# Gemma 3 27B > Source: Benchize (https://benchize.com) — https://benchize.com/models/gemma-3-27b-it. When citing or reusing this content, credit "Benchize" and link to https://benchize.com/models/gemma-3-27b-it. Google Canonical URL: https://benchize.com/models/gemma-3-27b-it Last updated: Wed, 21 Oct 2026 18:05:10 GMT Reproduction and quotation must name Benchize, link to the canonical HTML URL, and retain individual source citations. Google ## Benchmarks | Benchmark | Score | ± | Rank | Cost | Latency | Source | | | --- | --- | --- | --- | --- | --- | --- | --- | | [Arena text / spanish](https://benchize.com/benchmarks/lmarena%3Atext%3Aspanish.md) | 1,348.9 | — | 108 / 134 | — | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1348.8975378823377 \| rating \| reported \| Higher is better \| ### Configuration category spanish config text ### Reported statistics lower 1328.891611612226 rank 195 upper 1368.9034641524495 variance 104.1888263305218 votes 893 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) Source Arena Original model label Gemma 3 27B IT Observed 2026-10-21T16:40:19.533Z Evidence SHA-256 `8e027ef69b8de06c4b2a8b217bfe816b1f1536269bb257fd295b4ef1ba8246ac` Source locator `/rows/10959/row` | | | | | | | | | [Arena text style control / french](https://benchize.com/benchmarks/lmarena%3Atext_style_control%3Afrench.md) | 1,387.51 | — | 101 / 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` \| 1387.513005962174 \| rating \| reported \| Higher is better \| ### Configuration category french config text_style_control ### Reported statistics lower 1363.7552354396942 rank 183 upper 1411.2707764846539 variance 146.93159201868616 votes 657 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label Gemma 3 27B IT Observed 2026-10-21T16:40:19.533Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/3020/row` | | | | | | | | | [Arena text / overall](https://benchize.com/benchmarks/lmarena%3Atext.md) | 1,357.82 | — | 109 / 151 | — | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1357.8167134471694 \| rating \| reported \| Higher is better \| ### Configuration category overall config text ### Reported statistics lower 1354.1580514335926 rank 200 upper 1361.4753754607461 variance 3.4845636395942914 votes 46664 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) Source Arena Original model label Gemma 3 27B IT Observed 2026-10-21T16:40:19.533Z Evidence SHA-256 `8e027ef69b8de06c4b2a8b217bfe816b1f1536269bb257fd295b4ef1ba8246ac` Source locator `/rows/199/row` | | | | | | | | | [Arena text / non english](https://benchize.com/benchmarks/lmarena%3Atext%3Anon_english.md) | 1,334.42 | — | 110 / 151 | — | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1334.4200141783745 \| rating \| reported \| Higher is better \| ### Configuration category non_english config text ### Reported statistics lower 1329.7958253271095 rank 203 upper 1339.0442030296397 variance 5.566406808000367 votes 23611 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) Source Arena Original model label Gemma 3 27B IT Observed 2026-10-21T16:40:19.533Z Evidence SHA-256 `8e027ef69b8de06c4b2a8b217bfe816b1f1536269bb257fd295b4ef1ba8246ac` Source locator `/rows/9933/row` | | | | | | | | | [Arena vision / homework (config: vision)](https://benchize.com/benchmarks/benchmark%3Avision%3Ahomework--config-vision.md) | 1,159.78 | — | 70 / 73 | — | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/vision/latest) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1159.7779975930737 \| rating \| reported \| Higher is better \| ### Configuration category homework config vision ### Reported statistics lower 1140.9745837925227 rank 110 upper 1178.5814113936246 variance 92.0401303406043 votes 1034 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/vision/latest) Source Arena Original model label Gemma 3 27B IT Observed 2026-10-21T16:40:19.533Z Evidence SHA-256 `06e61305486dce3fec5dc776ac2fd8321104e84c346cf9e08fa6f8e8a66ce0d7` Source locator `/rows/917/row` | | | | | | | | | [Longform Creative Writing](https://benchize.com/benchmarks/eq-bench%3Alongform-writing.md) | 41.9% | — | 76 / 93 | — | — | [eq bench · longform-writing](https://eqbench.com/creative_writing_longform.js) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `overall_score_100` \| 41.9 \| percent \| overall \| Higher is better \| \| `chapter1_avg` \| 10.31 \| rubric_score \| overall \| Higher is better \| \| `chapter2_avg` \| 9.78 \| rubric_score \| overall \| Higher is better \| \| `chapter3_avg` \| 9.02 \| rubric_score \| overall \| Higher is better \| \| `chapter4_avg` \| 8.63 \| rubric_score \| overall \| Higher is better \| \| `chapter5_avg` \| 8.32 \| rubric_score \| overall \| Higher is better \| \| `chapter6_avg` \| 7.99 \| rubric_score \| overall \| Higher is better \| \| `chapter7_avg` \| 7.24 \| rubric_score \| overall \| Higher is better \| \| `chapter8_avg` \| 5.98 \| rubric_score \| overall \| Higher is better \| \| `final_judgement_avg` \| 7.89 \| rubric_score \| overall \| Higher is better \| ### Configuration interactiveAdjustments none protocol longform-writing sourceModelVersion google/gemma-3-27b-it ### Source [Original source](https://eqbench.com/creative_writing_longform.js) Source eq bench Original model label google/gemma-3-27b-it Source version longform-writing Observed 2026-10-21T16:35:02.575Z Evidence SHA-256 `3ba283ce357ac7620e16db640a961879c30fe3ddc50a27de9a8ed4290784825c` Source locator `/leaderboardDataLongformV3/58` | | | | | | | | | [Arena vision / entity recognition (config: vision)](https://benchize.com/benchmarks/benchmark%3Avision%3Aentity_recognition--config-vision.md) | 1,196.02 | — | 28 / 34 | — | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/vision/latest) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1196.0216482696978 \| rating \| reported \| Higher is better \| ### Configuration category entity_recognition config vision ### Reported statistics lower 1161.6771113992443 rank 40 upper 1230.3661851401516 variance 307.0571019769028 votes 313 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/vision/latest) Source Arena Original model label Gemma 3 27B IT Observed 2026-10-21T16:40:19.533Z Evidence SHA-256 `06e61305486dce3fec5dc776ac2fd8321104e84c346cf9e08fa6f8e8a66ce0d7` Source locator `/rows/796/row` | | | | | | | | | [Arena text style control / industry medicine and healthcare](https://benchize.com/benchmarks/lmarena%3Atext_style_control%3Aindustry_medicine_and_healthcare.md) | 1,406.39 | — | 98 / 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` \| 1406.3940464327384 \| rating \| reported \| Higher is better \| ### Configuration category industry_medicine_and_healthcare config text_style_control ### Reported statistics lower 1393.7192545169291 rank 181 upper 1419.0688383485476 variance 41.82014115148952 votes 2342 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label Gemma 3 27B IT Observed 2026-10-21T16:40:19.533Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/6493/row` | | | | | | | | | [Arena text / industry writing and literature and language](https://benchize.com/benchmarks/lmarena%3Atext%3Aindustry_writing_and_literature_and_language.md) | 1,347.36 | — | 99 / 151 | — | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1347.364083300817 \| rating \| reported \| Higher is better \| ### Configuration category industry_writing_and_literature_and_language config text ### Reported statistics lower 1341.2424062799857 rank 182 upper 1353.4857603216483 variance 9.755390151651186 votes 10587 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) Source Arena Original model label Gemma 3 27B IT Observed 2026-10-21T16:40:19.533Z Evidence SHA-256 `8e027ef69b8de06c4b2a8b217bfe816b1f1536269bb257fd295b4ef1ba8246ac` Source locator `/rows/7299/row` | | | | | | | | | [Creative Writing v3](https://benchize.com/benchmarks/eq-bench%3Acreative-writing-v3.md) | 1,265.7elo | — | 68 / 90 | — | — | [eq bench · creative-writing-v3](https://eqbench.com/creative_writing.js) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `elo_score` \| 1265.7 \| elo \| overall \| Higher is better \| \| `creative_writing_score` \| 15.33 \| rubric_score \| overall \| Higher is better \| ### Configuration interactiveAdjustments none protocol creative-writing-v3 sourceModelVersion google/gemma-3-27b-it ### Source [Original source](https://eqbench.com/creative_writing.js) Source eq bench Original model label google/gemma-3-27b-it Source version creative-writing-v3 Observed 2026-10-21T16:35:01.421Z Evidence SHA-256 `722ddb132e8d3a5e5c39b8d445f8475f3f7e24893a007260c6f3e3cce5c1ee18` Source locator `/leaderboardDataCreativeWritingV3/97` | | | | | | | | | [EQ-Bench 3](https://benchize.com/benchmarks/eq-bench%3Aeqbench3.md) | 1,093.9elo | CI 1,069.2–1,118.7 | 34 / 50 | — | — | [eq bench · eqbench3](https://eqbench.com/eqbench3.js) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `elo_norm` \| 1093.9 \| elo \| overall \| Higher is better \| \| `rubric_0_100` \| 55.6 \| percent \| overall \| Higher is better \| ### Configuration interactiveAdjustments none protocol eqbench3 sourceModelVersion