# Qwen2.5 72B Instruct > Source: Benchize (https://benchize.com) — https://benchize.com/models/qwen-2-5-72b-instruct. When citing or reusing this content, credit "Benchize" and link to https://benchize.com/models/qwen-2-5-72b-instruct. Alibaba Canonical URL: https://benchize.com/models/qwen-2-5-72b-instruct Last updated: Thu, 22 Oct 2026 06:30:09 GMT Reproduction and quotation must name Benchize, link to the canonical HTML URL, and retain individual source citations. Alibaba ## Benchmarks | Benchmark | Score | ± | Rank | Source | | | --- | --- | --- | --- | --- | --- | | [Arena text / exclude ties](https://benchize.com/benchmarks/lmarena%3Atext%3Aexclude_ties.md) | 1,189.1 | — | 141 / 151 | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1189.098331182921 \| rating \| reported \| Higher is better \| ### Configuration category exclude_ties config text ### Reported statistics lower 1182.7174795162737 rank 283 upper 1195.479182849568 variance 10.598907834809632 votes 24444 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) Source Arena Original model label Qwen2.5-72B-Instruct Observed 2026-10-22T00:45:04.817Z Evidence SHA-256 `8e027ef69b8de06c4b2a8b217bfe816b1f1536269bb257fd295b4ef1ba8246ac` Source locator `/rows/2336/row` | | | | | | | [Arena text style control / overall](https://benchize.com/benchmarks/lmarena%3Atext_style_control%3Aoverall.md) | 1,302.91 | — | 139 / 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` \| 1302.9084257181844 \| rating \| reported \| Higher is better \| ### Configuration category overall config text_style_control ### Reported statistics lower 1298.8200482178788 rank 286 upper 1306.99680321849 variance 4.35116745101151 votes 39406 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label Qwen2.5-72B-Instruct Observed 2026-10-22T00:45:04.817Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/285/row` | | | | | | | [Arena text style control / german](https://benchize.com/benchmarks/lmarena%3Atext_style_control%3Agerman.md) | 1,266.08 | — | 121 / 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` \| 1266.0760848283558 \| rating \| reported \| Higher is better \| ### Configuration category german config text_style_control ### Reported statistics lower 1246.7215335497476 rank 246 upper 1285.4306361069634 variance 97.51468717516406 votes 926 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label Qwen2.5-72B-Instruct Observed 2026-10-22T00:45:04.817Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/3382/row` | | | | | | | [Arena text style control / spanish](https://benchize.com/benchmarks/lmarena%3Atext_style_control%3Aspanish.md) | 1,293.43 | — | 127 / 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` \| 1293.4321831127963 \| rating \| reported \| Higher is better \| ### Configuration category spanish config text_style_control ### Reported statistics lower 1262.1957043874463 rank 245 upper 1324.6686618381464 variance 253.99663219165714 votes 347 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label Qwen2.5-72B-Instruct Observed 2026-10-22T00:45:04.817Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/11009/row` | | | | | | | [Creative Writing v2](https://benchize.com/benchmarks/eq-bench%3Acreative-writing-v2.md) | 72.16% | CI 70.06–74.26% | 13 / 18 | [eq bench · creative-writing-v2](https://eqbench.com/creative_writing_v2.js) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `score` \| 72.16 \| percent \| overall \| Higher is better \| ### Configuration interactiveAdjustments none protocol creative-writing-v2 sourceModelVersion Qwen/Qwen2.5-72B-Instruct ### Reported statistics Uncertainty Confidence interval: 70.06–74.26% confidenceIntervalHigh 74.26 confidenceIntervalLow 70.06 ### Source [Original source](https://eqbench.com/creative_writing_v2.js) Source eq bench Original model label Qwen/Qwen2.5-72B-Instruct Source version creative-writing-v2 Observed 2026-10-22T05:10:05.638Z Evidence SHA-256 `264c33d486559c25267ca29861754404dadb674022dcdf6530388cd9951af31a` Source locator `/leaderboardDataCreativeWriting/19` | | | | | | | [Arena text style control / math](https://benchize.com/benchmarks/lmarena%3Atext_style_control%3Amath.md) | 1,295.92 | — | 132 / 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` \| 1295.920819892729 \| rating \| reported \| Higher is better \| ### Configuration category math config text_style_control ### Reported statistics lower 1287.6264342911818 rank 257 upper 1304.215205494276 variance 17.9090381332579 votes 5415 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label Qwen2.5-72B-Instruct Observed 2026-10-22T00:45:04.817Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/9169/row` | | | | | | | [Arena text style control / chinese](https://benchize.com/benchmarks/lmarena%3Atext_style_control%3Achinese.md) | 1,322.67 | — | 130 / 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` \| 1322.667181898144 \| rating \| reported \| Higher is better \| ### Configuration category chinese config text_style_control ### Reported statistics lower 1311.5458262856712 rank 260 upper 1333.7885375106168 variance 32.19728661225913 votes 3329 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label Qwen2.5-72B-Instruct Observed 2026-10-22T00:45:04.817Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/676/row` | | | | | | | [MATH Level 5](https://benchize.com/benchmarks/epoch-ai%3Amath_level_5.md) | 63.17% | SE ±1.07 pp | 11 / 21 | [epoch ai · MATH level 5](https://epoch.ai/data/benchmark_data.zip#file=math_level_5.csv) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `score` \| 0.631703172205438 \| score_fraction \| Best score (across scorers) \| Higher is better \| \| `mean_score` \| 0.631703172205438 \| score_fraction \| mean_score \| Higher is better \| ### Configuration benchmarkVersion MATH level 5 reasoningBudget