 variance 44.98059939088206 votes 2014 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) Source Arena Original model label Hy3 Observed 2026-10-22T00:45:04.817Z Evidence SHA-256 `8e027ef69b8de06c4b2a8b217bfe816b1f1536269bb257fd295b4ef1ba8246ac` Source locator `/rows/5560/row` | | | | | | | | [Arena webdev / overall](https://benchize.com/benchmarks/lmarena%3Awebdev%3Aoverall.md) | 1,507.1 | — | 42 / 90 | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/webdev/latest) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1507.103908462265 \| rating \| reported \| Higher is better \| ### Configuration category overall config webdev ### Reported statistics lower 1498.7377982117869 rank 61 upper 1515.4700187127432 variance 18.220109596413074 votes 6256 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/webdev/latest) Source Arena Original model label Hy3 Observed 2026-10-22T00:45:04.817Z Evidence SHA-256 `f82507859808110820a4ab6df15561b8864137ddefc1f6fb0c552af2e58ea738` Source locator `/rows/60/row` | | | | | | | | [Arena text style control / english](https://benchize.com/benchmarks/lmarena%3Atext_style_control%3Aenglish.md) | 1,464.54 | — | 45 / 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` \| 1464.5362388165333 \| rating \| reported \| Higher is better \| ### Configuration category english config text_style_control ### Reported statistics lower 1455.852177104057 rank 69 upper 1473.2203005290096 variance 19.631325323557327 votes 4863 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label Hy3 Observed 2026-10-22T00:45:04.817Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/1705/row` | | | | | | | | [Arena text style control / coding](https://benchize.com/benchmarks/lmarena%3Atext_style_control%3Acoding.md) | 1,502.04 | — | 49 / 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` \| 1502.0415086337503 \| rating \| reported \| Higher is better \| ### Configuration category coding config text_style_control ### Reported statistics lower 1491.7748597320956 rank 74 upper 1512.3081575354047 variance 27.43855514004952 votes 3471 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label Hy3 Observed 2026-10-22T00:45:04.817Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/883/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) | 1,430.36 | — | 51 / 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` \| 1430.3625020325778 \| rating \| reported \| Higher is better \| ### Configuration category industry_writing_and_literature_and_language config text_style_control ### Reported statistics lower 1419.9271519696392 rank 80 upper 1440.7978520955162 variance 28.347702271189128 votes 3435 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label Hy3 Observed 2026-10-22T00:45:04.817Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/7197/row` | | | | | | | | [Arena text style control / longer query](https://benchize.com/benchmarks/lmarena%3Atext_style_control%3Alonger_query.md) | 1,464.96 | — | 46 / 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` \| 1464.9587497530467 \| rating \| reported \| Higher is better \| ### Configuration category longer_query config text_style_control ### Reported statistics lower 1456.4971229636958 rank 70 upper 1473.420376542398 variance 18.638525431160325 votes 5770 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label Hy3 Observed 2026-10-22T00:45:04.817Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/8587/row` | | | | | | | | [Arena text style control / russian](https://benchize.com/benchmarks/lmarena%3Atext_style_control%3Arussian.md) | 1,448.3 | — | 51 / 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` \| 1448.29920799709 \| rating \| reported \| Higher is better \| ### Configuration category russian config text_style_control ### Reported statistics lower 1433.4146613892412 rank 78 upper 1463.1837546049387 variance 57.67333142495793 votes 1589 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label Hy3 Observed 2026-10-22T00:45:04.817Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/10461/row` | | | | | | | | [DesignArena UI component generation](https://benchize.com/benchmarks/designarena%3Aui-components.md) | 1,207elo | — | 48 / 112 | — | [designarena · public](https://www.designarena.ai/api/leaderboard#board=ui-components) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `elo` \| 1207 \| elo \| ui-components \| Higher is better \| ### Configuration arenaType models category uicomponent inputModality Not reported sourceModelVersion hy3-direct variationName public ### Reported statistics averageGenerationTimeMs 211298 battles 1567 losses 893 standardError Not reported winRate 43 wins 674 ### Source [Original source](https://www.designarena.ai/api/leaderboard#board=ui-components) Source designarena Original model label Hy3 Source version public Observed 2026-10-21T16:37:57.993Z Evidence SHA-256 `46482ec1b4012638eace65493daea4750e2088098018fd9d5fc46126fc1f8557` Source locator `/data/75` | | | | | | | | [Arena text / overall](https://benchize.com/benchmarks/lmarena%3Atext.md) | 1,438.07 | — | 50 / 151 | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1438.0671332571378 \| rating \| reported \| Higher is better \| ### Configuration category overall config text ### Reported statistics lower 1432.0398368886608 rank 80 upper 1444.094429625615 variance 9.456902496976973 votes 12791 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) Source Arena Original model label Hy3 Observed 2026-10-22T00:45:04.817Z Evidence SHA-256 `8e027ef69b8de06c4b2a8b217bfe816b1f1536269bb257fd295b4ef1ba8246ac` Source locator `/rows/79/row` | | | | | | | | [Arena text style control / hard prompts](https://benchize.com/benchmarks/lmarena%3Atext_style_control%3Ahard_prompts.md) | 1,475.35 | — | 48 / 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` \| 1475.3477742830135 \| rating \| reported \| Higher is better \| ### Configuration category hard_prompts config text_style_control ### Reported statistics lower 1468.2277281683305 rank 74 upper 1482.4678203976964 variance 13.196824186196114 votes 8479 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label Hy3 Observed 2026-10-22T00:45:04.817Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/3524/row` | | | | | | | | [Arena text style control / industry legal and government](https://benchize.com/benchmarks/lmarena%3Atext_style_control%3Aindustry_legal_and_government.md) | 1,447.68 | — | 60 / 