google/gemma-3-27b-it ### Reported statistics Uncertainty Confidence interval: 1,069.2–1,118.7 confidenceIntervalHigh 1118.7 confidenceIntervalLow 1069.2 ### Source [Original source](https://eqbench.com/eqbench3.js) Source eq bench Original model label google/gemma-3-27b-it Source version eqbench3 Observed 2026-10-21T16:35:00.608Z Evidence SHA-256 `3672ff093e739f07ff664a2e6013bc38a6977a146e4092b4cef80ba1780542b2` Source locator `/leaderboardDataEQBench3/51` | | | | | | | | | [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) | 1,391.38 | — | 104 / 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` \| 1391.3825129268662 \| rating \| reported \| Higher is better \| ### Configuration category industry_life_and_physical_and_social_science config text_style_control ### Reported statistics lower 1384.2327869242222 rank 192 upper 1398.53223892951 variance 13.307075332293872 votes 7868 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label Gemma 3 27B IT Observed 2026-10-21T16:40:19.533Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/5689/row` | | | | | | | | | [Arena vision / creative writing vision (config: vision)](https://benchize.com/benchmarks/benchmark%3Avision%3Acreative_writing_vision--config-vision.md) | 1,176.85 | — | 65 / 70 | — | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/vision/latest) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1176.8533610635618 \| rating \| reported \| Higher is better \| ### Configuration category creative_writing_vision config vision ### Reported statistics lower 1151.5870419882176 rank 95 upper 1202.1196801389062 variance 166.18344993784356 votes 627 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/vision/latest) Source Arena Original model label Gemma 3 27B IT Observed 2026-10-21T16:40:19.533Z Evidence SHA-256 `06e61305486dce3fec5dc776ac2fd8321104e84c346cf9e08fa6f8e8a66ce0d7` Source locator `/rows/457/row` | | | | | | | | | [Arena text style control / german](https://benchize.com/benchmarks/lmarena%3Atext_style_control%3Agerman.md) | 1,370.66 | — | 87 / 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` \| 1370.6629245157692 \| rating \| reported \| Higher is better \| ### Configuration category german config text_style_control ### Reported statistics lower 1353.2330500053852 rank 162 upper 1388.092799026153 variance 79.08467580366646 votes 1207 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label Gemma 3 27B IT Observed 2026-10-21T16:40:19.533Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/3298/row` | | | | | | | | | [GPQA Diamond](https://benchize.com/benchmarks/gpqa-diamond.md) | 47.73% | SE ±2.7 pp | 111 / 125 | — | — | [epoch ai · GPQA diamond](https://epoch.ai/data/benchmark_data.zip#file=gpqa_diamond.csv) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `score` \| 0.4772727272727273 \| score_fraction \| Best score (across scorers) \| Higher is better \| \| `mean_score` \| 0.4772727272727273 \| score_fraction \| mean_score \| Higher is better \| ### Configuration benchmarkVersion GPQA diamond reasoningBudget Not reported Reasoning effort Not reported sourceModelVersion gemma-3-27b-it ### Reported statistics Uncertainty Standard error: ±2.7 pp standardError 0.026982120891168943 ### Source [Original source](https://epoch.ai/data/benchmark_data.zip#file=gpqa_diamond.csv) Source epoch ai Original model label gemma-3-27b-it Source version GPQA diamond Evaluated 2026-08-27T14:17:43.000Z Observed 2026-10-21T16:30:24.199Z Evidence SHA-256 `4b2dd8376cdd249a2c3065603575208fa726c15eabbb1622689a9abc146ba29a` Source locator `/rows/53` | | | | | | | | | [Arena text style control / spanish](https://benchize.com/benchmarks/lmarena%3Atext_style_control%3Aspanish.md) | 1,357.4 | — | 108 / 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` \| 1357.4003666516992 \| rating \| reported \| Higher is better \| ### Configuration category spanish config text_style_control ### Reported statistics lower 1337.1397195071145 rank 199 upper 1377.661013796284 variance 106.858837196436 votes 893 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label Gemma 3 27B IT Observed 2026-10-21T16:40:19.533Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/10963/row` | | | | | | | | | [Arena text / french](https://benchize.com/benchmarks/lmarena%3Atext%3Afrench.md) | 1,368.43 | — | 99 / 132 | — | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1368.4317164236984 \| rating \| reported \| Higher is better \| ### Configuration category french config text ### Reported statistics lower 1344.775962009458 rank 175 upper 1392.0874708379388 variance 145.67244971943754 votes 657 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) Source Arena Original model label Gemma 3 27B IT Observed 2026-10-21T16:40:19.533Z Evidence SHA-256 `8e027ef69b8de06c4b2a8b217bfe816b1f1536269bb257fd295b4ef1ba8246ac` Source locator `/rows/3012/row` | | | | | | | | | [Berkeley Function Calling Leaderboard](https://benchize.com/benchmarks/bfcl%3Aoverall.md) | 29.47% | — | 19 / 26 | $11.82 | 10.88s | [Berkeley Function Calling Leaderboard](https://api.github.com/repos/HuanzhiMao/BFCL-Result/contents/2025-12-16/score/data_overall.csv?ref=cadd76a8dc62984e7bf15ecaf358f070bae745cc) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 29.47 \| percent \| reported \| Higher is better \| \| `cost_total` \| 11.82 \| USD \| evaluation_total \| Lower is better \| \| `latency_mean` \| 10.88 \| seconds \| per_call_mean \| Lower is better \| \| `latency_sd` \| 19.67 \| seconds \| per_call_sd \| Lower is better \| \| `non_live_ast_acc` \| 87.17 \| percent \| reported_task_score \| Higher is better \| \| `non_live_simple_ast` \| 77.67 \| percent \| reported_task_score \| Higher is better \| \| `non_live_multiple_ast` \| 92.5 \| percent \| reported_task_score \| Higher is better \| \| `non_live_parallel_ast` \| 89 \| percent \| reported_task_score \| Higher is better \| \| `non_live_parallel_multiple_ast` \| 89.5 \| percent \| reported_task_score \| Higher is better \| \| `live_acc` \| 74.54 \| percent \| reported_task_score \| Higher is better \| \| `live_simple_ast` \| 84.5 \| percent \| reported_task_score \| Higher is better \| \| `live_multiple_ast` \| 72.46 \| percent \| reported_task_score \| Higher is better \| \| `live_parallel_ast` \| 93.75 \| percent \| reported_task_score \| Higher is better \| \| `live_parallel_multiple_ast` \| 45.83 \| percent \| reported_task_score \| Higher is better \| \| `multi_turn_acc` \| 10.75 \| percent \| reported_task_score \| Higher is better \| \| `multi_turn_base` \| 16.5 \| percent \| reported_task_score \| Higher is better \| \| `multi_turn_miss_func` \| 4.5 \| percent \| reported_task_score \| Higher is better \| \| `multi_turn_miss_param` \| 8 \| percent \| reported_task_score \| Higher is better \| \| `multi_turn_long_context` \| 14 \| percent \| reported_task_score \| Higher is better \| \| `web_search_acc` \| 0 \| percent \| reported_task_score \| Higher is better \| \| `web_search_base` \| 0 \| percent \| reported_task_score \| Higher is better \| \| `web_search_no_snippet` \| 0 \| percent \| reported_task_score \| Higher is better \| \| `memory_acc` \| 13.55 \| percent \| reported_task_score \| Higher is better \| \| `memory_kv` \| 1.94 \| percent \| reported_task_score \| Higher is better \| \| `memory_vector` \| 3.23 \| percent \| reported_task_score \| Higher is better \| \| `memory_recursive_summarization` \| 35.48 \| percent \| reported_task_score \| Higher is better \| \| `relevance_detection` \| 81.25 \| percent \| reported_task_score \| Higher is better \| \| `irrelevance_detection` \| 73.67 \| percent \| reported_task_score \| Higher is better \| \| `latency_p95` \| 55.5 \| seconds \| per_call_p95 \| Lower is better \| ### Configuration mode Prompt sourceRelease 2025-12-16 ### Reported statistics rank 69 ### Source [Original source](https://api.github.com/repos/HuanzhiMao/BFCL-Result/contents/2025-12-16/score/data_overall.csv?ref=cadd76a8dc62984e7bf15ecaf358f070bae745cc) Source Berkeley Function Calling Leaderboard Original model label Gemma-3-27b-it Observed 2026-10-21T16:39:30.957Z Evidence SHA-256 `ede5081a24bc5ac7f9b3b09a52af6bcfcd35aa0f1709239fed979db77a8159a6` Source locator `/rows/69` | | | | | | | | | [Arena text style control / exclude ties](https://benchize.com/benchmarks/lmarena%3Atext_style_control%3Aexclude_ties.md) | 1,331.23 | — | 107 / 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` \| 1331.2257778621247 \| rating \| reported \| Higher is better \| ### Configuration category exclude_ties config text_style_control ### Reported statistics lower 1326.0104507947167 rank 201 upper 1336.4411049295325 variance 7.080548741928932 votes 32661 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label Gemma 3 27B IT Observed 2026-10-21T16:40:19.533Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/2254/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) | 1,354.61 | — | 99 / 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` \| 1354.6138406359873 \| rating \| reported \| Higher is better \| ### Configuration category industry_writing_and_literature_and_language