Not reported Reasoning effort Not reported sourceModelVersion qwen2.5-72b-instruct ### Reported statistics Uncertainty Standard error: ±1.07 pp standardError 0.01071424933114761 ### Source [Original source](https://epoch.ai/data/benchmark_data.zip#file=math_level_5.csv) Source epoch ai Original model label qwen2.5-72b-instruct Source version MATH level 5 Evaluated 2025-01-27T00:00:00.000Z Observed 2026-10-22T03:00:05.281Z Evidence SHA-256 `041b4bcb991a81d66152327113ef6d38e64cd8cce93d1e6ec821d1b9e47c1de3` Source locator `/rows/104` | | | | | | | [Arena text / coding](https://benchize.com/benchmarks/lmarena%3Atext%3Acoding.md) | 1,292.31 | — | 132 / 151 | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1292.3060644713746 \| rating \| reported \| Higher is better \| ### Configuration category coding config text ### Reported statistics lower 1284.7056374078081 rank 263 upper 1299.906491534941 variance 15.037644354639966 votes 6688 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) Source Arena Original model label Qwen2.5-72B-Instruct Observed 2026-10-22T00:45:04.817Z Evidence SHA-256 `8e027ef69b8de06c4b2a8b217bfe816b1f1536269bb257fd295b4ef1ba8246ac` Source locator `/rows/1072/row` | | | | | | | [Arena text / instruction following](https://benchize.com/benchmarks/lmarena%3Atext%3Ainstruction_following.md) | 1,253.98 | — | 135 / 151 | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1253.9816519637493 \| rating \| reported \| Higher is better \| ### Configuration category instruction_following config text ### Reported statistics lower 1248.3415331104927 rank 270 upper 1259.621770817006 variance 8.280953190879915 votes 16363 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) Source Arena Original model label Qwen2.5-72B-Instruct Observed 2026-10-22T00:45:04.817Z Evidence SHA-256 `8e027ef69b8de06c4b2a8b217bfe816b1f1536269bb257fd295b4ef1ba8246ac` Source locator `/rows/7803/row` | | | | | | | [Arena text style control / japanese](https://benchize.com/benchmarks/lmarena%3Atext_style_control%3Ajapanese.md) | 1,210.58 | — | 114 / 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` \| 1210.58168001483 \| rating \| reported \| Higher is better \| ### Configuration category japanese config text_style_control ### Reported statistics lower 1189.1400023701628 rank 230 upper 1232.0233576594972 variance 119.6799345449567 votes 788 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label Qwen2.5-72B-Instruct Observed 2026-10-22T00:45:04.817Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/8180/row` | | | | | | | [Arena text style control / creative writing](https://benchize.com/benchmarks/lmarena%3Atext_style_control%3Acreative_writing.md) | 1,254.08 | — | 140 / 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` \| 1254.0758048704097 \| rating \| reported \| Higher is better \| ### Configuration category creative_writing config text_style_control ### Reported statistics lower 1245.5863118925997 rank 295 upper 1262.5652978482199 variance 18.761489940236533 votes 5684 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label Qwen2.5-72B-Instruct Observed 2026-10-22T00:45:04.817Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/1516/row` | | | | | | | [OTIS Mock AIME 2024–2025](https://benchize.com/benchmarks/epoch-ai%3Aotis_mock_aime_2024_2025.md) | 8.06% | SE ±2.61 pp | 114 / 124 | [epoch ai · OTIS Mock AIME 2024-2025](https://epoch.ai/data/benchmark_data.zip#file=otis_mock_aime_2024_2025.csv) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `score` \| 0.08055555555555556 \| score_fraction \| Best score (across scorers) \| Higher is better \| \| `mean_score` \| 0.08055555555555556 \| score_fraction \| mean_score \| Higher is better \| ### Configuration benchmarkVersion OTIS Mock AIME 2024-2025 reasoningBudget Not reported Reasoning effort Not reported sourceModelVersion qwen2.5-72b-instruct ### Reported statistics Uncertainty Standard error: ±2.61 pp standardError 0.026098213018967212 ### Source [Original source](https://epoch.ai/data/benchmark_data.zip#file=otis_mock_aime_2024_2025.csv) Source epoch ai Original model label qwen2.5-72b-instruct Source version OTIS Mock AIME 2024-2025 Evaluated 2025-02-25T14:05:03.625Z Observed 2026-10-22T03:00:05.281Z Evidence SHA-256 `b7c9da8c0587c82f1e0d814ceb496c24308380b997a16203b6e5d39eb07f4f50` Source locator `/rows/292` | | | | | | | [Arena text style control / exclude ties](https://benchize.com/benchmarks/lmarena%3Atext_style_control%3Aexclude_ties.md) | 1,237.45 | — | 139 / 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` \| 1237.4504941100206 \| rating \| reported \| Higher is better \| ### Configuration category exclude_ties config text_style_control ### Reported statistics lower 1230.9788175801614 rank 285 upper 1243.9221706398798 variance 10.902784348880227 votes 24444 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label Qwen2.5-72B-Instruct Observed 2026-10-22T00:45:04.817Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/2338/row` | | | | | | | [Arena text / longer query](https://benchize.com/benchmarks/lmarena%3Atext%3Alonger_query.md) | 1,281.47 | — | 133 / 150 | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1281.4696736497958 \| rating \| reported \| Higher is better \| ### Configuration category longer_query config text ### Reported statistics lower 1273.4093230946728 rank 265 upper 1289.5300242049186 variance 16.912650663200864 votes 6008 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) Source Arena Original model label Qwen2.5-72B-Instruct Observed 2026-10-22T00:45:04.817Z Evidence SHA-256 `8e027ef69b8de06c4b2a8b217bfe816b1f1536269bb257fd295b4ef1ba8246ac` Source locator `/rows/8782/row` | | | | | | | [Arena text style control / expert](https://benchize.com/benchmarks/lmarena%3Atext_style_control%3Aexpert.md) | 