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` \| 1447.6821829765681 \| rating \| reported \| Higher is better \| ### Configuration category industry_legal_and_government config text_style_control ### Reported statistics lower 1428.4633508986587 rank 97 upper 1466.9010150544775 variance 96.15188491650605 votes 978 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label Hy3 Observed 2026-10-22T00:45:04.817Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/5204/row` | | | | | | | | [Arena text / russian](https://benchize.com/benchmarks/lmarena%3Atext%3Arussian.md) | 1,431.7 | — | 51 / 150 | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1431.6981604007285 \| rating \| reported \| Higher is better \| ### Configuration category russian config text ### Reported statistics lower 1416.799426934447 rank 79 upper 1446.5968938670098 variance 57.783323799676644 votes 1589 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) Source Arena Original model label Hy3 Observed 2026-10-22T00:45:04.817Z Evidence SHA-256 `8e027ef69b8de06c4b2a8b217bfe816b1f1536269bb257fd295b4ef1ba8246ac` Source locator `/rows/10462/row` | | | | | | | | [Arena text style control / overall](https://benchize.com/benchmarks/lmarena%3Atext_style_control%3Aoverall.md) | 1,453.36 | — | 47 / 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` \| 1453.363350861891 \| rating \| reported \| Higher is better \| ### Configuration category overall config text_style_control ### Reported statistics lower 1447.3143975751236 rank 74 upper 1459.4123041486582 variance 9.524984536703277 votes 12791 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label Hy3 Observed 2026-10-22T00:45:04.817Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/73/row` | | | | | | | | [Arena text / korean](https://benchize.com/benchmarks/lmarena%3Atext%3Akorean.md) | 1,396.28 | — | 43 / 124 | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1396.282782684972 \| rating \| reported \| Higher is better \| ### Configuration category korean config text ### Reported statistics lower 1360.4818908804336 rank 71 upper 1432.0836744895105 variance 333.65029115909454 votes 269 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) Source Arena Original model label Hy3 Observed 2026-10-22T00:45:04.817Z Evidence SHA-256 `8e027ef69b8de06c4b2a8b217bfe816b1f1536269bb257fd295b4ef1ba8246ac` Source locator `/rows/8304/row` | | | | | | | | [DesignArena Data visualization generation](https://benchize.com/benchmarks/designarena%3Adata-viz.md) | 1,163elo | — | 68 / 99 | — | [designarena · public](https://www.designarena.ai/api/leaderboard#board=data-viz) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `elo` \| 1163 \| elo \| data-viz \| Higher is better \| ### Configuration arenaType models category dataviz inputModality Not reported sourceModelVersion hy3-direct variationName public ### Reported statistics averageGenerationTimeMs 164241 battles 1219 losses 741 standardError Not reported winRate 39.2 wins 478 ### Source [Original source](https://www.designarena.ai/api/leaderboard#board=data-viz) Source designarena Original model label Hy3 Source version public Observed 2026-10-21T16:37:58.264Z Evidence SHA-256 `a895f6f1a25fa8eb01f821c2097ddec4f884de7bd22f1b8a22e82e6679b71849` Source locator `/data/97` | | | | | | | | [Arena text / industry software and it services](https://benchize.com/benchmarks/lmarena%3Atext%3Aindustry_software_and_it_services.md) | 1,462.68 | — | 51 / 151 | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1462.6834125494333 \| rating \| reported \| Higher is better \| ### Configuration category industry_software_and_it_services config text ### Reported statistics lower 1454.107363923797 rank 75 upper 1471.2594611750696 variance 19.146010269085124 votes 5048 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) Source Arena Original model label Hy3 Observed 2026-10-22T00:45:04.817Z Evidence SHA-256 `8e027ef69b8de06c4b2a8b217bfe816b1f1536269bb257fd295b4ef1ba8246ac` Source locator `/rows/6775/row` | | | | | | | | [Arena text / industry entertainment and sports and media](https://benchize.com/benchmarks/lmarena%3Atext%3Aindustry_entertainment_and_sports_and_media.md) | 1,399.63 | — | 57 / 151 | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1399.6300321236938 \| rating \| reported \| Higher is better \| ### Configuration category industry_entertainment_and_sports_and_media config text ### Reported statistics lower 1388.6329968819114 rank 95 upper 1410.6270673654763 variance 31.48147351144944 votes 3176 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) Source Arena Original model label Hy3 Observed 2026-10-22T00:45:04.817Z Evidence SHA-256 `8e027ef69b8de06c4b2a8b217bfe816b1f1536269bb257fd295b4ef1ba8246ac` Source locator `/rows/4787/row` | | | | | | | | [Arena text style control / spanish](https://benchize.com/benchmarks/lmarena%3Atext_style_control%3Aspanish.md) | 1,472.44 | — | 23 / 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` \| 1472.4446491998578 \| rating \| reported \| Higher is better \| ### Configuration category spanish config text_style_control ### Reported statistics lower 1445.2911657521254 rank 30 upper 1499.5981326475899 variance 191.9353291969021 votes 458 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label Hy3 Observed 2026-10-22T00:45:04.817Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/10794/row` | | | | | | | | [OpenVibeEval Accessibility](https://benchize.com/benchmarks/openvibeeval%3Aaccessibility.md) | 78 | — | 8 / 32 | — | [openvibeeval](https://openvibeeval.com/leaderboard/) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `adjusted_score` \| 78 \| score \| sample_size_adjusted_accessibility \| Higher is better \| ### Configuration Reasoning effort unknown Model configuration Hy3 thinkingEnabled Not reported ### Reported statistics runCount 9 ### Source [Original source](https://openvibeeval.com/leaderboard/) Source openvibeeval Original model label Hy3 Evaluated 2026-08-23 Observed 2026-10-22T06:20:03.682Z Evidence SHA-256 `f8bf65237be5f5dea4402ec650c39e0d49a8287f174d52a7c3e1bb7ede7b5530` Source locator `/rows/32` | | | | | | | | [Arena text / instruction following](https://benchize.com/benchmarks/lmarena%3Atext%3Ainstruction_following.md) | 1,426.45 | — | 55 / 151 | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1426.4515852090817 \| rating \| reported \| Higher is better \| ### Configuration