# gpt-oss-20b > Source: Benchize (https://benchize.com) — https://benchize.com/models/gpt-oss-20b. When citing or reusing this content, credit "Benchize" and link to https://benchize.com/models/gpt-oss-20b. OpenAI Canonical URL: https://benchize.com/models/gpt-oss-20b Last updated: Thu, 22 Oct 2026 07:32:33 GMT Reproduction and quotation must name Benchize, link to the canonical HTML URL, and retain individual source citations. OpenAI ## Benchmarks | Benchmark | Score | ± | Rank | Source | | | --- | --- | --- | --- | --- | --- | | [Arena text style control / multi turn](https://benchize.com/benchmarks/lmarena%3Atext_style_control%3Amulti_turn.md) | 1,289.32 | — | 158 / 173 | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1289.3184331131338 \| rating \| reported \| Higher is better \| ### Configuration category multi_turn config text_style_control ### Reported statistics lower 1274.8451401523675 rank 283 upper 1303.7917260738996 variance 54.53037996911505 votes 1777 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label gpt-oss-20b Observed 2026-10-22T06:45:03.380Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/9598/row` | | | | | | | [Arena text / industry medicine and healthcare](https://benchize.com/benchmarks/lmarena%3Atext%3Aindustry_medicine_and_healthcare.md) | 1,309.81 | — | 147 / 173 | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1309.8134548653384 \| rating \| reported \| Higher is better \| ### Configuration category industry_medicine_and_healthcare config text ### Reported statistics lower 1284.542390951136 rank 236 upper 1335.084518779541 variance 166.245871988891 votes 564 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) Source Arena Original model label gpt-oss-20b Observed 2026-10-22T06:45:03.380Z Evidence SHA-256 `8e027ef69b8de06c4b2a8b217bfe816b1f1536269bb257fd295b4ef1ba8246ac` Source locator `/rows/6548/row` | | | | | | | [Arena text style control / russian](https://benchize.com/benchmarks/lmarena%3Atext_style_control%3Arussian.md) | 1,309.83 | — | 149 / 172 | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1309.8292919479059 \| rating \| reported \| Higher is better \| ### Configuration category russian config text_style_control ### Reported statistics lower 1288.76364374765 rank 249 upper 1330.8949401481616 variance 115.51901368989732 votes 756 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label gpt-oss-20b Observed 2026-10-22T06:45:03.380Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/10632/row` | | | | | | | [EQ-Bench 3](https://benchize.com/benchmarks/eq-bench%3Aeqbench3.md) | 956elo | CI 922.2–989.9 | 41 / 50 | [eq bench · eqbench3](https://eqbench.com/eqbench3.js) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `elo_norm` \| 956.0 \| elo \| overall \| Higher is better \| \| `rubric_0_100` \| 40.7 \| percent \| overall \| Higher is better \| ### Configuration interactiveAdjustments none protocol eqbench3 sourceModelVersion openai/gpt-oss-20b ### Reported statistics Uncertainty Confidence interval: 922.2–989.9 confidenceIntervalHigh 989.9 confidenceIntervalLow 922.2 ### Source [Original source](https://eqbench.com/eqbench3.js) Source eq bench Original model label openai/gpt-oss-20b Source version eqbench3 Observed 2026-10-22T05:10:04.922Z Evidence SHA-256 `3672ff093e739f07ff664a2e6013bc38a6977a146e4092b4cef80ba1780542b2` Source locator `/leaderboardDataEQBench3/63` | | | | | | | [Arena text / industry software and it services](https://benchize.com/benchmarks/lmarena%3Atext%3Aindustry_software_and_it_services.md) | 1,311.14 | — | 148 / 173 | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1311.1406718606697 \| rating \| reported \| Higher is better \| ### Configuration category industry_software_and_it_services config text ### Reported statistics lower 1301.041821472172 rank 252 upper 1321.2395222491675 variance 26.54897108875791 votes 3591 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) Source Arena Original model label gpt-oss-20b Observed 2026-10-22T06:45:03.380Z Evidence SHA-256 `8e027ef69b8de06c4b2a8b217bfe816b1f1536269bb257fd295b4ef1ba8246ac` Source locator `/rows/6952/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) | 1,322.58 | — | 146 / 173 | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1322.5784184338443 \| rating \| reported \| Higher is better \| ### Configuration category industry_business_and_management_and_financial_operations config text_style_control ### Reported statistics lower 1308.63857748656 rank 243 upper 1336.5182593811285 variance 50.58473218267414 votes 1836 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label gpt-oss-20b Observed 2026-10-22T06:45:03.380Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/4525/row` | | | | | | | [MASK](https://benchize.com/benchmarks/scale%3Amask.md) | 86.46source score | CI 84.39–88.53 | 6 / 25 | [scale](https://labs.scale.com/leaderboard/mask) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `score` \| 86.46 \| source_score \| reported \| Higher is better \| ### Configuration Reasoning effort unknown Model configuration gpt-oss-20b sourceModelVersion gpt-oss-20b thinkingEnabled Not reported ### Reported statistics Uncertainty Confidence interval: 84.39–88.53 contaminationWarning Potential contamination warning: This model was evaluated after the public release of MASK, allowing model builder access to the prompts and solutions. rank 14 reportedConfidenceHalfWidth 2.07 ### Source [Original source](https://labs.scale.com/leaderboard/mask) Source scale Original model label gpt-oss-20b Observed 2026-10-22T03:30:12.706Z Evidence SHA-256 `fe1699303dff9a092aff10128cfc39d63ddc0680c0d241345fa747c450597b67` Source locator `/rows/13` | | | | | | | [Arena text / creative writing](https://benchize.com/benchmarks/lmarena%3Atext%3Acreative_writing.md) | 1,201.04 | — | 165 / 173 | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1201.0406457423835 \| rating \| reported \| Higher is better \| ### Configuration category creative_writing config text ### Reported statistics lower 1183.2664215774562 rank 306 upper 1218.8148699073108 variance 82.24038299283347 votes 1234 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) Source Arena Original model label gpt-oss-20b Observed 2026-10-22T06:45:03.380Z Evidence SHA-256 `8e027ef69b8de06c4b2a8b217bfe816b1f1536269bb257fd295b4ef1ba8246ac` Source locator `/rows/1527/row` | | | | | | | [Arena text / exclude ties](https://benchize.com/benchmarks/lmarena%3Atext%3Aexclude_ties.md) | 1,222.26 | — | 151 / 173 | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1222.2644486766424 \| rating \| reported \| Higher is better \| ### Configuration category exclude_ties config text ### Reported statistics lower 1213.3602173031327 rank 257 upper 1231.1686800501518 variance 20.639382082108533 votes 7621 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) Source Arena Original model label gpt-oss-20b Observed 2026-10-22T06:45:03.380Z Evidence SHA-256 `8e027ef69b8de06c4b2a8b217bfe816b1f1536269bb257fd295b4ef1ba8246ac` Source locator `/rows/2310/row` | | | | | | | [Arena text / spanish](https://benchize.com/benchmarks/lmarena%3Atext%3Aspanish.md) | 1,267.4 | — | 146 / 155 | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1267.3993963387143 \| rating \| reported \| Higher is better \| ### Configuration category spanish config text ### Reported statistics lower 1229.2822303187354 rank 234 upper 1305.516562358693 variance 378.22046602912377 votes 284 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) Source Arena Original model label gpt-oss-20b Observed 2026-10-22T06:45:03.380Z Evidence SHA-256 `8e027ef69b8de06c4b2a8b217bfe816b1f1536269bb257fd295b4ef1ba8246ac` Source locator `/rows/10998/row` | | | | | | | [Arena text style control / expert](https://benchize.com/benchmarks/lmarena%3Atext_style_control%3Aexpert.md) | 1,315.2 | — | 147 / 170 | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1315.1962600754755 \| rating \| reported \| Higher is better \| ### Configuration category expert config text_style_control ### Reported statistics lower 1287.6666919965485 rank 250 upper 1342.7258281544027 variance 197.28888268424714 votes 506 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label gpt-oss-20b Observed 2026-10-22T06:45:03.380Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/2720/row` | | | | | | | [Arena text / industry entertainment and sports and media](https://benchize.com/benchmarks/lmarena%3Atext%3Aindustry_entertainment_and_sports_and_media.md) | 1,216.48 | — | 163 / 173 | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1216.4802133066707 \| rating \| reported \| Higher is better \| ### Configuration category industry_entertainment_and_sports_and_media config text ### Reported statistics lower 1201.7301646936116 rank 294 upper 1231.23026191973 variance 56.63575850809076 votes 1729 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) Source Arena Original model label gpt-oss-20b Observed 2026-10-22T06:45:03.380Z Evidence SHA-256 `8e027ef69b8de06c4b2a8b217bfe816b1f1536269bb257fd295b4ef1ba8246ac` Source locator `/rows/4986/row` | | | | | | | [Arena text / korean](https://benchize.com/benchmarks/lmarena%3Atext%3Akorean.md) | 1,235.66 | — | 125 / 144 | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1235.657614812769 \| rating \| reported \| Higher is better \| ### Configuration category korean config text ### Reported statistics lower 1194.7939661255214 rank 203 upper 1276.5212635000169 variance 434.688450918518 votes 228 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) Source Arena Original model label gpt-oss-20b Observed 2026-10-22T06:45:03.380Z Evidence SHA-256 `8e027ef69b8de06c4b2a8b217bfe816b1f1536269bb257fd295b4ef1ba8246ac` Source locator `/rows/8436/row` | | | | | | | [Arena text / overall](https://benchize.com/benchmarks/lmarena%3Atext.md) | 1,287.56 | — | 153 / 173 | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1287.560241922985 \| rating \| reported \| Higher is better \| ### Configuration category overall config text ### Reported statistics lower 1281.1718742803828 rank 261 upper 1293.948609565587 variance 10.62389135012809 votes 10417 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) Source Arena Original model label gpt-oss-20b Observed 2026-10-22T06:45:03.380Z Evidence SHA-256 `8e027ef69b8de06c4b2a8b217bfe816b1f1536269bb257fd295b4ef1ba8246ac` Source locator `/rows/260/row` | | | | | | | [Fortress](https://benchize.com/benchmarks/scale%3Afortress.md) | 17.62source score | CI 14.83–20.41 | 22 / 31 | [scale](https://labs.scale.com/leaderboard/fortress) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `score` \| 17.62 \| source_score \| reported \| Higher is better \| ### Configuration Reasoning effort unknown Model configuration gpt-oss-20b sourceModelVersion Not reported thinkingEnabled Not reported ### Reported statistics Uncertainty Confidence interval: 14.83–20.41 contaminationWarning ORS score: 11.94 rank 25 reportedConfidenceHalfWidth 2.79 ### Source [Original source](https://labs.scale.com/leaderboard/fortress) Source scale Original model label gpt-oss-20b Observed 2026-10-22T03:30:12.378Z Evidence SHA-256 `2c005102a7346206e5d31d9249d525620bef39f6d514668ed48398e710616b0f` Source locator `/rows/24` | | | | | | | [Arena text style control / non english](https://benchize.com/benchmarks/lmarena%3Atext_style_control%3Anon_english.md) | 1,299.04 | — | 152 / 173 | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1299.0411682985095 \| rating \| reported \| Higher is better \| ### Configuration category non_english config text_style_control ### Reported statistics lower 1291.007201060518 rank 261 upper 1307.0751355365012 variance 16.802114143048296 votes 5894 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label gpt-oss-20b Observed 