1,294.89 | — | 134 / 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` \| 1294.890346546079 \| rating \| reported \| Higher is better \| ### Configuration category expert config text_style_control ### Reported statistics lower 1282.6853831161352 rank 273 upper 1307.0953099760227 variance 38.777230026208215 votes 2397 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label Qwen2.5-72B-Instruct Observed 2026-10-22T00:45:04.817Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/2743/row` | | | | | | | [Arena text style control / non english](https://benchize.com/benchmarks/lmarena%3Atext_style_control%3Anon_english.md) | 1,285.45 | — | 136 / 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` \| 1285.4472239437857 \| rating \| reported \| Higher is better \| ### Configuration category non_english config text_style_control ### Reported statistics lower 1279.9833801565342 rank 277 upper 1290.9110677310373 variance 7.771419745713417 votes 18845 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label Qwen2.5-72B-Instruct Observed 2026-10-22T00:45:04.817Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/10007/row` | | | | | | | [Arena text / german](https://benchize.com/benchmarks/lmarena%3Atext%3Agerman.md) | 1,233.56 | — | 120 / 129 | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1233.5649869195038 \| rating \| reported \| Higher is better \| ### Configuration category german config text ### Reported statistics lower 1214.3471510188856 rank 241 upper 1252.782822820122 variance 96.14191741780805 votes 926 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) Source Arena Original model label Qwen2.5-72B-Instruct Observed 2026-10-22T00:45:04.817Z Evidence SHA-256 `8e027ef69b8de06c4b2a8b217bfe816b1f1536269bb257fd295b4ef1ba8246ac` Source locator `/rows/3377/row` | | | | | | | [Arena text style control / industry business and management and financial operations](https://benchize.com/benchmarks/lmarena%3Atext_style_control%3Aindustry_business_and_management_and_financial_operations.md) | 1,299.36 | — | 137 / 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` \| 1299.3582061664995 \| rating \| reported \| Higher is better \| ### Configuration category industry_business_and_management_and_financial_operations config text_style_control ### Reported statistics lower 1289.996179682705 rank 275 upper 1308.7202326502938 variance 22.816212271001312 votes 4656 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label Qwen2.5-72B-Instruct Observed 2026-10-22T00:45:04.817Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/4557/row` | | | | | | | [Arena text / korean](https://benchize.com/benchmarks/lmarena%3Atext%3Akorean.md) | 1,187.92 | — | 118 / 124 | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1187.9173295910214 \| rating \| reported \| Higher is better \| ### Configuration category korean config text ### Reported statistics lower 1160.1509300133341 rank 226 upper 1215.6837291687086 variance 200.69795915929777 votes 527 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) Source Arena Original model label Qwen2.5-72B-Instruct Observed 2026-10-22T00:45:04.817Z Evidence SHA-256 `8e027ef69b8de06c4b2a8b217bfe816b1f1536269bb257fd295b4ef1ba8246ac` Source locator `/rows/8459/row` | | | | | | | [Arena text / multi turn](https://benchize.com/benchmarks/lmarena%3Atext%3Amulti_turn.md) | 1,271.8 | — | 134 / 151 | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1271.7961215048965 \| rating \| reported \| Higher is better \| ### Configuration category multi_turn config text ### Reported statistics lower 1263.9146698567533 rank 273 upper 1279.6775731530397 variance 16.170231930481314 votes 7250 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) Source Arena Original model label Qwen2.5-72B-Instruct Observed 2026-10-22T00:45:04.817Z Evidence SHA-256 `8e027ef69b8de06c4b2a8b217bfe816b1f1536269bb257fd295b4ef1ba8246ac` Source locator `/rows/9588/row` | | | | | | | [Arena text style control / english](https://benchize.com/benchmarks/lmarena%3Atext_style_control%3Aenglish.md) | 1,315.83 | — | 139 / 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` \| 1315.831102345005 \| rating \| reported \| Higher is better \| ### Configuration category english config text_style_control ### Reported statistics lower 1310.6555679577218 rank 291 upper 1321.0066367322881 variance 6.972912490862054 votes 20561 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label Qwen2.5-72B-Instruct Observed 2026-10-22T00:45:04.817Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/1927/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) | 1,244.56 | — | 142 / 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` \| 1244.5552087168264 \| rating \| reported \| Higher is better \| ### Configuration category industry_entertainment_and_sports_and_media config text_style_control ### Reported statistics lower 1236.4920512070553 rank 304 upper 1252.6183662265976 variance 16.92443211343066 votes 6207 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label Qwen2.5-72B-Instruct Observed 2026-10-22T00:45:04.817Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/4996/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) | 1,282.41 | — | 138 / 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` \| 1282.4069152479954 \| rating \| reported \| Higher is better \| ### Configuration category industry_writing_and_literature_and_language config text_style_control ### Reported statistics lower 1275.6076144888366 rank 283 upper 1289.2062160071544 variance 12.034618349792817 votes 10827 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label Qwen2.5-72B-Instruct Observed 2026-10-22T00:45:04.817Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/7400/row` | | | | | | | [EQ-Bench 3](https://benchize.com/benchmarks/eq-bench%3Aeqbench3.md) | 