category instruction_following config text ### Reported statistics lower 1417.3928053281961 rank 79 upper 1435.5103650899673 variance 21.362064976010277 votes 4617 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) Source Arena Original model label Hy3 Observed 2026-10-22T00:45:04.817Z Evidence SHA-256 `8e027ef69b8de06c4b2a8b217bfe816b1f1536269bb257fd295b4ef1ba8246ac` Source locator `/rows/7612/row` | | | | | | | | [Arena text / coding](https://benchize.com/benchmarks/lmarena%3Atext%3Acoding.md) | 1,465.85 | — | 51 / 151 | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1465.8547358249393 \| rating \| reported \| Higher is better \| ### Configuration category coding config text ### Reported statistics lower 1455.6233566062858 rank 79 upper 1476.0861150435928 variance 27.250356076179504 votes 3471 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) Source Arena Original model label Hy3 Observed 2026-10-22T00:45:04.817Z Evidence SHA-256 `8e027ef69b8de06c4b2a8b217bfe816b1f1536269bb257fd295b4ef1ba8246ac` Source locator `/rows/888/row` | | | | | | | | [Arena text style control / french](https://benchize.com/benchmarks/lmarena%3Atext_style_control%3Afrench.md) | 1,479.17 | — | 42 / 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` \| 1479.1699819260953 \| rating \| reported \| Higher is better \| ### Configuration category french config text_style_control ### Reported statistics lower 1451.6228228689424 rank 64 upper 1506.717140983248 variance 197.54109247042845 votes 521 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label Hy3 Observed 2026-10-22T00:45:04.817Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/2901/row` | | | | | | | | [Arena text / expert](https://benchize.com/benchmarks/lmarena%3Atext%3Aexpert.md) | 1,460.55 | — | 52 / 148 | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1460.552940047069 \| rating \| reported \| Higher is better \| ### Configuration category expert config text ### Reported statistics lower 1444.6016995281145 rank 72 upper 1476.5041805660235 variance 66.23579373618254 votes 1358 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) Source Arena Original model label Hy3 Observed 2026-10-22T00:45:04.817Z Evidence SHA-256 `8e027ef69b8de06c4b2a8b217bfe816b1f1536269bb257fd295b4ef1ba8246ac` Source locator `/rows/2542/row` | | | | | | | | [DesignArena Overall frontend coding](https://benchize.com/benchmarks/designarena%3Acode.md) | 1,227elo | SE ±2.22 | 44 / 116 | — | [designarena · public](https://www.designarena.ai/api/leaderboard#board=code) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `elo` \| 1227 \| elo \| code \| Higher is better \| ### Configuration arenaType models category allcategories inputModality text sourceModelVersion hy3-direct variationName public ### Reported statistics Uncertainty Standard error: ±2.22 averageGenerationTimeMs 229765 battles 29429 losses 15959 standardError 2.2154 winRate 45.8 wins 13470 ### Source [Original source](https://www.designarena.ai/api/leaderboard#board=code) Source designarena Original model label Hy3 Source version public Observed 2026-10-21T16:37:57.301Z Evidence SHA-256 `0c897b58670f5e352bd123db999a40c0d1781a443964c502b90774a76a3a7758` Source locator `/data/70` | | | | | | | | [Arena text style control / creative writing](https://benchize.com/benchmarks/lmarena%3Atext_style_control%3Acreative_writing.md) | 1,422.24 | — | 49 / 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` \| 1422.2395900022793 \| rating \| reported \| Higher is better \| ### Configuration category creative_writing config text_style_control ### Reported statistics lower 1410.0945865474941 rank 80 upper 1434.384593457064 variance 38.39715998571798 votes 2575 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label Hy3 Observed 2026-10-22T00:45:04.817Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/1301/row` | | | | | | | | [Arena text / longer query](https://benchize.com/benchmarks/lmarena%3Atext%3Alonger_query.md) | 1,441.66 | — | 52 / 150 | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1441.659243242107 \| rating \| reported \| Higher is better \| ### Configuration category longer_query config text ### Reported statistics lower 1433.234736106105 rank 74 upper 1450.0837503781095 variance 18.475356315736633 votes 5770 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) Source Arena Original model label Hy3 Observed 2026-10-22T00:45:04.817Z Evidence SHA-256 `8e027ef69b8de06c4b2a8b217bfe816b1f1536269bb257fd295b4ef1ba8246ac` Source locator `/rows/8591/row` | | | | | | | | [Arena text style control / polish](https://benchize.com/benchmarks/lmarena%3Atext_style_control%3Apolish.md) | 1,463.13 | — | 34 / 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` \| 1463.1285963352104 \| rating \| reported \| Higher is better \| ### Configuration category polish config text_style_control ### Reported statistics lower 1427.0334232221896 rank 50 upper 1499.2237694482312 variance 339.158008160951 votes 241 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label Hy3 Observed 2026-10-22T00:45:04.817Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/10197/row` | | | | | | | | [DesignArena UI component generation](https://benchize.com/benchmarks/designarena%3Aui-components.md) | 1,164elo | — | 63 / 112 | — | [designarena · public](https://www.designarena.ai/api/leaderboard#board=ui-components) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `elo` \| 1164 \| elo \| ui-components \| Higher is better \| ### Configuration arenaType models category uicomponent inputModality Not reported sourceModelVersion hy3 variationName public ### Reported statistics averageGenerationTimeMs 129643 battles 286 losses 171 standardError Not reported winRate 40.2 wins 115 ### Source [Original source](https://www.designarena.ai/api/leaderboard#board=ui-components) Source designarena Original model label Hy3 Low Source version public Observed 2026-10-21T16:37:57.993Z Evidence SHA-256 `46482ec1b4012638eace65493daea4750e2088098018fd9d5fc46126fc1f8557` Source locator `/data/95` | | | | | | | | [Arena text style control / industry medicine and healthcare](https://benchize.com/benchmarks/lmarena%3Atext_style_control%3Aindustry_medicine_and_healthcare.md) | 1,480.53 | — | 34 / 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` \| 1480.5272807944161 \| rating \| reported \| Higher is better \| ### Configuration category industry_medicine_and_healthcare