2026-10-22T06:45:03.380Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/9991/row` | | | | | | | [Arena text / english](https://benchize.com/benchmarks/lmarena%3Atext%3Aenglish.md) | 1,303.08 | — | 153 / 173 | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1303.0843700514529 \| rating \| reported \| Higher is better \| ### Configuration category english config text ### Reported statistics lower 1294.0220075158945 rank 265 upper 1312.1467325870112 variance 21.378965273159018 votes 4512 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) Source Arena Original model label gpt-oss-20b Observed 2026-10-22T06:45:03.380Z Evidence SHA-256 `8e027ef69b8de06c4b2a8b217bfe816b1f1536269bb257fd295b4ef1ba8246ac` Source locator `/rows/1901/row` | | | | | | | [Arena text style control / industry medicine and healthcare](https://benchize.com/benchmarks/lmarena%3Atext_style_control%3Aindustry_medicine_and_healthcare.md) | 1,350.15 | — | 143 / 173 | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1350.1526290541633 \| rating \| reported \| Higher is better \| ### Configuration category industry_medicine_and_healthcare config text_style_control ### Reported statistics lower 1324.4640367159118 rank 234 upper 1375.8412213924146 variance 171.78468054009497 votes 564 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label gpt-oss-20b Observed 2026-10-22T06:45:03.380Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/6546/row` | | | | | | | [Arena text style control / english](https://benchize.com/benchmarks/lmarena%3Atext_style_control%3Aenglish.md) | 1,331.12 | — | 152 / 173 | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1331.1248259060187 \| rating \| reported \| Higher is better \| ### Configuration category english config text_style_control ### Reported statistics lower 1322.0045697739804 rank 266 upper 1340.245082038057 variance 21.652990646650373 votes 4512 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label gpt-oss-20b Observed 2026-10-22T06:45:03.380Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/1902/row` | | | | | | | [Arena text style control / spanish](https://benchize.com/benchmarks/lmarena%3Atext_style_control%3Aspanish.md) | 1,302.95 | — | 146 / 155 | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1302.9498945855448 \| rating \| reported \| Higher is better \| ### Configuration category spanish config text_style_control ### Reported statistics lower 1264.6068859801885 rank 241 upper 1341.2929031909007 variance 382.7156238120924 votes 284 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label gpt-oss-20b Observed 2026-10-22T06:45:03.380Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/11005/row` | | | | | | | [MultiNRC](https://benchize.com/benchmarks/scale%3Amultinrc.md) | 10.43source score | CI 8.59–12.27 | 14 / 15 | [scale](https://labs.scale.com/leaderboard/multinrc) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `score` \| 10.43 \| source_score \| reported \| Higher is better \| ### Configuration Reasoning effort unknown Model configuration gpt-oss-20b sourceModelVersion Not reported thinkingEnabled Not reported ### Reported statistics Uncertainty Confidence interval: 8.59–12.27 contaminationWarning Potential contamination warning: This model was evaluated after the public release of MultiNRC, allowing model builder access to the prompts and solutions. rank 42 reportedConfidenceHalfWidth 1.84 ### Source [Original source](https://labs.scale.com/leaderboard/multinrc) Source scale Original model label gpt-oss-20b Observed 2026-10-22T03:30:11.806Z Evidence SHA-256 `6f8d6d2a3da92da83c015fe86a75cf2d33b76bb4fcd05d83781ad835c0b17f2e` Source locator `/rows/41` | | | | | | | [Arena text style control / overall](https://benchize.com/benchmarks/lmarena%3Atext_style_control%3Aoverall.md) | 1,317.52 | — | 155 / 173 | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1317.5213704505807 \| rating \| reported \| Higher is better \| ### Configuration category overall config text_style_control ### Reported statistics lower 1311.106560000791 rank 268 upper 1323.9361809003703 variance 10.712022444456656 votes 10417 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label gpt-oss-20b Observed 2026-10-22T06:45:03.380Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/267/row` | | | | | | | [Arena text style control / math](https://benchize.com/benchmarks/lmarena%3Atext_style_control%3Amath.md) | 1,334.97 | — | 141 / 170 | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1334.9719463229726 \| rating \| reported \| Higher is better \| ### Configuration category math config text_style_control ### Reported statistics lower 1312.8979350023583 rank 227 upper 1357.045957643587 variance 126.84295173430029 votes 678 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label gpt-oss-20b Observed 2026-10-22T06:45:03.380Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/9139/row` | | | | | | | [SVGBench Arena](https://benchize.com/benchmarks/svgbench%3Aarena.md) | 1,289 | — | 152 / 191 | [svgbench](https://svgbench.ai/api/leaderboard?shape=2) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1289 \| rating \| reported \| Higher is better \| ### Configuration Reasoning effort unknown sourceModelId model_openai_gpt_oss_20b ### Reported statistics coverageCount 27 draws 2 judged 123 losses 59 rank 237 ratingDeviation 28 wins 62 ### Source [Original source](https://svgbench.ai/api/leaderboard?shape=2) Source svgbench Original model label gpt-oss-20b Observed 2026-10-22T04:30:04.538Z Evidence SHA-256 `5c0a9c869593820d57d2c05f6d416e1b44a740b4835e66c66e9ad8b8edc59e2c` Source locator `/rows/223` | | | | | | | [Arena text / industry mathematical](https://benchize.com/benchmarks/lmarena%3Atext%3Aindustry_mathematical.md) | 1,305.25 | — | 145 / 169 | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1305.2504201317658 \| rating \| reported \| Higher is better \| ### Configuration