845.6elo | CI 822.5–868.6 | 45 / 50 | [eq bench · eqbench3](https://eqbench.com/eqbench3.js) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `elo_norm` \| 845.6 \| elo \| overall \| Higher is better \| \| `rubric_0_100` \| 33.5 \| percent \| overall \| Higher is better \| ### Configuration interactiveAdjustments none protocol eqbench3 sourceModelVersion qwen/qwen-2.5-72b-instruct ### Reported statistics Uncertainty Confidence interval: 822.5–868.6 confidenceIntervalHigh 868.6 confidenceIntervalLow 822.5 ### Source [Original source](https://eqbench.com/eqbench3.js) Source eq bench Original model label qwen/qwen-2.5-72b-instruct Source version eqbench3 Observed 2026-10-22T05:10:04.922Z Evidence SHA-256 `3672ff093e739f07ff664a2e6013bc38a6977a146e4092b4cef80ba1780542b2` Source locator `/leaderboardDataEQBench3/69` | | | | | | | [Arena text style control / coding](https://benchize.com/benchmarks/lmarena%3Atext_style_control%3Acoding.md) | 1,354.82 | — | 133 / 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` \| 1354.815933787153 \| rating \| reported \| Higher is better \| ### Configuration category coding config text_style_control ### Reported statistics lower 1347.1632411497274 rank 267 upper 1362.4686264245788 variance 15.245173080451808 votes 6688 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label Qwen2.5-72B-Instruct Observed 2026-10-22T00:45:04.817Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/1076/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) | 1,317.98 | — | 139 / 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` \| 1317.9795999437752 \| rating \| reported \| Higher is better \| ### Configuration category industry_life_and_physical_and_social_science config text_style_control ### Reported statistics lower 1310.060305192655 rank 282 upper 1325.8988946948953 variance 16.325888752801415 votes 6932 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label Qwen2.5-72B-Instruct Observed 2026-10-22T00:45:04.817Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/5779/row` | | | | | | | [Arena text / overall](https://benchize.com/benchmarks/lmarena%3Atext.md) | 1,269.04 | — | 141 / 151 | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1269.04278836006 \| rating \| reported \| Higher is better \| ### Configuration category overall config text ### Reported statistics lower 1264.9817245283432 rank 283 upper 1273.1038521917767 variance 4.293223021533936 votes 39406 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) Source Arena Original model label Qwen2.5-72B-Instruct Observed 2026-10-22T00:45:04.817Z Evidence SHA-256 `8e027ef69b8de06c4b2a8b217bfe816b1f1536269bb257fd295b4ef1ba8246ac` Source locator `/rows/282/row` | | | | | | | [Arena text / creative writing](https://benchize.com/benchmarks/lmarena%3Atext%3Acreative_writing.md) | 1,221.06 | — | 142 / 151 | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1221.05751497334 \| rating \| reported \| Higher is better \| ### Configuration category creative_writing config text ### Reported statistics lower 1212.6348302734968 rank 295 upper 1229.4801996731833 variance 18.467363797005248 votes 5684 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) Source Arena Original model label Qwen2.5-72B-Instruct Observed 2026-10-22T00:45:04.817Z Evidence SHA-256 `8e027ef69b8de06c4b2a8b217bfe816b1f1536269bb257fd295b4ef1ba8246ac` Source locator `/rows/1516/row` | | | | | | | [Arena text / expert](https://benchize.com/benchmarks/lmarena%3Atext%3Aexpert.md) | 1,245.22 | — | 131 / 148 | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1245.2152020065255 \| rating \| reported \| Higher is better \| ### Configuration category expert config text ### Reported statistics lower 1233.0842289788457 rank 261 upper 1257.3461750342058 variance 38.30849514917104 votes 2397 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) Source Arena Original model label Qwen2.5-72B-Instruct Observed 2026-10-22T00:45:04.817Z Evidence SHA-256 `8e027ef69b8de06c4b2a8b217bfe816b1f1536269bb257fd295b4ef1ba8246ac` Source locator `/rows/2731/row` | | | | | | | [Arena text / industry business and management and financial operations](https://benchize.com/benchmarks/lmarena%3Atext%3Aindustry_business_and_management_and_financial_operations.md) | 1,252.86 | — | 137 / 151 | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1252.8596305154624 \| rating \| reported \| Higher is better \| ### Configuration category industry_business_and_management_and_financial_operations config text ### Reported statistics lower 1243.5908260387912 rank 272 upper 1262.1284349921339 variance 22.364091465449654 votes 4656 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) Source Arena Original model label Qwen2.5-72B-Instruct Observed 2026-10-22T00:45:04.817Z Evidence SHA-256 `8e027ef69b8de06c4b2a8b217bfe816b1f1536269bb257fd295b4ef1ba8246ac` Source locator `/rows/4554/row` | | | | | | | [Arena text style control / multi turn](https://benchize.com/benchmarks/lmarena%3Atext_style_control%3Amulti_turn.md) | 1,298.74 | — | 132 / 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` \| 1298.7371123023936 \| rating \| reported \| Higher is better \| ### Configuration category multi_turn config text_style_control ### Reported statistics lower 1290.8159139362047 rank 271 upper 1306.658310668582 variance 16.33373842731267 votes 7250 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label Qwen2.5-72B-Instruct Observed 2026-10-22T00:45:04.817Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/9586/row` | | | | | | | [Arena text / industry medicine and healthcare](https://benchize.com/benchmarks/lmarena%3Atext%3Aindustry_medicine_and_healthcare.md) | 1,258.45 | — | 139 / 151 | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1258.4523697771438 \| rating \| reported \| Higher is better \| ### Configuration category industry_medicine_and_healthcare config text ### Reported statistics lower 1244.4710183304874 rank 271 upper 1272.4337212238 variance 50.88644637341153 votes 1956 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) Source Arena Original model label Qwen2.5-72B-Instruct Observed 2026-10-22T00:45:04.817Z Evidence SHA-256 `8e027ef69b8de06c4b2a8b217bfe816b1f1536269bb257fd295b4ef1ba8246ac` Source locator `/rows/6583/row` | | | | | | | [Arena text / industry writing and literature and language](https://benchize.com/benchmarks/lmarena%3Atext%3Aindustry_writing_and_literature_and_language.md) | 1,246.95 | — | 140 / 151 | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1246.951390380798 \| rating \| reported \| Higher is better \| ### Configuration category industry_writing_and_literature_and_language config text ### Reported statistics lower 1240.205041824522 rank 289 upper 1253.697738937074 variance 11.847899708721604 votes 10827 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) Source Arena Original model label Qwen2.5-72B-Instruct Observed 2026-10-22T00:45:04.817Z Evidence SHA-256 `8e027ef69b8de06c4b2a8b217bfe816b1f1536269bb257fd295b4ef1ba8246ac` Source locator `/rows/7406/row` | | | | | | | [Arena text / industry legal and government](https://benchize.com/benchmarks/lmarena%3Atext%3Aindustry_legal_and_government.md) | 1,287.82 | — | 133 / 151 | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1287.817596066817 \| rating \| reported \| Higher is better \| ### Configuration category industry_legal_and_government config text ### Reported statistics lower 1275.0155745605068 rank 261 upper 1300.6196175731272 variance 42.663936358015484 votes 2386 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) Source Arena Original model label Qwen2.5-72B-Instruct Observed 2026-10-22T00:45:04.817Z Evidence SHA-256 `8e027ef69b8de06c4b2a8b217bfe816b1f1536269bb257fd295b4ef1ba8246ac` Source locator `/rows/5368/row` | | | | | | | [GPQA Diamond](https://benchize.com/benchmarks/gpqa-diamond.md) | 49.15% | SE ±2.69 pp | 107 / 126 | [epoch ai · GPQA diamond](https://epoch.ai/data/benchmark_data.zip#file=gpqa_diamond.csv) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `score` \| 0.4914772727272727 \| score_fraction \| Best score (across scorers) \| Higher is better \| \| `mean_score` \| 0.4914772727272727 \| score_fraction \| mean_score \| Higher is better \| ### Configuration benchmarkVersion GPQA diamond reasoningBudget Not reported Reasoning effort Not reported sourceModelVersion qwen2.5-72b-instruct ### Reported statistics Uncertainty Standard error: ±2.69 pp standardError 0.026947767404178667 ### Source [Original source](https://epoch.ai/data/benchmark_data.zip#file=gpqa_diamond.csv) Source epoch ai Original model label qwen2.5-72b-instruct Source version GPQA diamond Evaluated 2025-01-27T00:00:00.000Z Observed 2026-10-22T03:00:05.281Z Evidence SHA-256 `9ef0b938bdd8406b029d595983ee8ad3a80bd9d64b82605b91b5ce39ba650c39` Source locator `/rows/306` | | | | | | | [Arena text / hard prompts](https://benchize.com/benchmarks/lmarena%3Atext%3Ahard_prompts.md) | 1,270.58 | — | 133 / 151 | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1270.5845167347181 \| rating \| reported \| Higher is better \| ### Configuration category hard_prompts config text ### Reported statistics lower 1264.245470086089 rank 267 upper 1276.9235633833473 variance 10.460482407627234 votes 10545 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) Source Arena Original model label Qwen2.5-72B-Instruct Observed 2026-10-22T00:45:04.817Z Evidence SHA-256 `8e027ef69b8de06c4b2a8b217bfe816b1f1536269bb257fd295b4ef1ba8246ac` Source locator `/rows/3717/row` | | | | | | | [Arena text / math](https://benchize.com/benchmarks/lmarena%3Atext%3Amath.md) | 1,282.59 | — | 131 / 149 | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1282.5886765110572 \| rating \| reported \| Higher is better \| ### Configuration category math config text ### Reported statistics lower 1274.3368659998555 rank 252 upper 1290.8404870222587 variance 17.725655770656708 votes 5415 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) Source Arena Original model label Qwen2.5-72B-Instruct Observed 2026-10-22T00:45:04.817Z Evidence SHA-256 `8e027ef69b8de06c4b2a8b217bfe816b1f1536269bb257fd295b4ef1ba8246ac` Source locator `/rows/9164/row` | | | | | | | [Arena text style control / longer query](https://benchize.com/benchmarks/lmarena%3Atext_style_control%3Alonger_query.md) | 1,316.96 | — | 134 / 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` \| 1316.9610946056316 \| rating \| reported \| Higher is better \| ### Configuration category longer_query config text_style_control ### Reported statistics lower 1308.8513927527342 rank 272 upper 1325.0707964585292 variance 17.120387647681532 votes 6008 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label Qwen2.5-72B-Instruct Observed 2026-10-22T00:45:04.817Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/8789/row` | | | | | | | [Arena text / industry life and physical and social science](https://benchize.com/benchmarks/lmarena%3Atext%3Aindustry_life_and_physical_and_social_science.md) | 1,274.86 | — | 138 / 151 | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1274.859153017481 \| rating \| reported \| Higher is better \| ### Configuration category industry_life_and_physical_and_social_science config text ### Reported statistics lower 1266.9894727686255 rank 276 upper 1282.7288332663366 variance 16.121965667208734 votes 6932 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) Source Arena Original model label Qwen2.5-72B-Instruct Observed 2026-10-22T00:45:04.817Z Evidence SHA-256 `8e027ef69b8de06c4b2a8b217bfe816b1f1536269bb257fd295b4ef1ba8246ac` Source locator `/rows/5773/row` | | | | | | | [Arena text / hard prompts english](https://benchize.com/benchmarks/lmarena%3Atext%3Ahard_prompts_english.md) | 1,279.44 | — | 135 / 151 | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1279.442674616178 \| rating \| reported \| Higher is better \| ### Configuration category hard_prompts_english config text ### Reported statistics lower 1271.6842559697784 rank 273 upper 1287.2010932625776 variance 15.669323218704672 votes 6208 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) Source Arena Original model label Qwen2.5-72B-Instruct Observed 2026-10-22T00:45:04.817Z Evidence SHA-256 `8e027ef69b8de06c4b2a8b217bfe816b1f1536269bb257fd295b4ef1ba8246ac` Source locator `/rows/4140/row` | | | | | | | [MAGI-Hard](https://benchize.com/benchmarks/eq-bench%3Amagi-hard.md) | 77.83% | — | 3 / 14 | [eq bench · magi-hard](https://eqbench.com/eqbench-v2.js) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `score` \| 77.83 \| percent \| overall \| Higher is better \| ### Configuration interactiveAdjustments none protocol magi-hard sourceModelVersion Qwen/Qwen2.5-72B-Instruct ### Source [Original source](https://eqbench.com/eqbench-v2.js) Source eq bench Original model label Qwen/Qwen2.5-72B-Instruct Source version magi-hard Observed 2026-10-22T05:10:05.138Z Evidence SHA-256 `088fe07c18b4347c82113934c58bb801cdb21adfe80852c7d0854e9818749dcd` Source locator `/leaderboardDataMagi/157` | | | | | | | [Arena text / chinese](https://benchize.com/benchmarks/lmarena%3Atext%3Achinese.md) | 1,272.52 | — | 131 / 146 | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1272.515208556042 \| rating \| reported \| Higher is better \| ### Configuration category chinese config text ### Reported statistics lower 1261.5033045626064 rank 259 upper 1283.5271125494774 variance 31.566661318194335 votes 3329 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) Source Arena Original model label Qwen2.5-72B-Instruct Observed 2026-10-22T00:45:04.817Z Evidence SHA-256 `8e027ef69b8de06c4b2a8b217bfe816b1f1536269bb257fd295b4ef1ba8246ac` Source locator `/rows/675/row` | | | | | | | [Arena text / french](https://benchize.com/benchmarks/lmarena%3Atext%3Afrench.md) | 1,280.45 | — | 121 / 132 | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1280.446405526386 \| rating \| reported \| Higher is better \| ### Configuration category french config text ### Reported statistics lower 1247.7322824641353 rank 227 upper 1313.1605285886365 variance 278.5956840059774 votes 340 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) Source Arena Original model label Qwen2.5-72B-Instruct Observed 2026-10-22T00:45:04.817Z Evidence SHA-256 `8e027ef69b8de06c4b2a8b217bfe816b1f1536269bb257fd295b4ef1ba8246ac` Source locator `/rows/3064/row` | | | | | | | [Arena text / industry software and it services](https://benchize.com/benchmarks/lmarena%3Atext%3Aindustry_software_and_it_services.md) | 1,292.21 | — | 134 / 151 | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1292.214283789055 \| rating \| reported \| Higher is better \| ### Configuration category industry_software_and_it_services config text ### Reported statistics lower 1285.6399408512252 rank 266 upper 1298.7886267268846 variance 11.251450837206015 votes 10448 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) Source Arena Original model label Qwen2.5-72B-Instruct Observed 2026-10-22T00:45:04.817Z Evidence SHA-256 `8e027ef69b8de06c4b2a8b217bfe816b1f1536269bb257fd295b4ef1ba8246ac` Source locator `/rows/6966/row` | | | | | | | [Arena text style control / industry mathematical](https://benchize.com/benchmarks/lmarena%3Atext_style_control%3Aindustry_mathematical.md) | 1,309.21 | — | 131 / 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` \| 1309.2102162192887 \| rating \| reported \| Higher is better \| ### Configuration category industry_mathematical config text_style_control ### Reported statistics lower 1300.329165094472 rank 255 upper 1318.0912673441055 variance 20.532061584707428 votes 4565 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label Qwen2.5-72B-Instruct Observed 2026-10-22T00:45:04.817Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/6167/row` | | | | | | | [Arena text style control / korean](https://benchize.com/benchmarks/lmarena%3Atext_style_control%3Akorean.md) | 1,229.42 | — | 119 / 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` \| 1229.4230934991479 \| rating \| reported \| Higher is better \| ### Configuration category korean config text_style_control ### Reported statistics lower 1201.447010815778 rank 231 upper 1257.3991761825177 variance 203.74062012340642 votes 527 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label Qwen2.5-72B-Instruct Observed 2026-10-22T00:45:04.817Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/8464/row` | | | | | | | [Arena text / industry mathematical](https://benchize.com/benchmarks/lmarena%3Atext%3Aindustry_mathematical.md) | 1,290.48 | — | 127 / 148 | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1290.4837294087083 \| rating \| reported \| Higher is better \| ### Configuration category industry_mathematical config text ### Reported statistics lower 1281.6673503671282 rank 248 upper 1299.3001084502885 variance 20.234120169682623 votes 4565 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) Source Arena Original model label Qwen2.5-72B-Instruct Observed 2026-10-22T00:45:04.817Z Evidence SHA-256 `8e027ef69b8de06c4b2a8b217bfe816b1f1536269bb257fd295b4ef1ba8246ac` Source locator `/rows/6160/row` | | | | | | | [Arena text style control / hard prompts](https://benchize.com/benchmarks/lmarena%3Atext_style_control%3Ahard_prompts.md) | 1,317.42 | — | 136 / 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` \| 1317.4193526254794 \| rating \| reported \| Higher is better \| ### Configuration