config text_style_control ### Reported statistics lower 1459.5347944415898 rank 56 upper 1501.5197671472424 variance 114.71800267638099 votes 821 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label Hy3 Observed 2026-10-22T00:45:04.817Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/6368/row` | | | | | | | | [Arena webdev / webdev-react](https://benchize.com/benchmarks/lmarena%3Awebdev%3Awebdev-react.md) | 1,510.83 | — | 42 / 81 | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/webdev/latest) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1510.8298957990887 \| rating \| reported \| Higher is better \| ### Configuration category webdev-react config webdev ### Reported statistics lower 1500.4902534669031 rank 57 upper 1521.1695381312747 variance 27.83010531874111 votes 3947 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/webdev/latest) Source Arena Original model label Hy3 Observed 2026-10-22T00:45:04.817Z Evidence SHA-256 `f82507859808110820a4ab6df15561b8864137ddefc1f6fb0c552af2e58ea738` Source locator `/rows/563/row` | | | | | | | | [Arena text style control / korean](https://benchize.com/benchmarks/lmarena%3Atext_style_control%3Akorean.md) | 1,412.56 | — | 44 / 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` \| 1412.55643265871 \| rating \| reported \| Higher is better \| ### Configuration category korean config text_style_control ### Reported statistics lower 1377.2453147665433 rank 71 upper 1447.8675505508772 variance 324.5837336788696 votes 269 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label Hy3 Observed 2026-10-22T00:45:04.817Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/8304/row` | | | | | | | | [DesignArena ASCII art generation](https://benchize.com/benchmarks/designarena%3Aascii.md) | 1,152elo | — | 36 / 65 | — | [designarena · public](https://www.designarena.ai/api/leaderboard#board=ascii) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `elo` \| 1152 \| elo \| ascii \| Higher is better \| ### Configuration arenaType models category ascii inputModality Not reported sourceModelVersion hy3-direct variationName public ### Reported statistics averageGenerationTimeMs 237291 battles 204 losses 118 standardError Not reported winRate 42.2 wins 86 ### Source [Original source](https://www.designarena.ai/api/leaderboard#board=ascii) Source designarena Original model label Hy3 Source version public Observed 2026-10-21T16:38:03.513Z Evidence SHA-256 `0603b8c65b44ee887f5b566feb469465f59635137a6ac5c6d94c23bcf3776311` Source locator `/data/54` | | | | | | | | [Arena text / exclude ties](https://benchize.com/benchmarks/lmarena%3Atext%3Aexclude_ties.md) | 1,432.11 | — | 51 / 151 | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1432.1063109526472 \| rating \| reported \| Higher is better \| ### Configuration category exclude_ties config text ### Reported statistics lower 1424.1725877704225 rank 81 upper 1440.0400341348716 variance 16.38543232406492 votes 9404 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) Source Arena Original model label Hy3 Observed 2026-10-22T00:45:04.817Z Evidence SHA-256 `8e027ef69b8de06c4b2a8b217bfe816b1f1536269bb257fd295b4ef1ba8246ac` Source locator `/rows/2134/row` | | | | | | | | [DesignArena Website generation](https://benchize.com/benchmarks/designarena%3Awebsite.md) | 1,230elo | — | 44 / 123 | — | [designarena · public](https://www.designarena.ai/api/leaderboard#board=website) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `elo` \| 1230 \| elo \| website \| Higher is better \| ### Configuration arenaType models category website inputModality text sourceModelVersion hy3-direct variationName public ### Reported statistics averageGenerationTimeMs 233864 battles 19430 losses 10470 standardError Not reported winRate 46.1 wins 8960 ### Source [Original source](https://www.designarena.ai/api/leaderboard#board=website) Source designarena Original model label Hy3 Source version public Observed 2026-10-21T16:37:57.757Z Evidence SHA-256 `51873e97776a3c5ae706b24cc2c60384793dd18398df970e213a8e7c276d8ac0` Source locator `/data/71` | | | | | | | | [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) | 1,417.81 | — | 49 / 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` \| 1417.8099735945254 \| rating \| reported \| Higher is better \| ### Configuration category industry_entertainment_and_sports_and_media config text_style_control ### Reported statistics lower 1406.7954193678984 rank 81 upper 1428.8245278211523 variance 31.581857433365382 votes 3176 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label Hy3 Observed 2026-10-22T00:45:04.817Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/4773/row` | | | | | | | | [DesignArena Data visualization generation](https://benchize.com/benchmarks/designarena%3Adata-viz.md) | 1,125elo | — | 80 / 99 | — | [designarena · public](https://www.designarena.ai/api/leaderboard#board=data-viz) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `elo` \| 1125 \| elo \| data-viz \| Higher is better \| ### Configuration arenaType models category dataviz inputModality Not reported sourceModelVersion hy3 variationName public ### Reported statistics averageGenerationTimeMs 97319 battles 266 losses 170 standardError Not reported winRate 36.1 wins 96 ### Source [Original source](https://www.designarena.ai/api/leaderboard#board=data-viz) Source designarena Original model label Hy3 Low Source version public Observed 2026-10-21T16:37:58.264Z Evidence SHA-256 `a895f6f1a25fa8eb01f821c2097ddec4f884de7bd22f1b8a22e82e6679b71849` Source locator `/data/117` | | | | | | | | [DesignArena Browser game generation](https://benchize.com/benchmarks/designarena%3Agame-dev.md) | 1,208elo | — | 43 / 117 | — | [designarena · public](https://www.designarena.ai/api/leaderboard#board=game-dev) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `elo` \| 1208 \| elo \| game-dev \| Higher is better \| ### Configuration arenaType models category gamedev inputModality Not reported sourceModelVersion hy3-direct variationName public ### Reported statistics averageGenerationTimeMs 241250 battles 3140 losses 1820 standardError Not reported winRate 42 wins 1320 ### Source [Original source](https://www.designarena.ai/api/leaderboard#board=game-dev) Source designarena Original model label Hy3 Source version public Observed 2026-10-21T16:38:01.100Z Evidence SHA-256 `53db6a89112ce8cdf644568c666d4b8309aece764cfcedb291ffd52ae3934e30` Source