category industry_mathematical config text ### Reported statistics lower 1281.0884191695454 rank 240 upper 1329.4124210939863 variance 151.9741113332711 votes 585 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) Source Arena Original model label gpt-oss-20b Observed 2026-10-22T06:45:03.380Z Evidence SHA-256 `8e027ef69b8de06c4b2a8b217bfe816b1f1536269bb257fd295b4ef1ba8246ac` Source locator `/rows/6152/row` | | | | | | | [Judgemark v2.1](https://benchize.com/benchmarks/eq-bench%3Ajudgemark-v2.md) | 42.8% | — | 37 / 39 | [eq bench · judgemark-v2](https://eqbench.com/judgemark-v2.js) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `judgemark_score` \| 42.8 \| percent \| overall \| Higher is better \| \| `stability` \| 0.331 \| score_fraction \| overall \| Higher is better \| \| `separability` \| 0.476 \| score_fraction \| overall \| Higher is better \| \| `human_corr` \| 0.334 \| correlation \| overall \| Higher is better \| ### Configuration interactiveAdjustments none protocol judgemark-v2 sourceModelVersion openai/gpt-oss-20b ### Source [Original source](https://eqbench.com/judgemark-v2.js) Source eq bench Original model label openai/gpt-oss-20b Source version judgemark-v2 Observed 2026-10-22T05:10:06.632Z Evidence SHA-256 `070cc3fbd6f0333dde2b52bec4329ea3fba7eccbf016bbbbef95e0f8b2197781` Source locator `/leaderboardDataV2/11` | | | | | | | [Arena text / non english](https://benchize.com/benchmarks/lmarena%3Atext%3Anon_english.md) | 1,268.59 | — | 153 / 173 | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1268.5912030099591 \| rating \| reported \| Higher is better \| ### Configuration category non_english config text ### Reported statistics lower 1260.5689999466679 rank 258 upper 1276.6134060732504 variance 16.752943345895773 votes 5894 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) Source Arena Original model label gpt-oss-20b Observed 2026-10-22T06:45:03.380Z Evidence SHA-256 `8e027ef69b8de06c4b2a8b217bfe816b1f1536269bb257fd295b4ef1ba8246ac` Source locator `/rows/9988/row` | | | | | | | [DesignArena Website generation](https://benchize.com/benchmarks/designarena%3Awebsite.md) | 853elo | — | 120 / 123 | [designarena · public](https://www.designarena.ai/api/leaderboard#board=website) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `elo` \| 853 \| elo \| website \| Higher is better \| ### Configuration arenaType models category website inputModality text sourceModelVersion gpt-oss-20b variationName public ### Reported statistics averageGenerationTimeMs 13086 battles 627 losses 452 standardError Not reported winRate 27.9 wins 175 ### Source [Original source](https://www.designarena.ai/api/leaderboard#board=website) Source designarena Original model label GPT OSS 20B Source version public Observed 2026-10-21T16:37:57.757Z Evidence SHA-256 `51873e97776a3c5ae706b24cc2c60384793dd18398df970e213a8e7c276d8ac0` Source locator `/data/188` | | | | | | | [Arena text style control / creative writing](https://benchize.com/benchmarks/lmarena%3Atext_style_control%3Acreative_writing.md) | 1,240.42 | — | 164 / 173 | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1240.420883353373 \| rating \| reported \| Higher is better \| ### Configuration category creative_writing config text_style_control ### Reported statistics lower 1222.0804316251815 rank 305 upper 1258.7613350815645 variance 87.56365362608251 votes 1234 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label gpt-oss-20b Observed 2026-10-22T06:45:03.380Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/1526/row` | | | | | | | [Arena text / coding](https://benchize.com/benchmarks/lmarena%3Atext%3Acoding.md) | 1,306.53 | — | 148 / 173 | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1306.5344955809405 \| rating \| reported \| Higher is better \| ### Configuration category coding config text ### Reported statistics lower 1293.4041428536982 rank 255 upper 1319.6648483081829 variance 44.88038809970792 votes 2112 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) Source Arena Original model label gpt-oss-20b Observed 2026-10-22T06:45:03.380Z Evidence SHA-256 `8e027ef69b8de06c4b2a8b217bfe816b1f1536269bb257fd295b4ef1ba8246ac` Source locator `/rows/1064/row` | | | | | | | [Arena text / industry business and management and financial operations](https://benchize.com/benchmarks/lmarena%3Atext%3Aindustry_business_and_management_and_financial_operations.md) | 1,283.74 | — | 150 / 173 | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1283.7446971482295 \| rating \| reported \| Higher is better \| ### Configuration category industry_business_and_management_and_financial_operations config text ### Reported statistics lower 1269.7164499969717 rank 249 upper 1297.7729442994873 variance 51.22838154001355 votes 1836 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) Source Arena Original model label gpt-oss-20b Observed 2026-10-22T06:45:03.380Z Evidence SHA-256 `8e027ef69b8de06c4b2a8b217bfe816b1f1536269bb257fd295b4ef1ba8246ac` Source locator `/rows/4531/row` | | | | | | | [Longform Creative Writing](https://benchize.com/benchmarks/eq-bench%3Alongform-writing.md) | 21.2% | — | 93 / 93 | [eq bench · longform-writing](https://eqbench.com/creative_writing_longform.js) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `overall_score_100` \| 21.2 \| percent \| overall \| Higher is better \| \| `chapter1_avg` \| 7.48 \| rubric_score \| overall \| Higher is better \| \| `chapter2_avg` \| 5.68 \| rubric_score \| overall \| Higher is better \| \| `chapter3_avg` \| 4.70 \| rubric_score \| overall \| Higher is better \| \| `chapter4_avg` \| 4.34 \| rubric_score \| overall \| Higher is better \| \| `chapter5_avg` \| 3.91 \| rubric_score \| overall \| Higher is better \| \| `chapter6_avg` \| 3.54 \| rubric_score \| overall \| Higher is better \| \| `chapter7_avg` \| 2.98 \| rubric_score \| overall \| Higher is better \| \| `chapter8_avg` \| 