config text_style_control ### Reported statistics lower 1348.4260741903413 rank 190 upper 1360.8016070816336 variance 9.967164916516348 votes 10587 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label Gemma 3 27B IT Observed 2026-10-21T16:40:19.533Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/7307/row` | | | | | | | | | [Arena vision / captioning (config: vision)](https://benchize.com/benchmarks/benchmark%3Avision%3Acaptioning--config-vision.md) | 1,151.18 | — | 21 / 22 | — | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/vision/latest) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1151.1786351856742 \| rating \| reported \| Higher is better \| ### Configuration category captioning config vision ### Reported statistics lower 1112.5530093767077 rank 30 upper 1189.8042609946406 variance 388.37822784853233 votes 258 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/vision/latest) Source Arena Original model label Gemma 3 27B IT Observed 2026-10-21T16:40:19.533Z Evidence SHA-256 `06e61305486dce3fec5dc776ac2fd8321104e84c346cf9e08fa6f8e8a66ce0d7` Source locator `/rows/196/row` | | | | | | | | | [Creative Writing v2](https://benchize.com/benchmarks/eq-bench%3Acreative-writing-v2.md) | 85.25% | CI 85.25–85.25% | 2 / 18 | — | — | [eq bench · creative-writing-v2](https://eqbench.com/creative_writing_v2.js) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `score` \| 85.25 \| percent \| overall \| Higher is better \| ### Configuration interactiveAdjustments none protocol creative-writing-v2 sourceModelVersion google/gemma-3-27b-it ### Reported statistics Uncertainty Confidence interval: 85.25–85.25% confidenceIntervalHigh 85.25 confidenceIntervalLow 85.25 ### Source [Original source](https://eqbench.com/creative_writing_v2.js) Source eq bench Original model label google/gemma-3-27b-it Source version creative-writing-v2 Observed 2026-10-21T16:35:01.751Z Evidence SHA-256 `264c33d486559c25267ca29861754404dadb674022dcdf6530388cd9951af31a` Source locator `/leaderboardDataCreativeWriting/82` | | | | | | | | | [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) | 1,377.69 | — | 105 / 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` \| 1377.6908772976426 \| rating \| reported \| Higher is better \| ### Configuration category industry_business_and_management_and_financial_operations config text_style_control ### Reported statistics lower 1370.0225296473902 rank 189 upper 1385.359224947895 variance 15.307610579697815 votes 6495 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label Gemma 3 27B IT Observed 2026-10-21T16:40:19.533Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/4471/row` | | | | | | | | | [Arena text / russian](https://benchize.com/benchmarks/lmarena%3Atext%3Arussian.md) | 1,349.08 | — | 106 / 150 | — | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1349.0847100263181 \| rating \| reported \| Higher is better \| ### Configuration category russian config text ### Reported statistics lower 1339.4091900817489 rank 194 upper 1358.7602299708876 variance 24.36982682033338 votes 3433 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) Source Arena Original model label Gemma 3 27B IT Observed 2026-10-21T16:40:19.533Z Evidence SHA-256 `8e027ef69b8de06c4b2a8b217bfe816b1f1536269bb257fd295b4ef1ba8246ac` Source locator `/rows/10577/row` | | | | | | | | | [Arena vision / chinese (config: vision)](https://benchize.com/benchmarks/benchmark%3Avision%3Achinese--config-vision.md) | 1,163.67 | — | 63 / 74 | — | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/vision/latest) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1163.668923848267 \| rating \| reported \| Higher is better \| ### Configuration category chinese config vision ### Reported statistics lower 1142.8086836726573 rank 96 upper 1184.5291640238768 variance 113.27717945066885 votes 1020 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/vision/latest) Source Arena Original model label Gemma 3 27B IT Observed 2026-10-21T16:40:19.533Z Evidence SHA-256 `06e61305486dce3fec5dc776ac2fd8321104e84c346cf9e08fa6f8e8a66ce0d7` Source locator `/rows/296/row` | | | | | | | | | [Arena text / hard prompts](https://benchize.com/benchmarks/lmarena%3Atext%3Ahard_prompts.md) | 1,340.31 | — | 114 / 151 | — | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1340.3077443848174 \| rating \| reported \| Higher is better \| ### Configuration category hard_prompts config text ### Reported statistics lower 1335.1781689485924 rank 218 upper 1345.4373198210424 variance 6.849622860506511 votes 17704 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) Source Arena Original model label Gemma 3 27B IT Observed 2026-10-21T16:40:19.533Z Evidence SHA-256 `8e027ef69b8de06c4b2a8b217bfe816b1f1536269bb257fd295b4ef1ba8246ac` Source locator `/rows/3668/row` | | | | | | | | | [Arena text style control / english](https://benchize.com/benchmarks/lmarena%3Atext_style_control%3Aenglish.md) | 1,376.72 | — | 110 / 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` \| 1376.716750590971 \| rating \| reported \| Higher is better \| ### Configuration category english config text_style_control ### Reported statistics lower 1372.0002176281353 rank 209 upper 1381.4332835538069 variance 5.790946676215288 votes 23043 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label Gemma 3 27B IT Observed 2026-10-21T16:40:19.533Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/1845/row` | | | | | | | | | [Arena vision style control / english](https://benchize.com/benchmarks/lmarena%3Avision_style_control%3Aenglish.md) | 1,174.07 | — | 70 / 82 | — | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/vision_style_control/latest) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1174.0716950807775 \| rating \| reported \| Higher is better \| ### Configuration category english config vision_style_control ### Reported statistics lower 1163.5841172325977 rank 108 upper 1184.5592729289576 variance 28.632166646982473 votes 7938 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/vision_style_control/latest) Source Arena Original model label Gemma 3 27B IT Observed 2026-10-21T16:40:19.533Z Evidence SHA-256 `38568936995f36625aae49e9ea05557d55c1b1df9b2954f5c50cee523f26fe92` Source locator `/rows/697/row` | | | | | | | | | [Arena vision style control / creative writing](https://benchize.com/benchmarks/lmarena%3Avision_style_control%3Acreative_writing.md) | 1,174.6 | — | 10 / 13 | — | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/vision_style_control/latest) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1174.6045963457343 \| rating \| reported \| Higher is better \| ### Configuration category creative_writing config vision_style_control ### Reported statistics lower 1152.6282918089 rank 25 upper 1196.5809008825686 variance 125.72254022195004 votes 732 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/vision_style_control/latest) Source Arena Original model label gemma-3-27b-it Observed 2026-10-21T16:40:19.533Z Evidence SHA-256 `38568936995f36625aae49e9ea05557d55c1b1df9b2954f5c50cee523f26fe92` Source locator `/rows/353/row` | | | | | | | | | [Arena vision style control / homework](https://benchize.com/benchmarks/lmarena%3Avision_style_control%3Ahomework.md) | 1,167.33 | — | 70 / 73 | — | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/vision_style_control/latest) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1167.3311163492217 \| rating \| reported \| Higher is better \| ### Configuration category homework config vision_style_control ### Reported statistics lower 1148.371375127383 rank 109 upper 1186.2908575710603 variance 93.57689460644418 votes 1034 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/vision_style_control/latest) Source Arena Original model label Gemma 3 27B IT Observed 2026-10-21T16:40:19.533Z Evidence SHA-256 `38568936995f36625aae49e9ea05557d55c1b1df9b2954f5c50cee523f26fe92` Source locator `/rows/916/row` | | | | | | | | | [Arena text style control / industry software and it services](https://benchize.com/benchmarks/lmarena%3Atext_style_control%3Aindustry_software_and_it_services.md) | 1,376.48 | — | 117 / 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` \| 1376.4792602744553 \| rating \| reported \| Higher is better \| ### Configuration category industry_software_and_it_services config text_style_control ### Reported statistics lower 1370.879976587118 rank 231 upper 1382.0785439617925 variance 8.161476999932075 votes 14082 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label Gemma 3 27B IT Observed 2026-10-21T16:40:19.533Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/6931/row` | | | | | | | | | [Arena text style control / math](https://benchize.com/benchmarks/lmarena%3Atext_style_control%3Amath.md) | 1,323.16 | — | 122 / 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` \| 1323.1585292390328 \| rating \| reported \| Higher is better \| ### Configuration category math config text_style_control ### Reported statistics lower 1313.6371199158914 rank 230 upper 1332.679938562174 variance 23.59968952691263 votes 3587 