locator `/data/68` | | | | | | | | [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) | 1,449.99 | — | 50 / 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` \| 1449.9864727409865 \| rating \| reported \| Higher is better \| ### Configuration category industry_business_and_management_and_financial_operations config text_style_control ### Reported statistics lower 1437.6580799558924 rank 76 upper 1462.3148655260804 variance 39.56550772971572 votes 2408 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label Hy3 Observed 2026-10-22T00:45:04.817Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/4358/row` | | | | | | | | [Arena text / english](https://benchize.com/benchmarks/lmarena%3Atext%3Aenglish.md) | 1,447.83 | — | 47 / 151 | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1447.8273404868328 \| rating \| reported \| Higher is better \| ### Configuration category english config text ### Reported statistics lower 1439.172558921097 rank 77 upper 1456.4821220525687 variance 19.49916618839748 votes 4863 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) Source Arena Original model label Hy3 Observed 2026-10-22T00:45:04.817Z Evidence SHA-256 `8e027ef69b8de06c4b2a8b217bfe816b1f1536269bb257fd295b4ef1ba8246ac` Source locator `/rows/1713/row` | | | | | | | | [Arena text / polish](https://benchize.com/benchmarks/lmarena%3Atext%3Apolish.md) | 1,446.56 | — | 34 / 117 | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1446.5598903325551 \| rating \| reported \| Higher is better \| ### Configuration category polish config text ### Reported statistics lower 1409.9155196166166 rank 55 upper 1483.2042610484934 variance 349.5572822317767 votes 241 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) Source Arena Original model label Hy3 Observed 2026-10-22T00:45:04.817Z Evidence SHA-256 `8e027ef69b8de06c4b2a8b217bfe816b1f1536269bb257fd295b4ef1ba8246ac` Source locator `/rows/10202/row` | | | | | | | | [Arena text style control / industry software and it services](https://benchize.com/benchmarks/lmarena%3Atext_style_control%3Aindustry_software_and_it_services.md) | 1,491.06 | — | 47 / 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` \| 1491.0551834080352 \| rating \| reported \| Higher is better \| ### Configuration category industry_software_and_it_services config text_style_control ### Reported statistics lower 1482.4287965833255 rank 71 upper 1499.681570232745 variance 19.37142974139127 votes 5048 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label Hy3 Observed 2026-10-22T00:45:04.817Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/6771/row` | | | | | | | | [Arena text / industry business and management and financial operations](https://benchize.com/benchmarks/lmarena%3Atext%3Aindustry_business_and_management_and_financial_operations.md) | 1,424.01 | — | 60 / 151 | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1424.0073936778208 \| rating \| reported \| Higher is better \| ### Configuration category industry_business_and_management_and_financial_operations config text ### Reported statistics lower 1411.7443145185416 rank 95 upper 1436.2704728371002 variance 39.14739620704234 votes 2408 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) Source Arena Original model label Hy3 Observed 2026-10-22T00:45:04.817Z Evidence SHA-256 `8e027ef69b8de06c4b2a8b217bfe816b1f1536269bb257fd295b4ef1ba8246ac` Source locator `/rows/4377/row` | | | | | | | | [Arena text / japanese](https://benchize.com/benchmarks/lmarena%3Atext%3Ajapanese.md) | 1,396.87 | — | 47 / 120 | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1396.8749167362332 \| rating \| reported \| Higher is better \| ### Configuration category japanese config text ### Reported statistics lower 1357.4976136488294 rank 80 upper 1436.2522198236372 variance 403.6414473804244 votes 236 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) Source Arena Original model label Hy3 Observed 2026-10-22T00:45:04.817Z Evidence SHA-256 `8e027ef69b8de06c4b2a8b217bfe816b1f1536269bb257fd295b4ef1ba8246ac` Source locator `/rows/8030/row` | | | | | | | | [Arena text style control / chinese](https://benchize.com/benchmarks/lmarena%3Atext_style_control%3Achinese.md) | 1,501.33 | — | 40 / 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` \| 1501.3285053161574 \| rating \| reported \| Higher is better \| ### Configuration category chinese config text_style_control ### Reported statistics lower 1482.4325125827854 rank 55 upper 1520.2244980495293 variance 92.9486838323376 votes 973 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label Hy3 Observed 2026-10-22T00:45:04.817Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/471/row` | | | | | | | | [Arena text / industry legal and government](https://benchize.com/benchmarks/lmarena%3Atext%3Aindustry_legal_and_government.md) | 1,422.25 | — | 73 / 151 | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1422.2461856743241 \| rating \| reported \| Higher is better \| ### Configuration category industry_legal_and_government config text ### Reported statistics lower 1403.0541801601767 rank 126 upper 1441.4381911884718 variance 95.8836454710492 votes 978 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) Source Arena Original model label Hy3 Observed 2026-10-22T00:45:04.817Z Evidence SHA-256 `8e027ef69b8de06c4b2a8b217bfe816b1f1536269bb257fd295b4ef1ba8246ac` Source locator `/rows/5233/row` | | | | | | | | [Arena text / industry medicine and healthcare](https://benchize.com/benchmarks/lmarena%3Atext%3Aindustry_medicine_and_healthcare.md) | 1,451.67 | — | 42 / 151 | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1451.665651572402 \| rating \| reported \| Higher is better \| ### Configuration category industry_medicine_and_healthcare config text ### Reported statistics lower 1430.9775897535706 rank 70 upper 1472.3537133912337 variance 111.41493942721974 votes 821 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) Source Arena Original model label Hy3 Observed 2026-10-22T00:45:04.817Z Evidence SHA-256 `8e027ef69b8de06c4b2a8b217bfe816b1f1536269bb257fd295b4ef1ba8246ac` Source locator `/rows/6382/row` | | | | | | | | [Arena text style control / math](https://benchize.com/benchmarks/lmarena%3Atext_style_control%3Amath.md) | 1,481.02 | — | 33 / 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` \| 1481.0203138901077 \| rating \| reported \| Higher is better \| ### Configuration