3.18 \| rubric_score \| overall \| Higher is better \| \| `final_judgement_avg` \| 3.14 \| rubric_score \| overall \| Higher is better \| ### Configuration interactiveAdjustments none protocol longform-writing sourceModelVersion openai/gpt-oss-20b ### Source [Original source](https://eqbench.com/creative_writing_longform.js) Source eq bench Original model label openai/gpt-oss-20b Source version longform-writing Observed 2026-10-22T05:10:05.903Z Evidence SHA-256 `3ba283ce357ac7620e16db640a961879c30fe3ddc50a27de9a8ed4290784825c` Source locator `/leaderboardDataLongformV3/87` | | | | | | | [Arena text / german](https://benchize.com/benchmarks/lmarena%3Atext%3Agerman.md) | 1,254.86 | — | 137 / 149 | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1254.858751599011 \| rating \| reported \| Higher is better \| ### Configuration category german config text ### Reported statistics lower 1214.5025557234276 rank 226 upper 1295.2149474745943 variance 423.9593918786724 votes 217 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) Source Arena Original model label gpt-oss-20b Observed 2026-10-22T06:45:03.380Z Evidence SHA-256 `8e027ef69b8de06c4b2a8b217bfe816b1f1536269bb257fd295b4ef1ba8246ac` Source locator `/rows/3362/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) | 1,275.58 | — | 161 / 173 | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1275.5766970903705 \| rating \| reported \| Higher is better \| ### Configuration category industry_writing_and_literature_and_language config text_style_control ### Reported statistics lower 1262.3955880924732 rank 290 upper 1288.7578060882677 variance 45.22803510960271 votes 2171 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label gpt-oss-20b Observed 2026-10-22T06:45:03.380Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/7407/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) | 1,327.64 | — | 154 / 173 | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1327.6361230514888 \| rating \| reported \| Higher is better \| ### Configuration category industry_life_and_physical_and_social_science config text_style_control ### Reported statistics lower 1312.4945242600254 rank 270 upper 1342.7777218429521 variance 59.682538499845016 votes 1668 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label gpt-oss-20b Observed 2026-10-22T06:45:03.380Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/5767/row` | | | | | | | [Arena text / industry writing and literature and language](https://benchize.com/benchmarks/lmarena%3Atext%3Aindustry_writing_and_literature_and_language.md) | 1,238.28 | — | 164 / 173 | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1238.2753884626914 \| rating \| reported \| Higher is better \| ### Configuration category industry_writing_and_literature_and_language config text ### Reported statistics lower 1225.272335610816 rank 295 upper 1251.2784413145664 variance 44.014368332629275 votes 2171 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) Source Arena Original model label gpt-oss-20b Observed 2026-10-22T06:45:03.380Z Evidence SHA-256 `8e027ef69b8de06c4b2a8b217bfe816b1f1536269bb257fd295b4ef1ba8246ac` Source locator `/rows/7412/row` | | | | | | | [Arena text style control / korean](https://benchize.com/benchmarks/lmarena%3Atext_style_control%3Akorean.md) | 1,277.46 | — | 122 / 144 | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1277.4642120577596 \| rating \| reported \| Higher is better \| ### Configuration category korean config text_style_control ### Reported statistics lower 1235.2585899931892 rank 197 upper 1319.66983412233 variance 463.7078300205468 votes 228 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label gpt-oss-20b Observed 2026-10-22T06:45:03.380Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/8430/row` | | | | | | | [Arena text style control / german](https://benchize.com/benchmarks/lmarena%3Atext_style_control%3Agerman.md) | 1,274 | — | 139 / 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` \| 1274.0007914664152 \| rating \| reported \| Higher is better \| ### Configuration category german config text_style_control ### Reported statistics lower 1233.343671483005 rank 240 upper 1314.6579114498254 variance 430.30564233582896 votes 217 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label gpt-oss-20b Observed 2026-10-22T06:45:03.380Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/3376/row` | | | | | | | [Arena text / hard prompts](https://benchize.com/benchmarks/lmarena%3Atext%3Ahard_prompts.md) | 1,273.84 | — | 153 / 173 | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1273.8430716903963 \| rating \| reported \| Higher is better \| ### Configuration category hard_prompts config text ### Reported statistics lower 1264.888184783027 rank 263 upper 1282.7979585977655 variance 20.87488198279886 votes 4719 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) Source Arena Original model label gpt-oss-20b Observed 2026-10-22T06:45:03.380Z Evidence SHA-256 `8e027ef69b8de06c4b2a8b217bfe816b1f1536269bb257fd295b4ef1ba8246ac` Source locator `/rows/3713/row` | | | | | | | [Arena text / instruction following](https://benchize.com/benchmarks/lmarena%3Atext%3Ainstruction_following.md) | 1,236.17 | — | 163 / 173 | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1236.174449969801 \| rating \| reported \| Higher is better \| ### Configuration category instruction_following config text ### Reported statistics lower 1223.952915660341 rank 290 upper 1248.395984279261 variance 38.882598473441334 votes 2541 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) Source Arena Original model label gpt-oss-20b Observed 2026-10-22T06:45:03.380Z Evidence SHA-256 `8e027ef69b8de06c4b2a8b217bfe816b1f1536269bb257fd295b4ef1ba8246ac` Source locator `/rows/7823/row` | | | | | | | [Arena text style control / instruction following](https://benchize.com/benchmarks/lmarena%3Atext_style_control%3Ainstruction_following.md) | 