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label Gemma 3 27B IT Observed 2026-10-21T16:40:19.533Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/9142/row` | | | | | | | | | [Arena text / industry mathematical](https://benchize.com/benchmarks/lmarena%3Atext%3Aindustry_mathematical.md) | 1,327.3 | — | 120 / 148 | — | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1327.2969151761342 \| rating \| reported \| Higher is better \| ### Configuration category industry_mathematical config text ### Reported statistics lower 1317.2387678077052 rank 227 upper 1337.3550625445632 variance 26.33539319490927 votes 3210 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) Source Arena Original model label Gemma 3 27B IT Observed 2026-10-21T16:40:19.533Z Evidence SHA-256 `8e027ef69b8de06c4b2a8b217bfe816b1f1536269bb257fd295b4ef1ba8246ac` Source locator `/rows/6139/row` | | | | | | | | | [Arena text / creative writing](https://benchize.com/benchmarks/lmarena%3Atext%3Acreative_writing.md) | 1,345.47 | — | 96 / 151 | — | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1345.4672515150396 \| rating \| reported \| Higher is better \| ### Configuration category creative_writing config text ### Reported statistics lower 1337.8296310670914 rank 173 upper 1353.104871962988 variance 15.185180638322437 votes 6304 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) Source Arena Original model label Gemma 3 27B IT Observed 2026-10-21T16:40:19.533Z Evidence SHA-256 `8e027ef69b8de06c4b2a8b217bfe816b1f1536269bb257fd295b4ef1ba8246ac` Source locator `/rows/1394/row` | | | | | | | | | [Arena text / industry legal and government](https://benchize.com/benchmarks/lmarena%3Atext%3Aindustry_legal_and_government.md) | 1,375.15 | — | 103 / 151 | — | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1375.1543108412243 \| rating \| reported \| Higher is better \| ### Configuration category industry_legal_and_government config text ### Reported statistics lower 1363.581562360102 rank 181 upper 1386.7270593223466 variance 34.863970605603946 votes 2661 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) Source Arena Original model label Gemma 3 27B IT Observed 2026-10-21T16:40:19.533Z Evidence SHA-256 `8e027ef69b8de06c4b2a8b217bfe816b1f1536269bb257fd295b4ef1ba8246ac` Source locator `/rows/5288/row` | | | | | | | | | [MATH Level 5](https://benchize.com/benchmarks/epoch-ai%3Amath_level_5.md) | 74.04% | SE ±1.12 pp | 7 / 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` \| 0.740370090634441 \| score_fraction \| Best score (across scorers) \| Higher is better \| \| `mean_score` \| 0.740370090634441 \| score_fraction \| mean_score \| Higher is better \| ### Configuration benchmarkVersion MATH level 5 reasoningBudget Not reported Reasoning effort Not reported sourceModelVersion gemma-3-27b-it ### Reported statistics Uncertainty Standard error: ±1.12 pp standardError 0.011195857525727288 ### Source [Original source](https://epoch.ai/data/benchmark_data.zip#file=math_level_5.csv) Source epoch ai Original model label gemma-3-27b-it Source version MATH level 5 Evaluated 2025-03-13T05:52:35.397Z Observed 2026-10-21T16:30:24.199Z Evidence SHA-256 `041b4bcb991a81d66152327113ef6d38e64cd8cce93d1e6ec821d1b9e47c1de3` Source locator `/rows/33` | | | | | | | | | [Arena text / industry life and physical and social science](https://benchize.com/benchmarks/lmarena%3Atext%3Aindustry_life_and_physical_and_social_science.md) | 1,382.95 | — | 101 / 151 | — | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1382.9451993275009 \| rating \| reported \| Higher is better \| ### Configuration category industry_life_and_physical_and_social_science config text ### Reported statistics lower 1375.874114531734 rank 180 upper 1390.0162841232675 variance 13.015951106795917 votes 7868 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) Source Arena Original model label Gemma 3 27B IT Observed 2026-10-21T16:40:19.533Z Evidence SHA-256 `8e027ef69b8de06c4b2a8b217bfe816b1f1536269bb257fd295b4ef1ba8246ac` Source locator `/rows/5677/row` | | | | | | | | | [Arena text / expert](https://benchize.com/benchmarks/lmarena%3Atext%3Aexpert.md) | 1,303.71 | — | 121 / 148 | — | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1303.7097697020426 \| rating \| reported \| Higher is better \| ### Configuration category expert config text ### Reported statistics lower 1291.086860379902 rank 232 upper 1316.3326790241833 variance 41.47847138087869 votes 2263 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) Source Arena Original model label Gemma 3 27B IT Observed 2026-10-21T16:40:19.533Z Evidence SHA-256 `8e027ef69b8de06c4b2a8b217bfe816b1f1536269bb257fd295b4ef1ba8246ac` Source locator `/rows/2702/row` | | | | | | | | | [Arena text style control / expert](https://benchize.com/benchmarks/lmarena%3Atext_style_control%3Aexpert.md) | 1,338.84 | — | 122 / 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` \| 1338.836565441706 \| rating \| reported \| Higher is better \| ### Configuration category expert config text_style_control ### Reported statistics lower 1326.0290459421797 rank 231 upper 1351.6440849412322 variance 42.70058938211072 votes 2263 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label Gemma 3 27B IT Observed 2026-10-21T16:40:19.533Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/2701/row` | | | | | | | | | [Arena text / math](https://benchize.com/benchmarks/lmarena%3Atext%3Amath.md) | 1,312.15 | — | 124 / 149 | — | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1312.1476295489206 \| rating \| reported \| Higher is better \| ### Configuration category math config text ### Reported statistics lower 1302.6809269981397 rank 231 upper 1321.6143320997016 variance 23.32927707103954 votes 3587 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) Source Arena Original model label Gemma 3 27B IT Observed 2026-10-21T16:40:19.533Z Evidence SHA-256 `8e027ef69b8de06c4b2a8b217bfe816b1f1536269bb257fd295b4ef1ba8246ac` Source locator `/rows/9143/row` | | | | | | | | | [Arena text / instruction following](https://benchize.com/benchmarks/lmarena%3Atext%3Ainstruction_following.md) | 1,320.59 | — | 112 / 151 | — | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1320.590765553906 \| rating \| reported \| Higher is better \| ### Configuration category instruction_following config text ### Reported statistics lower 1314.942295821886 rank 213 upper 1326.239235285926 variance 8.305493252113473 votes 12501 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) Source Arena Original model label Gemma 3 27B IT Observed 2026-10-21T16:40:19.533Z Evidence SHA-256 `8e027ef69b8de06c4b2a8b217bfe816b1f1536269bb257fd295b4ef1ba8246ac` Source locator `/rows/7746/row` | | | | | | | | | [Arena text / polish](https://benchize.com/benchmarks/lmarena%3Atext%3Apolish.md) | 1,345.1 | — | 94 / 117 | — | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1345.0983466288367 \| rating \| reported \| Higher is better \| ### Configuration category polish config text ### Reported statistics lower 1333.3534289042514 rank 171 upper 1356.8432643534222 variance 35.90903841378537 votes 2829 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) Source Arena Original model label Gemma 3 27B IT Observed 2026-10-21T16:40:19.533Z Evidence SHA-256 `8e027ef69b8de06c4b2a8b217bfe816b1f1536269bb257fd295b4ef1ba8246ac` Source locator `/rows/10318/row` | | | | | | | | | [Spiral-Bench v1.2](https://benchize.com/benchmarks/eq-bench%3Aspiral-bench-v1.2.md) | 25.2% | CI 25.2–25.2% | 13 / 16 | — | — | [eq bench · spiral-bench-v1.2](https://eqbench.com/spiral-bench.js) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `score_norm` \| 25.2 \| percent \| overall \| Higher is better \| ### Configuration interactiveAdjustments none protocol spiral-bench-v1.2 sourceModelVersion gemma-3-27b-it ### Reported statistics Uncertainty Confidence interval: 25.2–25.2% confidenceIntervalHigh 25.2 confidenceIntervalLow 25.2 ### Source [Original source](https://eqbench.com/spiral-bench.js) Source eq bench Original model label gemma-3-27b-it Source version spiral-bench-v1.2 Observed 2026-10-21T16:35:04.308Z Evidence SHA-256 `2f0402654b01e7363c0d02bbc708afd7849e669dc5da63d9f85c995ed8f0a97f` Source locator `/leaderboardDataDelusion/22` | | | | | | | | | [Arena text style control / russian](https://benchize.com/benchmarks/lmarena%3Atext_style_control%3Arussian.md) | 1,367.4 | — | 102 / 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` \| 1367.401676504208 \| rating \| reported \| Higher is better \| ### Configuration category russian config text_style_control ### Reported statistics lower 1357.6581957234812 rank 191 upper 1377.1451572849346 variance 24.71337639049168 votes 3433 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label Gemma 3 27B IT Observed 2026-10-21T16:40:19.533Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/10574/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) | 1,327.27 | — | 108 / 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` \| 1327.2719699743316 \| rating \| reported \| Higher is better \| ### Configuration category