category math config text_style_control ### Reported statistics lower 1459.2057186087386 rank 38 upper 1502.8349091714765 variance 123.87912756642254 votes 689 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label Hy3 Observed 2026-10-22T00:45:04.817Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/8950/row` | | | | | | | | [Arena text / german](https://benchize.com/benchmarks/lmarena%3Atext%3Agerman.md) | 1,448.51 | — | 36 / 129 | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1448.511448651218 \| rating \| reported \| Higher is better \| ### Configuration category german config text ### Reported statistics lower 1412.0231356924915 rank 54 upper 1484.9997616099445 variance 346.58629565457414 votes 227 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) Source Arena Original model label Hy3 Observed 2026-10-22T00:45:04.817Z Evidence SHA-256 `8e027ef69b8de06c4b2a8b217bfe816b1f1536269bb257fd295b4ef1ba8246ac` Source locator `/rows/3190/row` | | | | | | | | [Arena text style control / industry mathematical](https://benchize.com/benchmarks/lmarena%3Atext_style_control%3Aindustry_mathematical.md) | 1,492.53 | — | 26 / 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` \| 1492.533135107807 \| rating \| reported \| Higher is better \| ### Configuration category industry_mathematical config text_style_control ### Reported statistics lower 1471.5846291475782 rank 31 upper 1513.4816410680364 variance 114.23782538074056 votes 754 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label Hy3 Observed 2026-10-22T00:45:04.817Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/5943/row` | | | | | | | | [Arena text / math](https://benchize.com/benchmarks/lmarena%3Atext%3Amath.md) | 1,473.02 | — | 33 / 149 | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1473.0190855339595 \| rating \| reported \| Higher is better \| ### Configuration category math config text ### Reported statistics lower 1451.1754614036486 rank 42 upper 1494.8627096642704 variance 124.20904073626902 votes 689 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) Source Arena Original model label Hy3 Observed 2026-10-22T00:45:04.817Z Evidence SHA-256 `8e027ef69b8de06c4b2a8b217bfe816b1f1536269bb257fd295b4ef1ba8246ac` Source locator `/rows/8954/row` | | | | | | | | [Arena text style control / industry life and physical and social science](https://benchize.com/benchmarks/lmarena%3Atext_style_control%3Aindustry_life_and_physical_and_social_science.md) | 1,482.77 | — | 40 / 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` \| 1482.7716532566299 \| rating \| reported \| Higher is better \| ### Configuration category industry_life_and_physical_and_social_science config text_style_control ### Reported statistics lower 1469.5193979102328 rank 55 upper 1496.0239086030272 variance 45.7175984342273 votes 2014 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label Hy3 Observed 2026-10-22T00:45:04.817Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/5552/row` | | | | | | | | [Arena text / hard prompts english](https://benchize.com/benchmarks/lmarena%3Atext%3Ahard_prompts_english.md) | 1,454.84 | — | 51 / 151 | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1454.8375474910918 \| rating \| reported \| Higher is better \| ### Configuration category hard_prompts_english config text ### Reported statistics lower 1444.3201894365475 rank 74 upper 1465.3549055456356 variance 28.79500356781066 votes 3247 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) Source Arena Original model label Hy3 Observed 2026-10-22T00:45:04.817Z Evidence SHA-256 `8e027ef69b8de06c4b2a8b217bfe816b1f1536269bb257fd295b4ef1ba8246ac` Source locator `/rows/3941/row` | | | | | | | | [DesignArena Overall frontend coding](https://benchize.com/benchmarks/designarena%3Acode.md) | 1,177elo | SE ±5.64 | 57 / 116 | — | [designarena · public](https://www.designarena.ai/api/leaderboard#board=code) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `elo` \| 1177 \| elo \| code \| Higher is better \| ### Configuration arenaType models category allcategories inputModality text sourceModelVersion hy3 variationName public ### Reported statistics Uncertainty Standard error: ±5.64 averageGenerationTimeMs 132343 battles 4072 losses 2396 standardError 5.6446 winRate 41.2 wins 1676 ### Source [Original source](https://www.designarena.ai/api/leaderboard#board=code) Source designarena Original model label Hy3 Low Source version public Observed 2026-10-21T16:37:57.301Z Evidence SHA-256 `0c897b58670f5e352bd123db999a40c0d1781a443964c502b90774a76a3a7758` Source locator `/data/90` | | | | | | | | [DesignArena 3D design generation](https://benchize.com/benchmarks/designarena%3A3d-design.md) | 1,176elo | — | 45 / 110 | — | [designarena · public](https://www.designarena.ai/api/leaderboard#board=3d-design) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `elo` \| 1176 \| elo \| 3d-design \| Higher is better \| ### Configuration arenaType models category 3d inputModality Not reported sourceModelVersion hy3 variationName public ### Reported statistics averageGenerationTimeMs 120415 battles 769 losses 431 standardError Not reported winRate 44 wins 338 ### Source [Original source](https://www.designarena.ai/api/leaderboard#board=3d-design) Source designarena Original model label Hy3 Low Source version public Observed 2026-10-21T16:37:58.515Z Evidence SHA-256 `bcc0267f7bc7e9ec112306b3a35413cf78bbccbfaa838356232d5d5ed0b83d0f` Source locator `/data/73` | | | | | | | | [Arena text style control / german](https://benchize.com/benchmarks/lmarena%3Atext_style_control%3Agerman.md) | 1,467.34 | — | 34 / 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` \| 1467.3404885107034 \| rating \| reported \| Higher is better \| ### Configuration category german config text_style_control ### Reported statistics lower 1430.8288000854902 rank 48 upper 1503.8521769359163 variance 347.0305042652908 votes 227 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label Hy3 Observed 2026-10-22T00:45:04.817Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/3184/row` | | | | | | | | [Arena text / industry mathematical](https://benchize.com/benchmarks/lmarena%3Atext%3Aindustry_mathematical.md) | 1,482.21 | — | 32 / 148 | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1482.2144185719412 \| rating \| reported \| Higher is better \| ### Configuration category industry_mathematical config text ### Reported