1,281.38 | — | 162 / 173 | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1281.3797932482785 \| rating \| reported \| Higher is better \| ### Configuration category instruction_following config text_style_control ### Reported statistics lower 1269.2043716874857 rank 288 upper 1293.5552148090712 variance 38.58973819644677 votes 2541 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label gpt-oss-20b Observed 2026-10-22T06:45:03.380Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/7821/row` | | | | | | | [Arena text style control / industry software and it services](https://benchize.com/benchmarks/lmarena%3Atext_style_control%3Aindustry_software_and_it_services.md) | 1,357.89 | — | 146 / 173 | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1357.8936208119674 \| rating \| reported \| Higher is better \| ### Configuration category industry_software_and_it_services config text_style_control ### Reported statistics lower 1347.8618352097235 rank 246 upper 1367.9254064142112 variance 26.197527311044652 votes 3591 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label gpt-oss-20b Observed 2026-10-22T06:45:03.380Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/6946/row` | | | | | | | [Arena text style control / industry mathematical](https://benchize.com/benchmarks/lmarena%3Atext_style_control%3Aindustry_mathematical.md) | 1,329.29 | — | 143 / 169 | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1329.2855708356924 \| rating \| reported \| Higher is better \| ### Configuration category industry_mathematical config text_style_control ### Reported statistics lower 1305.3023613411283 rank 233 upper 1353.2687803302567 variance 149.7333082321636 votes 585 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label gpt-oss-20b Observed 2026-10-22T06:45:03.380Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/6145/row` | | | | | | | [Arena text style control / exclude ties](https://benchize.com/benchmarks/lmarena%3Atext_style_control%3Aexclude_ties.md) | 1,262.1 | — | 152 / 173 | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1262.098656467334 \| rating \| reported \| Higher is better \| ### Configuration category exclude_ties config text_style_control ### Reported statistics lower 1253.0011626576065 rank 264 upper 1271.1961502770616 variance 21.545042516706033 votes 7621 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label gpt-oss-20b Observed 2026-10-22T06:45:03.380Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/2317/row` | | | | | | | [Arena text style control / japanese](https://benchize.com/benchmarks/lmarena%3Atext_style_control%3Ajapanese.md) | 1,255.46 | — | 121 / 138 | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1255.4579150145696 \| rating \| reported \| Higher is better \| ### Configuration category japanese config text_style_control ### Reported statistics lower 1216.8586720295066 rank 194 upper 1294.0571579996326 variance 387.8478537876717 votes 246 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label gpt-oss-20b Observed 2026-10-22T06:45:03.380Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/8144/row` | | | | | | | [Arena text style control / hard prompts english](https://benchize.com/benchmarks/lmarena%3Atext_style_control%3Ahard_prompts_english.md) | 1,337.11 | — | 152 / 173 | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1337.1097920335978 \| rating \| reported \| Higher is better \| ### Configuration category hard_prompts_english config text_style_control ### Reported statistics lower 1323.7837130068863 rank 263 upper 1350.4358710603092 variance 46.22837065687174 votes 2081 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label gpt-oss-20b Observed 2026-10-22T06:45:03.380Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/4130/row` | | | | | | | [Arena text / japanese](https://benchize.com/benchmarks/lmarena%3Atext%3Ajapanese.md) | 1,244.44 | — | 119 / 138 | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1244.4364120504868 \| rating \| reported \| Higher is better \| ### Configuration category japanese config text ### Reported statistics lower 1205.8929393147025 rank 188 upper 1282.9798847862708 variance 386.7278968425064 votes 246 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) Source Arena Original model label gpt-oss-20b Observed 2026-10-22T06:45:03.380Z Evidence SHA-256 `8e027ef69b8de06c4b2a8b217bfe816b1f1536269bb257fd295b4ef1ba8246ac` Source locator `/rows/8138/row` | | | | | | | [Humanity's Last Exam (Text Only)](https://benchize.com/benchmarks/scale%3Ahumanitys_last_exam_text_only.md) | 9.73source score | CI 8.48–10.98 | 14 / 25 | [scale](https://labs.scale.com/leaderboard/humanitys_last_exam_text_only) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `score` \| 9.73 \| source_score \| reported \| Higher is better \| ### Configuration Reasoning effort unknown Model configuration gpt-oss-20b sourceModelVersion Not reported thinkingEnabled Not reported ### Reported statistics Uncertainty Confidence interval: 8.48–10.98 contaminationWarning Potential contamination warning: This model was evaluated after the public release of HLE, allowing model builder access to the prompts and solutions. rank 39 reportedConfidenceHalfWidth 1.25 ### Source [Original source](https://labs.scale.com/leaderboard/humanitys_last_exam_text_only) Source scale Original model label gpt-oss-20b Observed 2026-10-22T03:30:09.372Z Evidence SHA-256 `16bd91dbd41a73afd31ff09fba3b9b08e9e3e2cfe682c50cc3b2bf8397610af6` Source locator `/rows/38` | | | | | | | [Arena text style control / polish](https://benchize.com/benchmarks/lmarena%3Atext_style_control%3Apolish.md) | 1,275.26 | — | 134 / 137 | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1275.2610294892925 \| rating \| reported \| Higher is better \| ### Configuration category polish config text_style_control ### Reported statistics lower 1253.036007863804 