category hard_prompts config text_style_control ### Reported statistics lower 1311.0358172214742 rank 276 upper 1323.8028880294848 variance 10.607825348711433 votes 10545 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label Qwen2.5-72B-Instruct Observed 2026-10-22T00:45:04.817Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/3726/row` | | | | | | | [Arena text style control / industry medicine and healthcare](https://benchize.com/benchmarks/lmarena%3Atext_style_control%3Aindustry_medicine_and_healthcare.md) | 1,313.38 | — | 139 / 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` \| 1313.382695375408 \| rating \| reported \| Higher is better \| ### Configuration category industry_medicine_and_healthcare config text_style_control ### Reported statistics lower 1299.3049571263132 rank 277 upper 1327.460433624503 variance 51.590482538145224 votes 1956 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label Qwen2.5-72B-Instruct Observed 2026-10-22T00:45:04.817Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/6589/row` | | | | | | | [BuzzBench](https://benchize.com/benchmarks/eq-bench%3Abuzzbench.md) | 45.89% | CI 45.08–46.7% | 9 / 15 | [eq bench · buzzbench](https://eqbench.com/buzzbench.js) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `score` \| 45.89 \| percent \| overall \| Higher is better \| ### Configuration interactiveAdjustments none protocol buzzbench sourceModelVersion Qwen/Qwen2.5-72B-Instruct ### Reported statistics Uncertainty Confidence interval: 45.08–46.7% confidenceIntervalHigh 46.7 confidenceIntervalLow 45.08 ### Source [Original source](https://eqbench.com/buzzbench.js) Source eq bench Original model label Qwen/Qwen2.5-72B-Instruct Source version buzzbench Observed 2026-10-22T05:10:06.154Z Evidence SHA-256 `4d0f19f1f87e08772b741a28b1ac39111587b832035dd1a783af3de67d51be1c` Source locator `/leaderboardDataBuzzbench/16` | | | | | | | [Arena text style control / french](https://benchize.com/benchmarks/lmarena%3Atext_style_control%3Afrench.md) | 1,321.44 | — | 122 / 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` \| 1321.435466797087 \| rating \| reported \| Higher is better \| ### Configuration category french config text_style_control ### Reported statistics lower 1288.2931673099006 rank 235 upper 1354.5777662842734 variance 285.9361681507966 votes 340 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label Qwen2.5-72B-Instruct Observed 2026-10-22T00:45:04.817Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/3072/row` | | | | | | | [Arena text / english](https://benchize.com/benchmarks/lmarena%3Atext%3Aenglish.md) | 1,282.63 | — | 141 / 151 | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1282.6296631787825 \| rating \| reported \| Higher is better \| ### Configuration category english config text ### Reported statistics lower 1277.4893103337592 rank 284 upper 1287.7700160238057 variance 6.878435668500428 votes 20561 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) Source Arena Original model label Qwen2.5-72B-Instruct Observed 2026-10-22T00:45:04.817Z Evidence SHA-256 `8e027ef69b8de06c4b2a8b217bfe816b1f1536269bb257fd295b4ef1ba8246ac` Source locator `/rows/1920/row` | | | | | | | [Arena text style control / industry software and it services](https://benchize.com/benchmarks/lmarena%3Atext_style_control%3Aindustry_software_and_it_services.md) | 1,342.69 | — | 134 / 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` \| 1342.689520990993 \| rating \| reported \| Higher is better \| ### Configuration category industry_software_and_it_services config text_style_control ### Reported statistics lower 1336.0661490186035 rank 272 upper 1349.3128929633826 variance 11.419894975396323 votes 10448 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label Qwen2.5-72B-Instruct Observed 2026-10-22T00:45:04.817Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/6972/row` | | | | | | | [Arena text style control / instruction following](https://benchize.com/benchmarks/lmarena%3Atext_style_control%3Ainstruction_following.md) | 1,291.95 | — | 134 / 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` \| 1291.9457657886505 \| rating \| reported \| Higher is better \| ### Configuration category instruction_following config text_style_control ### Reported statistics lower 1286.2640272970727 rank 275 upper 1297.6275042802283 variance 8.403617946591183 votes 16363 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label Qwen2.5-72B-Instruct Observed 2026-10-22T00:45:04.817Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/7808/row` | | | | | | | [Arena text / russian](https://benchize.com/benchmarks/lmarena%3Atext%3Arussian.md) | 1,263.83 | — | 134 / 150 | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1263.833437130743 \| rating \| reported \| Higher is better \| ### Configuration category russian config text ### Reported statistics lower 1255.365315507329 rank 263 upper 1272.3015587541572 variance 18.667148907762584 votes 5776 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) Source Arena Original model label Qwen2.5-72B-Instruct Observed 2026-10-22T00:45:04.817Z Evidence SHA-256 `8e027ef69b8de06c4b2a8b217bfe816b1f1536269bb257fd295b4ef1ba8246ac` Source locator `/rows/10646/row` | | | | | | | [Arena text style control / russian](https://benchize.com/benchmarks/lmarena%3Atext_style_control%3Arussian.md) | 1,297.33 | — | 134 / 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` \| 1297.3257651872414 \| rating \| reported \| Higher is better \| ### Configuration category russian config text_style_control ### Reported statistics lower 1288.825703319268 rank 266 upper 1305.8258270552144 variance 18.80823279170662 votes 5776 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label Qwen2.5-72B-Instruct Observed 