statistics lower 1461.1624422849843 rank 39 upper 1503.2663948588981 variance 115.3691152952461 votes 754 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) Source Arena Original model label Hy3 Observed 2026-10-22T00:45:04.817Z Evidence SHA-256 `8e027ef69b8de06c4b2a8b217bfe816b1f1536269bb257fd295b4ef1ba8246ac` Source locator `/rows/5951/row` | | | | | | | | [Arena text / spanish](https://benchize.com/benchmarks/lmarena%3Atext%3Aspanish.md) | 1,456.83 | — | 31 / 134 | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1456.8268662597588 \| rating \| reported \| Higher is better \| ### Configuration category spanish config text ### Reported statistics lower 1429.595828351682 rank 46 upper 1484.0579041678357 variance 193.03328765532117 votes 458 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) Source Arena Original model label Hy3 Observed 2026-10-22T00:45:04.817Z Evidence SHA-256 `8e027ef69b8de06c4b2a8b217bfe816b1f1536269bb257fd295b4ef1ba8246ac` Source locator `/rows/10810/row` | | | | | | | | [Arena text / multi turn](https://benchize.com/benchmarks/lmarena%3Atext%3Amulti_turn.md) | 1,435.85 | — | 58 / 151 | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1435.8540734950047 \| rating \| reported \| Higher is better \| ### Configuration category multi_turn config text ### Reported statistics lower 1422.4909433585963 rank 92 upper 1449.2172036314134 variance 46.48578974232588 votes 2060 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) Source Arena Original model label Hy3 Observed 2026-10-22T00:45:04.817Z Evidence SHA-256 `8e027ef69b8de06c4b2a8b217bfe816b1f1536269bb257fd295b4ef1ba8246ac` Source locator `/rows/9407/row` | | | | | | | | [DesignArena 3D design generation](https://benchize.com/benchmarks/designarena%3A3d-design.md) | 1,233elo | — | 33 / 110 | — | [designarena · public](https://www.designarena.ai/api/leaderboard#board=3d-design) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `elo` \| 1233 \| elo \| 3d-design \| Higher is better \| ### Configuration arenaType models category 3d inputModality Not reported sourceModelVersion hy3-direct variationName public ### Reported statistics averageGenerationTimeMs 227543 battles 4172 losses 2093 standardError Not reported winRate 49.8 wins 2079 ### Source [Original source](https://www.designarena.ai/api/leaderboard#board=3d-design) Source designarena Original model label Hy3 Source version public Observed 2026-10-21T16:37:58.515Z Evidence SHA-256 `bcc0267f7bc7e9ec112306b3a35413cf78bbccbfaa838356232d5d5ed0b83d0f` Source locator `/data/53` | | | | | | | | [DesignArena SVG generation](https://benchize.com/benchmarks/designarena%3Asvgs.md) | 1,200elo | — | 22 / 77 | — | [designarena · public](https://www.designarena.ai/api/leaderboard#board=svgs) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `elo` \| 1200 \| elo \| svgs \| Higher is better \| ### Configuration arenaType models category svg inputModality Not reported sourceModelVersion hy3-direct variationName public ### Reported statistics averageGenerationTimeMs 185376 battles 1097 losses 608 standardError Not reported winRate 44.6 wins 489 ### Source [Original source](https://www.designarena.ai/api/leaderboard#board=svgs) Source designarena Original model label Hy3 Source version public Observed 2026-10-21T16:38:03.249Z Evidence SHA-256 `8cbc34a474a66ef5c64f3ffe557df9b55bf7e13368c07c0214223e3ed8f3f21e` Source locator `/data/44` | | | | | | | | [Arena text style control / multi turn](https://benchize.com/benchmarks/lmarena%3Atext_style_control%3Amulti_turn.md) | 1,451.21 | — | 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` \| 1451.2055951058674 \| rating \| reported \| Higher is better \| ### Configuration category multi_turn config text_style_control ### Reported statistics lower 1437.8009415159881 rank 87 upper 1464.6102486957466 variance 46.775130556311396 votes 2060 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label Hy3 Observed 2026-10-22T00:45:04.817Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/9402/row` | | | | | | | | [Arena text / french](https://benchize.com/benchmarks/lmarena%3Atext%3Afrench.md) | 1,456.17 | — | 46 / 132 | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1456.173625292643 \| rating \| reported \| Higher is better \| ### Configuration category french config text ### Reported statistics lower 1429.0172808848329 rank 70 upper 1483.329969700453 variance 191.97577691652654 votes 521 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) Source Arena Original model label Hy3 Observed 2026-10-22T00:45:04.817Z Evidence SHA-256 `8e027ef69b8de06c4b2a8b217bfe816b1f1536269bb257fd295b4ef1ba8246ac` Source locator `/rows/2907/row` | | | | | | | | [Arena text style control / japanese](https://benchize.com/benchmarks/lmarena%3Atext_style_control%3Ajapanese.md) | 1,416.64 | — | 48 / 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` \| 1416.638668388446 \| rating \| reported \| Higher is better \| ### Configuration category japanese config text_style_control ### Reported statistics lower 1377.2299116323277 rank 75 upper 1456.0474251445642 variance 404.2865436163324 votes 236 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label Hy3 Observed 2026-10-22T00:45:04.817Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/8025/row` | | | | | | | | [Arena text style control / hard prompts english](https://benchize.com/benchmarks/lmarena%3Atext_style_control%3Ahard_prompts_english.md) | 1,483.48 | — | 48 / 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` \| 1483.4804990217172 \| rating \| reported \| Higher is better \| ### Configuration category hard_prompts_english config text_style_control ### Reported statistics lower 1472.893982556674 rank 69 upper 1494.0670154867603 variance 29.174940067268306 votes 3247 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label Hy3 Observed 2026-10-22T00:45:04.817Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/3936/row` | | | | | | | | [Long-Horizon Terminal-Bench](https://benchize.com/benchmarks/lhtb%3Aoverall.md) | 28.8% | — | 13 / 19 | $2.47 | [lhtb](https://zli12321.github.io/LHTB/script.js) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `mean_reward` \| 0.288 \| score_fraction \| reported \| Higher is better \| \| `solved_count` \| 1 \| tasks \| reward_gte_0_95 \| Higher is better \| \| `cost_per_task` \| 2.47 \| 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 Hy3 Observed 