rank 224 upper 1297.4860511147813 variance 128.58437622512 votes 809 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label gpt-oss-20b Observed 2026-10-22T06:45:03.380Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/10371/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) | 1,256.14 | — | 161 / 173 | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1256.1356885834928 \| rating \| reported \| Higher is better \| ### Configuration category industry_entertainment_and_sports_and_media config text_style_control ### Reported statistics lower 1241.084997572621 rank 291 upper 1271.1863795943646 variance 58.96804065279753 votes 1729 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label gpt-oss-20b Observed 2026-10-22T06:45:03.380Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/4983/row` | | | | | | | [Arena text / longer query](https://benchize.com/benchmarks/lmarena%3Atext%3Alonger_query.md) | 1,250.41 | — | 164 / 172 | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1250.412762452922 \| rating \| reported \| Higher is better \| ### Configuration category longer_query config text ### Reported statistics lower 1237.1409598090434 rank 290 upper 1263.6845650968003 variance 45.852566339948744 votes 2104 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) Source Arena Original model label gpt-oss-20b Observed 2026-10-22T06:45:03.380Z Evidence SHA-256 `8e027ef69b8de06c4b2a8b217bfe816b1f1536269bb257fd295b4ef1ba8246ac` Source locator `/rows/8807/row` | | | | | | | [Arena text / chinese](https://benchize.com/benchmarks/lmarena%3Atext%3Achinese.md) | 1,314.89 | — | 143 / 168 | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1314.8895635695733 \| rating \| reported \| Higher is better \| ### Configuration category chinese config text ### Reported statistics lower 1292.0786414064594 rank 240 upper 1337.7004857326872 variance 135.45327288907833 votes 664 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) Source Arena Original model label gpt-oss-20b Observed 2026-10-22T06:45:03.380Z Evidence SHA-256 `8e027ef69b8de06c4b2a8b217bfe816b1f1536269bb257fd295b4ef1ba8246ac` Source locator `/rows/656/row` | | | | | | | [Arena text / hard prompts english](https://benchize.com/benchmarks/lmarena%3Atext%3Ahard_prompts_english.md) | 1,292.08 | — | 152 / 173 | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1292.0795230022063 \| rating \| reported \| Higher is better \| ### Configuration category hard_prompts_english config text ### Reported statistics lower 1278.7682993381436 rank 260 upper 1305.390746666269 variance 46.12536114670189 votes 2081 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) Source Arena Original model label gpt-oss-20b Observed 2026-10-22T06:45:03.380Z Evidence SHA-256 `8e027ef69b8de06c4b2a8b217bfe816b1f1536269bb257fd295b4ef1ba8246ac` Source locator `/rows/4127/row` | | | | | | | [Arena text / expert](https://benchize.com/benchmarks/lmarena%3Atext%3Aexpert.md) | 1,257.97 | — | 147 / 170 | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1257.9698257503899 \| rating \| reported \| Higher is better \| ### Configuration category expert config text ### Reported statistics lower 1231.071827881576 rank 249 upper 1284.8678236192038 variance 188.34050373081593 votes 506 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) Source Arena Original model label gpt-oss-20b Observed 2026-10-22T06:45:03.380Z Evidence SHA-256 `8e027ef69b8de06c4b2a8b217bfe816b1f1536269bb257fd295b4ef1ba8246ac` Source locator `/rows/2719/row` | | | | | | | [Arena text / russian](https://benchize.com/benchmarks/lmarena%3Atext%3Arussian.md) | 1,278.17 | — | 151 / 172 | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1278.1744750303014 \| rating \| reported \| Higher is better \| ### Configuration category russian config text ### Reported statistics lower 1257.0937612347673 rank 252 upper 1299.2551888258356 variance 115.68430507057397 votes 756 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) Source Arena Original model label gpt-oss-20b Observed 2026-10-22T06:45:03.380Z Evidence SHA-256 `8e027ef69b8de06c4b2a8b217bfe816b1f1536269bb257fd295b4ef1ba8246ac` Source locator `/rows/10635/row` | | | | | | | [Arena text / polish](https://benchize.com/benchmarks/lmarena%3Atext%3Apolish.md) | 1,252.43 | — | 133 / 137 | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1252.4341955001032 \| rating \| reported \| Higher is better \| ### Configuration category polish config text ### Reported statistics lower 1230.4559175251002 rank 216 upper 1274.4124734751063 variance 125.74512061519974 votes 809 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) Source Arena Original model label gpt-oss-20b Observed 2026-10-22T06:45:03.380Z Evidence SHA-256 `8e027ef69b8de06c4b2a8b217bfe816b1f1536269bb257fd295b4ef1ba8246ac` Source locator `/rows/10363/row` | | | | | | | [Arena text style control / hard prompts](https://benchize.com/benchmarks/lmarena%3Atext_style_control%3Ahard_prompts.md) | 1,322.88 | — | 152 / 173 | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1322.878006699345 \| rating \| reported \| Higher is better \| ### Configuration category hard_prompts config text_style_control ### Reported statistics lower 1313.953871046243 rank 267 upper 1331.802142352447 variance 20.731758655316003 votes 4719 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label gpt-oss-20b Observed 2026-10-22T06:45:03.380Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/3717/row` | | | | | | | [Arena text / multi turn](https://benchize.com/benchmarks/lmarena%3Atext%3Amulti_turn.md) | 1,268.22 | — | 159 / 173 | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1268.2212951777597 \| rating \| reported \| Higher is better \| ### Configuration category multi_turn config text ### Reported statistics lower 1253.736845038413 rank 277 upper 1282.7057453171064 variance 54.61448518178068 votes 1777 