industry_entertainment_and_sports_and_media config text_style_control ### Reported statistics lower 1320.350240547485 rank 202 upper 1334.193699401178 variance 12.47191249334148 votes 8002 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label Gemma 3 27B IT Observed 2026-10-21T16:40:19.533Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/4894/row` | | | | | | | | | [OTIS Mock AIME 2024–2025](https://benchize.com/benchmarks/epoch-ai%3Aotis_mock_aime_2024_2025.md) | 22.5% | SE ±5.28 pp | 106 / 123 | — | — | [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` \| 0.225 \| score_fraction \| Best score (across scorers) \| Higher is better \| \| `mean_score` \| 0.225 \| score_fraction \| mean_score \| Higher is better \| ### Configuration benchmarkVersion OTIS Mock AIME 2024-2025 reasoningBudget Not reported Reasoning effort Not reported sourceModelVersion gemma-3-27b-it ### Reported statistics Uncertainty Standard error: ±5.28 pp standardError 0.052794388667238824 ### Source [Original source](https://epoch.ai/data/benchmark_data.zip#file=otis_mock_aime_2024_2025.csv) Source epoch ai Original model label gemma-3-27b-it Source version OTIS Mock AIME 2024-2025 Evaluated 2026-08-27T14:17:59.000Z Observed 2026-10-21T16:30:24.199Z Evidence SHA-256 `5b411612f91e155dff4b09d09b548b42f7936482ea8b3c00b510bd46e2f6bc2c` Source locator `/rows/60` | | | | | | | | | [Arena text / hard prompts english](https://benchize.com/benchmarks/lmarena%3Atext%3Ahard_prompts_english.md) | 1,353.1 | — | 115 / 151 | — | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1353.0969697122011 \| rating \| reported \| Higher is better \| ### Configuration category hard_prompts_english config text ### Reported statistics lower 1346.512428023534 rank 222 upper 1359.6815114008682 variance 11.286386571745332 votes 8933 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) Source Arena Original model label Gemma 3 27B IT Observed 2026-10-21T16:40:19.533Z Evidence SHA-256 `8e027ef69b8de06c4b2a8b217bfe816b1f1536269bb257fd295b4ef1ba8246ac` Source locator `/rows/4089/row` | | | | | | | | | [Arena vision / humor (config: vision)](https://benchize.com/benchmarks/benchmark%3Avision%3Ahumor--config-vision.md) | 1,166.24 | — | 57 / 63 | — | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/vision/latest) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1166.242332648924 \| rating \| reported \| Higher is better \| ### Configuration category humor config vision ### Reported statistics lower 1142.1332928369002 rank 85 upper 1190.351372460948 variance 151.30861159478079 votes 762 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/vision/latest) Source Arena Original model label Gemma 3 27B IT Observed 2026-10-21T16:40:19.533Z Evidence SHA-256 `06e61305486dce3fec5dc776ac2fd8321104e84c346cf9e08fa6f8e8a66ce0d7` Source locator `/rows/1010/row` | | | | | | | | | [Arena vision / ocr (config: vision)](https://benchize.com/benchmarks/benchmark%3Avision%3Aocr--config-vision.md) | 1,156.27 | — | 69 / 74 | — | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/vision/latest) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1156.2739576246106 \| rating \| reported \| Higher is better \| ### Configuration category ocr config vision ### Reported statistics lower 1146.3294903572046 rank 112 upper 1166.2184248920166 variance 25.743456808588043 votes 6196 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/vision/latest) Source Arena Original model label Gemma 3 27B IT Observed 2026-10-21T16:40:19.533Z Evidence SHA-256 `06e61305486dce3fec5dc776ac2fd8321104e84c346cf9e08fa6f8e8a66ce0d7` Source locator `/rows/1130/row` | | | | | | | | | [Arena vision style control / creative writing vision](https://benchize.com/benchmarks/lmarena%3Avision_style_control%3Acreative_writing_vision.md) | 1,167.34 | — | 64 / 70 | — | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/vision_style_control/latest) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1167.3430959814239 \| rating \| reported \| Higher is better \| ### Configuration category creative_writing_vision config vision_style_control ### Reported statistics lower 1141.793606554178 rank 93 upper 1192.89258540867 variance 169.92930042004133 votes 627 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/vision_style_control/latest) Source Arena Original model label Gemma 3 27B IT Observed 2026-10-21T16:40:19.533Z Evidence SHA-256 `38568936995f36625aae49e9ea05557d55c1b1df9b2954f5c50cee523f26fe92` Source locator `/rows/455/row` | | | | | | | | | [Arena text / german](https://benchize.com/benchmarks/lmarena%3Atext%3Agerman.md) | 1,361.89 | — | 88 / 129 | — | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1361.8899521105077 \| rating \| reported \| Higher is better \| ### Configuration category german config text ### Reported statistics lower 1344.5783292364804 rank 160 upper 1379.201574984535 variance 78.0152282039541 votes 1207 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) Source Arena Original model label Gemma 3 27B IT Observed 2026-10-21T16:40:19.533Z Evidence SHA-256 `8e027ef69b8de06c4b2a8b217bfe816b1f1536269bb257fd295b4ef1ba8246ac` Source locator `/rows/3296/row` | | | | | | | | | [Arena text style control / industry legal and government](https://benchize.com/benchmarks/lmarena%3Atext_style_control%3Aindustry_legal_and_government.md) | 1,383.9 | — | 104 / 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` \| 1383.8992803572737 \| rating \| reported \| Higher is better \| ### Configuration category industry_legal_and_government config text_style_control ### Reported statistics lower 1372.2389670925618 rank 193 upper 1395.5595936219854 variance 35.39356056578698 votes 2661 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label Gemma 3 27B IT Observed 2026-10-21T16:40:19.533Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/5300/row` | | | | | | | | | [Arena vision / creative writing (config: vision)](https://benchize.com/benchmarks/benchmark%3Avision%3Acreative_writing--config-vision.md) | 1,182.13 | — | 10 / 13 | — | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/vision/latest) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1182.1307034271204 \| rating \| reported \| Higher is better \| ### Configuration category creative_writing config vision ### Reported statistics lower 1160.6506866246389 rank 25 upper 1203.6107202296018 variance 120.10830868454175 votes 732 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/vision/latest) Source Arena Original model label gemma-3-27b-it Observed 2026-10-21T16:40:19.533Z Evidence SHA-256 `06e61305486dce3fec5dc776ac2fd8321104e84c346cf9e08fa6f8e8a66ce0d7` Source locator `/rows/353/row` | | | | | | | | | [SWE-Bench Pro](https://benchize.com/benchmarks/scale%3Aswe_bench_pro.md) | 11.38source score | CI 9.23–13.53 | 7 / 7 | — | — | [scale](https://labs.scale.com/leaderboard/swe_bench_pro) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `score` \| 11.38 \| source_score \| reported \| Higher is better \| ### Configuration Reasoning effort unknown Model configuration gemma-3-27b-it sourceModelVersion Not reported thinkingEnabled Not reported ### Reported statistics Uncertainty Confidence interval: 9.23–13.53 contaminationWarning Not reported rank 21 reportedConfidenceHalfWidth 2.15 ### Source [Original source](https://labs.scale.com/leaderboard/swe_bench_pro) Source scale Original model label gemma-3-27b-it Observed 2026-10-21T16:35:31.591Z Evidence SHA-256 `84e15e1dddeda00cf2a551d7da18b80ff1a852172af780b528894ae989215060` Source locator `/rows/20` | | | | | | | | | [Arena vision style control / overall](https://benchize.com/benchmarks/lmarena%3Avision_style_control%3Aoverall.md) | 1,159.9 | — | 72 / 82 | — | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/vision_style_control/latest) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1159.8979133944738 \| rating \| reported \| Higher is better \| ### Configuration category overall config vision_style_control ### Reported statistics lower 1151.7904610152007 rank 113 upper 1168.005365773747 variance 17.11089123956961 votes 16982 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/vision_style_control/latest) Source Arena Original model label Gemma 3 27B IT Observed 2026-10-21T16:40:19.533Z Evidence SHA-256 `38568936995f36625aae49e9ea05557d55c1b1df9b2954f5c50cee523f26fe92` Source locator `/rows/112/row` | | | | | | | | | [Arena text / industry business and management and financial operations](https://benchize.com/benchmarks/lmarena%3Atext%3Aindustry_business_and_management_and_financial_operations.md) | 1,359.54 | — | 103 / 151 | — | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1359.543023021105 \| rating \| reported \| Higher is better \| ### Configuration category industry_business_and_management_and_financial_operations config text ### Reported statistics lower 1351.9306666901603 rank 182 upper 1367.15537935205 variance 15.084886136773713 votes 6495 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) Source Arena Original model label Gemma 3 27B IT Observed 2026-10-21T16:40:19.533Z Evidence SHA-256 `8e027ef69b8de06c4b2a8b217bfe816b1f1536269bb257fd295b4ef1ba8246ac` Source locator `/rows/4464/row` | | | | | | | | | [Arena text / industry medicine and healthcare](https://benchize.com/benchmarks/lmarena%3Atext%3Aindustry_medicine_and_healthcare.md) | 1,391.07 | — | 96 / 151 | — | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1391.0666489504688 \| rating \| reported \| Higher is better \| ### Configuration category industry_medicine_and_healthcare config text ### Reported statistics lower 1378.5436462762113 rank 168 upper 1403.5896516247258 variance 40.82448967944908 votes 2342 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) Source Arena Original model label Gemma 3 27B IT Observed 2026-10-21T16:40:19.533Z Evidence SHA-256 `8e027ef69b8de06c4b2a8b217bfe816b1f1536269bb257fd295b4ef1ba8246ac` Source locator `/rows/6480/row` | | | | | | | | | [Arena text / industry entertainment and sports and media](https://benchize.com/benchmarks/lmarena%3Atext%3Aindustry_entertainment_and_sports_and_media.md) | 1,319.97 | — | 107 / 151 | — | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1319.9702350149241 \| rating \| reported \| Higher is better \| ### Configuration category industry_entertainment_and_sports_and_media config text ### Reported statistics lower 1313.144825128037 rank 199 upper 1326.7956449018113 variance 12.127221011209235 votes 8002 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) Source Arena Original model label Gemma 3 27B IT Observed 2026-10-21T16:40:19.533Z Evidence SHA-256 `8e027ef69b8de06c4b2a8b217bfe816b1f1536269bb257fd295b4ef1ba8246ac` Source locator `/rows/4891/row` | | | | | | | | | [Arena text style control / polish](https://benchize.com/benchmarks/lmarena%3Atext_style_control%3Apolish.md) | 1,369.01 | — | 88 / 117 | — | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1369.0066445875555 \| rating \| reported \| Higher is better \| ### Configuration category polish config text_style_control ### Reported statistics lower 1356.9656345435944 rank 162 upper 1381.0476546315163 variance 37.74241236108565 votes 2829 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label Gemma 3 27B IT Observed 2026-10-21T16:40:19.533Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/10309/row` | | | | | | | | | [Slop Score](https://benchize.com/benchmarks/eq-bench%3Aslop-score.md) | 69.48% | — | 13 / 16 | — | — | [eq bench · slop-score](https://eqbench.com/data/leaderboard_results.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `slop_score` \| 69.48152692002944 \| percent \| official_normalized_composite \| Lower is better \| \| `slop_list_matches_per_1k_words` \| 32.26903897173587 \| matches_per_1000_words \| writing_samples \| Lower is better \| \| `slop_trigram_matches_per_1k_words` \| 0.7818818284097658 \| matches_per_1000_words \| writing_samples \| Lower is better \| \| `not_x_but_y_per_1k_chars` \| 0.577146282667755 \| matches_per_1000_chars \| writing_samples \| Lower is better \| ### Configuration normalization official_population_min_max_10_percent_buffer protocol slop-score ### Reported statistics samples 300 ### Source [Original source](https://eqbench.com/data/leaderboard_results.json) Source eq bench Original model label google/gemma-3-27b-it Source version slop-score Evaluated 2025-11-01T08:21:30.159894+00:00 Observed 2026-10-21T16:35:04.972Z Evidence SHA-256 `16925b79d955a1cacef4d2ac91b696e73f976a4a3ceb45122544a9cf661b04de` Source locator `/results/18` | | | | | | | | | [Arena text style control / non english](https://benchize.com/benchmarks/lmarena%3Atext_style_control%3Anon_english.md) | 1,349.61 | — | 108 / 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` \| 1349.6086965147413 \| rating \| reported \| Higher is better \| ### Configuration category non_english config text_style_control ### Reported statistics lower 1344.9442018463435 rank 202 upper 1354.2731911831388 variance 5.66386665250757 votes 23611 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label Gemma 3 27B IT Observed 2026-10-21T16:40:19.533Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/9932/row` | | | | | | | | | [Arena vision / diagram (config: vision)](https://benchize.com/benchmarks/benchmark%3Avision%3Adiagram--config-vision.md) | 1,155.79 | — | 69 / 74 | — | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/vision/latest) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1155.7942444275386 \| rating \| reported \| Higher is better \| ### Configuration category diagram config vision ### Reported statistics lower 1140.6826905608232 rank 109 upper 1170.9057982942536 variance 59.445921699447716 votes 1715 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/vision/latest) Source Arena Original model label Gemma 3 27B IT Observed 2026-10-21T16:40:19.533Z Evidence SHA-256 `06e61305486dce3fec5dc776ac2fd8321104e84c346cf9e08fa6f8e8a66ce0d7` Source locator `/rows/575/row` | | | | | | | | | [Arena text style control / hard prompts english](https://benchize.com/benchmarks/lmarena%3Atext_style_control%3Ahard_prompts_english.md) | 1,375.06 | — | 115 / 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` \| 1375.059012355892 \| rating \| reported \| Higher is better \| ### Configuration category hard_prompts_english config text_style_control ### Reported statistics lower 1368.3822717426733 rank 225 upper 1381.7357529691108 variance 11.604670854742666 votes 8933 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label Gemma 3 27B IT Observed 2026-10-21T16:40:19.533Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/4092/row` | | | | | | | | | [Arena text style control / longer query](https://benchize.com/benchmarks/lmarena%3Atext_style_control%3Alonger_query.md) | 1,365.39 | — | 109 / 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` \| 1365.3860224304988 \| rating \| reported \| Higher is better \| ### Configuration category longer_query config text_style_control ### Reported statistics lower 1357.9199683009172 rank 208 upper 1372.8520765600804 variance 14.510623923796123 votes 6675 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label Gemma 3 27B IT Observed 2026-10-21T16:40:19.533Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/8725/row` | | | | | | | | | [NC Bench](https://benchize.com/benchmarks/nc-bench%3Aoverall.md) | 75.7% | — | 136 / 144 | — | — | [nc bench](https://www.nc-bench.com/models) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `score` \| 75.7 \| percent \| reported \| Higher is better \| \| `tooling` \| 96.15 \| percent \| category \| Higher is better \| \| `creative_writing` \| 78.79 \| percent \| category \| Higher is better \| \| `language` \| 77.21 \| percent \| category \| Higher is better \| \| `utility` \| 76.82 \| percent \| category \| Higher is better \| \| `reasoning` \| 61.51 \| percent \| category \| Higher is better \| \| `text_editing` \| 86.63 \| percent \| category \| Higher is better \| \| `rule_following` \| 47.98 \| percent \| category \| Higher is better \| \| `hallucination` \| 80.53 \| percent \| category \| Higher is better \| ### Configuration Reasoning effort unknown Model configuration Gemma 3 27B thinkingEnabled Not reported ### Source [Original source](https://www.nc-bench.com/models) Source nc bench Original model label Gemma 3 27B Observed 2026-10-21T16:31:48.370Z Evidence SHA-256 `ec261022458543624b08a136d01f5a2f0666cd52ffb49c64d6ca983e8543d1b5` Source locator `/rows/182` | | | | | | | | | [Arena text style control / instruction following](https://benchize.com/benchmarks/lmarena%3Atext_style_control%3Ainstruction_following.md) | 1,343.27 | — | 112 / 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` \| 1343.2661128933207 \| rating \| reported \| Higher is better \| ### Configuration category instruction_following config text_style_control ### Reported statistics lower 1337.552959934951 rank 214 upper 1348.9792658516901 variance 8.49680245168659 votes 12501 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label Gemma 3 27B IT Observed 2026-10-21T16:40:19.533Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/7747/row` | | | | | | | | | [Arena text / japanese](https://benchize.com/benchmarks/lmarena%3Atext%3Ajapanese.md) | 1,286.81 | — | 91 / 120 | — | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1286.8071367999462 \| rating \| reported \| Higher is better \| ### Configuration category japanese config text ### Reported statistics lower 1267.906435005383 rank 168 upper 1305.7078385945097 variance 92.9950169978549 votes 1052 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) Source Arena Original model label Gemma 3 27B IT Observed 2026-10-21T16:40:19.533Z Evidence SHA-256 `8e027ef69b8de06c4b2a8b217bfe816b1f1536269bb257fd295b4ef1ba8246ac` Source locator `/rows/8118/row` | | | | | | | | | [Arena vision / english (config: vision)](https://benchize.com/benchmarks/benchmark%3Avision%3Aenglish--config-vision.md) | 1,188.22 | — | 69 / 82 | — | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/vision/latest) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1188.222184536285 \| rating \| reported \| Higher is better \| ### Configuration category english config