2026-10-22T00:45:04.817Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/10649/row` | | | | | | | [Arena text / japanese](https://benchize.com/benchmarks/lmarena%3Atext%3Ajapanese.md) | 1,179.86 | — | 112 / 120 | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1179.860374600005 \| rating \| reported \| Higher is better \| ### Configuration category japanese config text ### Reported statistics lower 1158.523866410515 rank 220 upper 1201.1968827894948 variance 118.50877569420568 votes 788 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) Source Arena Original model label Qwen2.5-72B-Instruct Observed 2026-10-22T00:45:04.817Z Evidence SHA-256 `8e027ef69b8de06c4b2a8b217bfe816b1f1536269bb257fd295b4ef1ba8246ac` Source locator `/rows/8170/row` | | | | | | | [Arena text style control / industry legal and government](https://benchize.com/benchmarks/lmarena%3Atext_style_control%3Aindustry_legal_and_government.md) | 1,330.49 | — | 130 / 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` \| 1330.4926027010983 \| rating \| reported \| Higher is better \| ### Configuration category industry_legal_and_government config text_style_control ### Reported statistics lower 1317.645597389309 rank 257 upper 1343.339608012888 variance 42.964288616616436 votes 2386 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label Qwen2.5-72B-Instruct Observed 2026-10-22T00:45:04.817Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/5364/row` | | | | | | | [SVGBench Arena](https://benchize.com/benchmarks/svgbench%3Aarena.md) | 1,282 | — | 167 / 191 | [svgbench](https://svgbench.ai/api/leaderboard?shape=2) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1282 \| rating \| reported \| Higher is better \| ### Configuration Reasoning effort unknown sourceModelId model_qwen_qwen_2_5_72b_instruct ### Reported statistics coverageCount 27 draws 0 judged 15 losses 12 rank 268 ratingDeviation 52 wins 3 ### Source [Original source](https://svgbench.ai/api/leaderboard?shape=2) Source svgbench Original model label Qwen 2.5 72b Instruct Observed 2026-10-22T04:30:04.538Z Evidence SHA-256 `5c0a9c869593820d57d2c05f6d416e1b44a740b4835e66c66e9ad8b8edc59e2c` Source locator `/rows/252` | | | | | | | [Arena text style control / hard prompts english](https://benchize.com/benchmarks/lmarena%3Atext_style_control%3Ahard_prompts_english.md) | 1,325.96 | — | 136 / 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` \| 1325.9624740361353 \| rating \| reported \| Higher is better \| ### Configuration category hard_prompts_english config text_style_control ### Reported statistics lower 1318.1396525537552 rank 276 upper 1333.785295518515 variance 15.930545868542218 votes 6208 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label Qwen2.5-72B-Instruct Observed 2026-10-22T00:45:04.817Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/4143/row` | | | | | | | [EQ-Bench v2](https://benchize.com/benchmarks/eq-bench%3Aeqbench-v2.md) | 79.05% | — | 6 / 18 | [eq bench · eqbench-v2](https://eqbench.com/eqbench-v2.js) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `score` \| 79.05 \| percent \| overall \| Higher is better \| ### Configuration interactiveAdjustments none protocol eqbench-v2 sourceModelVersion Qwen/Qwen2.5-72B-Instruct ### Source [Original source](https://eqbench.com/eqbench-v2.js) Source eq bench Original model label Qwen/Qwen2.5-72B-Instruct Source version eqbench-v2 Observed 2026-10-22T05:10:05.138Z Evidence SHA-256 `088fe07c18b4347c82113934c58bb801cdb21adfe80852c7d0854e9818749dcd` Source locator `/leaderboardDataEqbench/167` | | | | | | | [Arena text / industry entertainment and sports and media](https://benchize.com/benchmarks/lmarena%3Atext%3Aindustry_entertainment_and_sports_and_media.md) | 1,210.95 | — | 143 / 151 | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1210.9464354298302 \| rating \| reported \| Higher is better \| ### Configuration category industry_entertainment_and_sports_and_media config text ### Reported statistics lower 1202.9278985001924 rank 299 upper 1218.9649723594682 variance 16.73763470939605 votes 6207 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) Source Arena Original model label Qwen2.5-72B-Instruct Observed 2026-10-22T00:45:04.817Z Evidence SHA-256 `8e027ef69b8de06c4b2a8b217bfe816b1f1536269bb257fd295b4ef1ba8246ac` Source locator `/rows/4991/row` | | | | | | | [Arena text / non english](https://benchize.com/benchmarks/lmarena%3Atext%3Anon_english.md) | 1,251.82 | — | 140 / 151 | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1251.8154421817358 \| rating \| reported \| Higher is better \| ### Configuration category non_english config text ### Reported statistics lower 1246.3774246145424 rank 278 upper 1257.2534597489291 variance 7.698126269582181 votes 18845 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) Source Arena Original model label Qwen2.5-72B-Instruct Observed 2026-10-22T00:45:04.817Z Evidence SHA-256 `8e027ef69b8de06c4b2a8b217bfe816b1f1536269bb257fd295b4ef1ba8246ac` Source locator `/rows/10008/row` | | | | | | | [Arena text / spanish](https://benchize.com/benchmarks/lmarena%3Atext%3Aspanish.md) | 1,255.41 | — | 126 / 134 | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1255.4070189783847 \| rating \| reported \| Higher is better \| ### Configuration category spanish config text ### Reported statistics lower 1224.4607488764104 rank 241 upper 1286.3532890803588 variance 249.29894551135524 votes 347 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) Source Arena Original model label Qwen2.5-72B-Instruct Observed 2026-10-22T00:45:04.817Z Evidence SHA-256 `8e027ef69b8de06c4b2a8b217bfe816b1f1536269bb257fd295b4ef1ba8246ac` Source locator `/rows/11005/row` | | | | | | --- Cite as: Qwen2.5 72B Instruct — Benchize, https://benchize.com/models/qwen-2-5-72b-instruct (retrieved 2026-10-22)