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) Source Arena Original model label gpt-oss-20b Observed 2026-10-22T06:45:03.380Z Evidence SHA-256 `8e027ef69b8de06c4b2a8b217bfe816b1f1536269bb257fd295b4ef1ba8246ac` Source locator `/rows/9592/row` | | | | | | | [Arena text style control / chinese](https://benchize.com/benchmarks/lmarena%3Atext_style_control%3Achinese.md) | 1,352.12 | — | 142 / 168 | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1352.124533848067 \| rating \| reported \| Higher is better \| ### Configuration category chinese config text_style_control ### Reported statistics lower 1329.093445175936 rank 238 upper 1375.1556225201975 variance 138.08062774644065 votes 664 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label gpt-oss-20b Observed 2026-10-22T06:45:03.380Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/654/row` | | | | | | | [Arena text style control / coding](https://benchize.com/benchmarks/lmarena%3Atext_style_control%3Acoding.md) | 1,368.38 | — | 145 / 173 | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1368.3788382145758 \| rating \| reported \| Higher is better \| ### Configuration category coding config text_style_control ### Reported statistics lower 1355.3298953801614 rank 250 upper 1381.4277810489905 variance 44.32558489981455 votes 2112 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label gpt-oss-20b Observed 2026-10-22T06:45:03.380Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/1059/row` | | | | | | | [Arena text style control / industry legal and government](https://benchize.com/benchmarks/lmarena%3Atext_style_control%3Aindustry_legal_and_government.md) | 1,321.42 | — | 160 / 173 | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1321.4178347715545 \| rating \| reported \| Higher is better \| ### Configuration category industry_legal_and_government config text_style_control ### Reported statistics lower 1297.8097296992842 rank 280 upper 1345.0259398438247 variance 145.08619019965087 votes 678 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label gpt-oss-20b Observed 2026-10-22T06:45:03.380Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/5387/row` | | | | | | | [Creative Writing v3](https://benchize.com/benchmarks/eq-bench%3Acreative-writing-v3.md) | 665.6elo | — | 87 / 90 | [eq bench · creative-writing-v3](https://eqbench.com/creative_writing.js) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `elo_score` \| 665.6 \| elo \| overall \| Higher is better \| \| `creative_writing_score` \| 7.87 \| rubric_score \| overall \| Higher is better \| ### Configuration interactiveAdjustments none protocol creative-writing-v3 sourceModelVersion openai/gpt-oss-20b ### Source [Original source](https://eqbench.com/creative_writing.js) Source eq bench Original model label openai/gpt-oss-20b Source version creative-writing-v3 Observed 2026-10-22T05:10:05.433Z Evidence SHA-256 `722ddb132e8d3a5e5c39b8d445f8475f3f7e24893a007260c6f3e3cce5c1ee18` Source locator `/leaderboardDataCreativeWritingV3/136` | | | | | | | [Arena text style control / longer query](https://benchize.com/benchmarks/lmarena%3Atext_style_control%3Alonger_query.md) | 1,302.87 | — | 162 / 172 | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1302.8734270722875 \| rating \| reported \| Higher is better \| ### Configuration category longer_query config text_style_control ### Reported statistics lower 1289.5449045548803 rank 285 upper 1316.201949589695 variance 46.24532522385242 votes 2104 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label gpt-oss-20b Observed 2026-10-22T06:45:03.380Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/8802/row` | | | | | | | [Arena text / industry legal and government](https://benchize.com/benchmarks/lmarena%3Atext%3Aindustry_legal_and_government.md) | 1,279.94 | — | 161 / 173 | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1279.940600110788 \| rating \| reported \| Higher is better \| ### Configuration category industry_legal_and_government config text ### Reported statistics lower 1256.560791349616 rank 271 upper 1303.32040887196 variance 142.29371788767526 votes 678 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) Source Arena Original model label gpt-oss-20b Observed 2026-10-22T06:45:03.380Z Evidence SHA-256 `8e027ef69b8de06c4b2a8b217bfe816b1f1536269bb257fd295b4ef1ba8246ac` Source locator `/rows/5378/row` | | | | | | | [Arena text / math](https://benchize.com/benchmarks/lmarena%3Atext%3Amath.md) | 1,316.9 | — | 140 / 170 | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1316.9037813084988 \| rating \| reported \| Higher is better \| ### Configuration category math config text ### Reported statistics lower 1294.5514456351998 rank 227 upper 1339.256116981798 variance 130.06176386958074 votes 678 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) Source Arena Original model label gpt-oss-20b Observed 2026-10-22T06:45:03.380Z Evidence SHA-256 `8e027ef69b8de06c4b2a8b217bfe816b1f1536269bb257fd295b4ef1ba8246ac` Source locator `/rows/9139/row` | | | | | | | [Arena text / industry life and physical and social science](https://benchize.com/benchmarks/lmarena%3Atext%3Aindustry_life_and_physical_and_social_science.md) | 1,296.28 | — | 152 / 173 | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1296.2821691062227 \| rating \| reported \| Higher is better \| ### Configuration category industry_life_and_physical_and_social_science config text ### Reported statistics lower 1281.3733551613216 rank 258 upper 1311.1909830511238 variance 57.86154261143795 votes 1668 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) Source Arena Original model label gpt-oss-20b Observed 2026-10-22T06:45:03.380Z Evidence SHA-256 `8e027ef69b8de06c4b2a8b217bfe816b1f1536269bb257fd295b4ef1ba8246ac` Source locator `/rows/5755/row` | | | | | | --- Cite as: gpt-oss-20b — Benchize, https://benchize.com/models/gpt-oss-20b (retrieved 2026-10-22)