vision ### Reported statistics lower 1177.8797798191026 rank 105 upper 1198.564589253468 variance 27.84497773548369 votes 7938 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/vision/latest) Source Arena Original model label Gemma 3 27B IT Observed 2026-10-21T16:40:19.533Z Evidence SHA-256 `06e61305486dce3fec5dc776ac2fd8321104e84c346cf9e08fa6f8e8a66ce0d7` Source locator `/rows/694/row` | | | | | | | | | [Arena text style control / japanese](https://benchize.com/benchmarks/lmarena%3Atext_style_control%3Ajapanese.md) | 1,307.92 | — | 89 / 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` \| 1307.9218612634677 \| rating \| reported \| Higher is better \| ### Configuration category japanese config text_style_control ### Reported statistics lower 1289.0020431976363 rank 168 upper 1326.841679329299 variance 93.18322344516905 votes 1052 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label Gemma 3 27B IT Observed 2026-10-21T16:40:19.533Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/8118/row` | | | | | | | | | [Arena text style control / coding](https://benchize.com/benchmarks/lmarena%3Atext_style_control%3Acoding.md) | 1,357.51 | — | 131 / 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` \| 1357.5078839490384 \| rating \| reported \| Higher is better \| ### Configuration category coding config text_style_control ### Reported statistics lower 1350.5645986799482 rank 263 upper 1364.4511692181286 variance 12.54971420447329 votes 8024 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label Gemma 3 27B IT Observed 2026-10-21T16:40:19.533Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/1072/row` | | | | | | | | | [SVGBench Arena](https://benchize.com/benchmarks/svgbench%3Aarena.md) | 1,275 | — | 176 / 191 | — | — | [svgbench](https://svgbench.ai/api/leaderboard?shape=2) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1275 \| rating \| reported \| Higher is better \| ### Configuration Reasoning effort unknown sourceModelId model_google_gemma_3_27b_it ### Reported statistics coverageCount 27 draws 0 judged 13 losses 12 rank 290 ratingDeviation 70 wins 1 ### Source [Original source](https://svgbench.ai/api/leaderboard?shape=2) Source svgbench Original model label Gemma 3 27B Observed 2026-10-21T16:32:23.388Z Evidence SHA-256 `5c0a9c869593820d57d2c05f6d416e1b44a740b4835e66c66e9ad8b8edc59e2c` Source locator `/rows/274` | | | | | | | | | [Arena text / coding](https://benchize.com/benchmarks/lmarena%3Atext%3Acoding.md) | 1,321.82 | — | 123 / 151 | — | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1321.8183408111595 \| rating \| reported \| Higher is better \| ### Configuration category coding config text ### Reported statistics lower 1314.9773371755082 rank 241 upper 1328.6593444468108 variance 12.18269749265129 votes 8024 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) Source Arena Original model label Gemma 3 27B IT Observed 2026-10-21T16:40:19.533Z Evidence SHA-256 `8e027ef69b8de06c4b2a8b217bfe816b1f1536269bb257fd295b4ef1ba8246ac` Source locator `/rows/1050/row` | | | | | | | | | [Arena vision style control / captioning](https://benchize.com/benchmarks/lmarena%3Avision_style_control%3Acaptioning.md) | 1,116.75 | — | 21 / 22 | — | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/vision_style_control/latest) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1116.7484194373712 \| rating \| reported \| Higher is better \| ### Configuration category captioning config vision_style_control ### Reported statistics lower 1077.7485995319785 rank 31 upper 1155.7482393427642 variance 395.93967387062725 votes 258 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/vision_style_control/latest) Source Arena Original model label Gemma 3 27B IT Observed 2026-10-21T16:40:19.533Z Evidence SHA-256 `38568936995f36625aae49e9ea05557d55c1b1df9b2954f5c50cee523f26fe92` Source locator `/rows/197/row` | | | | | | | | | [Arena vision style control / chinese](https://benchize.com/benchmarks/lmarena%3Avision_style_control%3Achinese.md) | 1,173.76 | — | 62 / 74 | — | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/vision_style_control/latest) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1173.763103500749 \| rating \| reported \| Higher is better \| ### Configuration category chinese config vision_style_control ### Reported statistics lower 1152.3256036537873 rank 95 upper 1195.2006033477107 variance 119.63330108155192 votes 1020 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/vision_style_control/latest) Source Arena Original model label Gemma 3 27B IT Observed 2026-10-21T16:40:19.533Z Evidence SHA-256 `38568936995f36625aae49e9ea05557d55c1b1df9b2954f5c50cee523f26fe92` Source locator `/rows/295/row` | | | | | | | | | [Arena vision style control / entity recognition](https://benchize.com/benchmarks/lmarena%3Avision_style_control%3Aentity_recognition.md) | 1,169.96 | — | 27 / 34 | — | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/vision_style_control/latest) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1169.9597789527795 \| rating \| reported \| Higher is better \| ### Configuration category entity_recognition config vision_style_control ### Reported statistics lower 1135.4337915342062 rank 41 upper 1204.4857663713528 variance 310.31018757923107 votes 313 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/vision_style_control/latest) Source Arena Original model label Gemma 3 27B IT Observed 2026-10-21T16:40:19.533Z Evidence SHA-256 `38568936995f36625aae49e9ea05557d55c1b1df9b2954f5c50cee523f26fe92` Source locator `/rows/797/row` | | | | | | | | | [Arena text / multi turn](https://benchize.com/benchmarks/lmarena%3Atext%3Amulti_turn.md) | 1,344.57 | — | 110 / 151 | — | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1344.5746372295214 \| rating \| reported \| Higher is better \| ### Configuration category multi_turn config text ### Reported statistics lower 1337.0792842231554 rank 207 upper 1352.0699902358874 variance 14.624734850050508 votes 6730 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) Source Arena Original model label Gemma 3 27B IT Observed 2026-10-21T16:40:19.533Z Evidence SHA-256 `8e027ef69b8de06c4b2a8b217bfe816b1f1536269bb257fd295b4ef1ba8246ac` Source locator `/rows/9522/row` | | | | | | | | | [Arena text style control / overall](https://benchize.com/benchmarks/lmarena%3Atext_style_control%3Aoverall.md) | 1,365.44 | — | 107 / 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` \| 1365.4398998316287 \| rating \| reported \| Higher is better \| ### Configuration category overall config text_style_control ### Reported statistics lower 1361.7354517854194 rank 201 upper 1369.1443478778378 variance 3.5723239445226342 votes 46664 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label Gemma 3 27B IT Observed 2026-10-21T16:40:19.533Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/200/row` | | | | | | | | | [Arena vision / overall (config: vision)](https://benchize.com/benchmarks/benchmark%3Avision%3Aoverall--config-vision.md) | 1,164.55 | — | 69 / 82 | — | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/vision/latest) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1164.5475341760637 \| rating \| reported \| Higher is better \| ### Configuration category overall config vision ### Reported statistics lower 1156.530712137832 rank 112 upper 1172.564356214295 variance 16.730476257210015 votes 16982 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/vision/latest) Source Arena Original model label Gemma 3 27B IT Observed 2026-10-21T16:40:19.533Z Evidence SHA-256 `06e61305486dce3fec5dc776ac2fd8321104e84c346cf9e08fa6f8e8a66ce0d7` Source locator `/rows/111/row` | | | | | | | | | [Arena text style control / chinese](https://benchize.com/benchmarks/lmarena%3Atext_style_control%3Achinese.md) | 1,370.68 | — | 113 / 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` \| 1370.678515366981 \| rating \| reported \| Higher is better \| ### Configuration category chinese config text_style_control ### Reported statistics lower 1359.3439165707036 rank 219 upper 1382.0131141632583 variance 33.443838882374514 votes 2850 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label Gemma 3 27B IT Observed 2026-10-21T16:40:19.533Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/635/row` | | | | | | | | | [Arena text style control / industry mathematical](https://benchize.com/benchmarks/lmarena%3Atext_style_control%3Aindustry_mathematical.md) | 1,340.18 | — | 121 / 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` \| 1340.1827867526408 \| rating \| reported \| Higher is better \| ### Configuration category industry_mathematical config text_style_control ### Reported statistics lower 1330.0542367082844 rank 228 upper 1350.3113367969972 variance 26.705356165316484 votes 3210 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label Gemma 3 27B IT Observed 2026-10-21T16:40:19.533Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/6140/row` | | | | | | | | | [Arena text style control / creative writing](https://benchize.com/benchmarks/lmarena%3Atext_style_control%3Acreative_writing.md) | 