2026-10-22T05:00:05.057Z Evidence SHA-256 `8b9c27664cc6298fa234c607ca27c953ec91b2eb9d116b8530cfaaa6722fa39e` Source locator `/rows/13` | | | | | | | | [Arena text style control / exclude ties](https://benchize.com/benchmarks/lmarena%3Atext_style_control%3Aexclude_ties.md) | 1,454.6 | — | 49 / 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` \| 1454.6001258946885 \| rating \| reported \| Higher is better \| ### Configuration category exclude_ties config text_style_control ### Reported statistics lower 1446.5608590291688 rank 76 upper 1462.6393927602085 variance 16.824288571539903 votes 9404 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label Hy3 Observed 2026-10-22T00:45:04.817Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/2129/row` | | | | | | | | [Arena text style control / instruction following](https://benchize.com/benchmarks/lmarena%3Atext_style_control%3Ainstruction_following.md) | 1,447.29 | — | 46 / 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` \| 1447.2880882657869 \| rating \| reported \| Higher is better \| ### Configuration category instruction_following config text_style_control ### Reported statistics lower 1438.2189013489178 rank 68 upper 1456.3572751826562 variance 21.411176111019373 votes 4617 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label Hy3 Observed 2026-10-22T00:45:04.817Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/7601/row` | | | | | | | | [Arena webdev / webdev-html](https://benchize.com/benchmarks/lmarena%3Awebdev%3Awebdev-html.md) | 1,486.65 | — | 46 / 89 | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/webdev/latest) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1486.651034528798 \| rating \| reported \| Higher is better \| ### Configuration category webdev-html config webdev ### Reported statistics lower 1466.1317729100742 rank 67 upper 1507.1702961475212 variance 109.60421991495899 votes 970 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/webdev/latest) Source Arena Original model label Hy3 Observed 2026-10-22T00:45:04.817Z Evidence SHA-256 `f82507859808110820a4ab6df15561b8864137ddefc1f6fb0c552af2e58ea738` Source locator `/rows/426/row` | | | | | | | | [Arena text / creative writing](https://benchize.com/benchmarks/lmarena%3Atext%3Acreative_writing.md) | 1,402.76 | — | 56 / 151 | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1402.7596029581148 \| rating \| reported \| Higher is better \| ### Configuration category creative_writing config text ### Reported statistics lower 1390.621169439883 rank 93 upper 1414.8980364763468 variance 38.35562872177601 votes 2575 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) Source Arena Original model label Hy3 Observed 2026-10-22T00:45:04.817Z Evidence SHA-256 `8e027ef69b8de06c4b2a8b217bfe816b1f1536269bb257fd295b4ef1ba8246ac` Source locator `/rows/1314/row` | | | | | | | | [Arena text / non english](https://benchize.com/benchmarks/lmarena%3Atext%3Anon_english.md) | 1,425.79 | — | 52 / 151 | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1425.787759773208 \| rating \| reported \| Higher is better \| ### Configuration category non_english config text ### Reported statistics lower 1418.606034082735 rank 81 upper 1432.9694854636812 variance 13.426457577874295 votes 7927 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) Source Arena Original model label Hy3 Observed 2026-10-22T00:45:04.817Z Evidence SHA-256 `8e027ef69b8de06c4b2a8b217bfe816b1f1536269bb257fd295b4ef1ba8246ac` Source locator `/rows/9811/row` | | | | | | | | [DesignArena Browser game generation](https://benchize.com/benchmarks/designarena%3Agame-dev.md) | 1,136elo | — | 73 / 117 | — | [designarena · public](https://www.designarena.ai/api/leaderboard#board=game-dev) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `elo` \| 1136 \| elo \| game-dev \| Higher is better \| ### Configuration arenaType models category gamedev inputModality Not reported sourceModelVersion hy3 variationName public ### Reported statistics averageGenerationTimeMs 89395 battles 342 losses 210 standardError Not reported winRate 38.6 wins 132 ### Source [Original source](https://www.designarena.ai/api/leaderboard#board=game-dev) Source designarena Original model label Hy3 Low Source version public Observed 2026-10-21T16:38:01.100Z Evidence SHA-256 `53db6a89112ce8cdf644568c666d4b8309aece764cfcedb291ffd52ae3934e30` Source locator `/data/110` | | | | | | | | [Arena text / hard prompts](https://benchize.com/benchmarks/lmarena%3Atext%3Ahard_prompts.md) | 1,447.47 | — | 53 / 151 | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1447.4650180538183 \| rating \| reported \| Higher is better \| ### Configuration category hard_prompts config text ### Reported statistics lower 1440.3738035493047 rank 81 upper 1454.5562325583319 variance 13.090163267697907 votes 8479 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) Source Arena Original model label Hy3 Observed 2026-10-22T00:45:04.817Z Evidence SHA-256 `8e027ef69b8de06c4b2a8b217bfe816b1f1536269bb257fd295b4ef1ba8246ac` Source locator `/rows/3531/row` | | | | | | | | [Arena text style control / non english](https://benchize.com/benchmarks/lmarena%3Atext_style_control%3Anon_english.md) | 1,439.73 | — | 48 / 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` \| 1439.7263417205975 \| rating \| reported \| Higher is better \| ### Configuration category non_english config text_style_control ### Reported statistics lower 1432.5273182562219 rank 73 upper 1446.925365184973 variance 13.491212911470404 votes 7927 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label Hy3 Observed 2026-10-22T00:45:04.817Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/9803/row` | | | | | | | | [Arena text / chinese](https://benchize.com/benchmarks/lmarena%3Atext%3Achinese.md) | 1,484.96 | — | 47 / 146 | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1484.960800662788 \| rating \| reported \| Higher is better \| ### Configuration category chinese config text ### Reported statistics lower 1465.9182481014357 rank 72 upper 1504.00335322414 variance 94.39612006210082 votes 973 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) Source Arena Original model label Hy3 Observed 2026-10-22T00:45:04.817Z Evidence SHA-256 `8e027ef69b8de06c4b2a8b217bfe816b1f1536269bb257fd295b4ef1ba8246ac` Source locator `/rows/488/row` | | | | | | | --- Cite as: Hy3 — Benchize, https://benchize.com/models/hy3 (retrieved 2026-10-22)