1,348.36 | — | 96 / 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` \| 1348.3559887716992 \| rating \| reported \| Higher is better \| ### Configuration category creative_writing config text_style_control ### Reported statistics lower 1340.6234804158307 rank 183 upper 1356.088497127568 variance 15.564838324304567 votes 6304 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label Gemma 3 27B IT Observed 2026-10-21T16:40:19.533Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/1404/row` | | | | | | | | | [Arena vision style control / ocr](https://benchize.com/benchmarks/lmarena%3Avision_style_control%3Aocr.md) | 1,161.32 | — | 70 / 74 | — | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/vision_style_control/latest) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1161.3212992438362 \| rating \| reported \| Higher is better \| ### Configuration category ocr config vision_style_control ### Reported statistics lower 1151.2741769638428 rank 110 upper 1171.3684215238295 variance 26.277690539163064 votes 6196 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/vision_style_control/latest) Source Arena Original model label Gemma 3 27B IT Observed 2026-10-21T16:40:19.533Z Evidence SHA-256 `38568936995f36625aae49e9ea05557d55c1b1df9b2954f5c50cee523f26fe92` Source locator `/rows/1128/row` | | | | | | | | | [Arena text style control / korean](https://benchize.com/benchmarks/lmarena%3Atext_style_control%3Akorean.md) | 1,323.72 | — | 89 / 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` \| 1323.718145049606 \| rating \| reported \| Higher is better \| ### Configuration category korean config text_style_control ### Reported statistics lower 1302.9855485649443 rank 168 upper 1344.4507415342678 variance 111.89513595205848 votes 889 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label Gemma 3 27B IT Observed 2026-10-21T16:40:19.533Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/8401/row` | | | | | | | | | [Arena text / chinese](https://benchize.com/benchmarks/lmarena%3Atext%3Achinese.md) | 1,346.27 | — | 117 / 146 | — | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1346.2714784682012 \| rating \| reported \| Higher is better \| ### Configuration category chinese config text ### Reported statistics lower 1335.068266042065 rank 221 upper 1357.4746908943373 variance 32.67299599542538 votes 2850 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) Source Arena Original model label Gemma 3 27B IT Observed 2026-10-21T16:40:19.533Z Evidence SHA-256 `8e027ef69b8de06c4b2a8b217bfe816b1f1536269bb257fd295b4ef1ba8246ac` Source locator `/rows/637/row` | | | | | | | | | [Arena text / longer query](https://benchize.com/benchmarks/lmarena%3Atext%3Alonger_query.md) | 1,333.21 | — | 111 / 150 | — | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1333.2052945298594 \| rating \| reported \| Higher is better \| ### Configuration category longer_query config text ### Reported statistics lower 1325.8209885338802 rank 211 upper 1340.589600525839 variance 14.194600954333167 votes 6675 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) Source Arena Original model label Gemma 3 27B IT Observed 2026-10-21T16:40:19.533Z Evidence SHA-256 `8e027ef69b8de06c4b2a8b217bfe816b1f1536269bb257fd295b4ef1ba8246ac` Source locator `/rows/8728/row` | | | | | | | | | [Arena text / korean](https://benchize.com/benchmarks/lmarena%3Atext%3Akorean.md) | 1,307.5 | — | 93 / 124 | — | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1307.5044867876766 \| rating \| reported \| Higher is better \| ### Configuration category korean config text ### Reported statistics lower 1286.9360612305816 rank 167 upper 1328.0729123447713 variance 110.13007027921554 votes 889 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) Source Arena Original model label Gemma 3 27B IT Observed 2026-10-21T16:40:19.533Z Evidence SHA-256 `8e027ef69b8de06c4b2a8b217bfe816b1f1536269bb257fd295b4ef1ba8246ac` Source locator `/rows/8400/row` | | | | | | | | | [Arena vision style control / humor](https://benchize.com/benchmarks/lmarena%3Avision_style_control%3Ahumor.md) | 1,153.74 | — | 59 / 63 | — | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/vision_style_control/latest) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1153.7366332280392 \| rating \| reported \| Higher is better \| ### Configuration category humor config vision_style_control ### Reported statistics lower 1129.1861278465597 rank 85 upper 1178.2871386095185 variance 156.90063140573747 votes 762 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/vision_style_control/latest) Source Arena Original model label Gemma 3 27B IT Observed 2026-10-21T16:40:19.533Z Evidence SHA-256 `38568936995f36625aae49e9ea05557d55c1b1df9b2954f5c50cee523f26fe92` Source locator `/rows/1010/row` | | | | | | | | | [Arena text / industry software and it services](https://benchize.com/benchmarks/lmarena%3Atext%3Aindustry_software_and_it_services.md) | 1,354.03 | — | 118 / 151 | — | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1354.0268582146582 \| rating \| reported \| Higher is better \| ### Configuration category industry_software_and_it_services config text ### Reported statistics lower 1348.508465392501 rank 223 upper 1359.5452510368154 variance 7.927368419410429 votes 14082 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) Source Arena Original model label Gemma 3 27B IT Observed 2026-10-21T16:40:19.533Z Evidence SHA-256 `8e027ef69b8de06c4b2a8b217bfe816b1f1536269bb257fd295b4ef1ba8246ac` Source locator `/rows/6923/row` | | | | | | | | | [Arena text / exclude ties](https://benchize.com/benchmarks/lmarena%3Atext%3Aexclude_ties.md) | 1,321.4 | — | 109 / 151 | — | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1321.39974977213 \| rating \| reported \| Higher is better \| ### Configuration category exclude_ties config text ### Reported statistics lower 1316.306025605726 rank 200 upper 1326.493473938534 variance 6.754211640545384 votes 32661 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) Source Arena Original model label Gemma 3 27B IT Observed 2026-10-21T16:40:19.533Z Evidence SHA-256 `8e027ef69b8de06c4b2a8b217bfe816b1f1536269bb257fd295b4ef1ba8246ac` Source locator `/rows/2253/row` | | | | | | | | | [Arena text / english](https://benchize.com/benchmarks/lmarena%3Atext%3Aenglish.md) | 1,376.52 | — | 108 / 151 | — | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1376.520738681046 \| rating \| reported \| Higher is better \| ### Configuration category english config text ### Reported statistics lower 1371.8667456745895 rank 197 upper 1381.1747316875023 variance 5.638392057585818 votes 23043 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) Source Arena Original model label Gemma 3 27B IT Observed 2026-10-21T16:40:19.533Z Evidence SHA-256 `8e027ef69b8de06c4b2a8b217bfe816b1f1536269bb257fd295b4ef1ba8246ac` Source locator `/rows/1833/row` | | | | | | | | | [Arena text style control / multi turn](https://benchize.com/benchmarks/lmarena%3Atext_style_control%3Amulti_turn.md) | 1,357.92 | — | 107 / 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` \| 1357.915515441279 \| rating \| reported \| Higher is better \| ### Configuration category multi_turn config text_style_control ### Reported statistics lower 1350.3477219272809 rank 204 upper 1365.4833089552772 variance 14.908788911646562 votes 6730 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label Gemma 3 27B IT Observed 2026-10-21T16:40:19.533Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/9519/row` | | | | | | | | | [Arena text style control / hard prompts](https://benchize.com/benchmarks/lmarena%3Atext_style_control%3Ahard_prompts.md) | 1,366.55 | — | 115 / 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` \| 1366.546694931966 \| rating \| reported \| Higher is better \| ### Configuration category hard_prompts config text_style_control ### Reported statistics lower 1361.3460191466138 rank 220 upper 1371.7473707173178 variance 7.040822220621745 votes 17704 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label Gemma 3 27B IT Observed 2026-10-21T16:40:19.533Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/3670/row` | | | | | | | | | [Arena vision style control / diagram](https://benchize.com/benchmarks/lmarena%3Avision_style_control%3Adiagram.md) | 1,166.21 | — | 70 / 74 | — | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/vision_style_control/latest) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1166.2113025317599 \| rating \| reported \| Higher is better \| ### Configuration category diagram config vision_style_control ### Reported statistics lower 1150.9275893460726 rank 113 upper 1181.4950157174467 variance 60.80811994755025 votes 1715 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/vision_style_control/latest) Source Arena Original model label Gemma 3 27B IT Observed 2026-10-21T16:40:19.533Z Evidence SHA-256 `38568936995f36625aae49e9ea05557d55c1b1df9b2954f5c50cee523f26fe92` Source locator `/rows/579/row` | | | | | | | | --- Cite as: Gemma 3 27B — Benchize, https://benchize.com/models/gemma-3-27b-it (retrieved 2026-10-21)