# Llama 4 Maverick > Source: Benchize (https://benchize.com) — https://benchize.com/models/llama-4-maverick. When citing or reusing this content, credit "Benchize" and link to https://benchize.com/models/llama-4-maverick. Meta Canonical URL: https://benchize.com/models/llama-4-maverick Last updated: Wed, 21 Oct 2026 18:52:20 GMT Reproduction and quotation must name Benchize, link to the canonical HTML URL, and retain individual source citations. Meta ## Benchmarks | Benchmark | Score | ± | Rank | Cost | Source | | | --- | --- | --- | --- | --- | --- | --- | | [Arena text style control / english](https://benchize.com/benchmarks/lmarena%3Atext_style_control%3Aenglish.md) | 1,339.96 | — | 130 / 151 | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1339.9561122346147 \| rating \| reported \| Higher is better \| ### Configuration category english config text_style_control ### Reported statistics lower 1334.5779302540057 rank 259 upper 1345.334294215224 variance 7.529650262220406 votes 18914 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label Llama 4 Maverick 17B 128E Instruct Observed 2026-10-21T18:45:05.190Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/1895/row` | | | | | | | | [Slop Score](https://benchize.com/benchmarks/eq-bench%3Aslop-score.md) | 49.18% | — | 7 / 16 | — | [eq bench · slop-score](https://eqbench.com/data/leaderboard_results.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `slop_score` \| 49.17981324278487 \| percent \| official_normalized_composite \| Lower is better \| \| `slop_list_matches_per_1k_words` \| 23.733409337760076 \| matches_per_1000_words \| writing_samples \| Lower is better \| \| `slop_trigram_matches_per_1k_words` \| 1.1246600984462742 \| matches_per_1000_words \| writing_samples \| Lower is better \| \| `not_x_but_y_per_1k_chars` \| 0.1300421672616044 \| 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 meta-llama/llama-4-maverick Source version slop-score Evaluated 2025-11-01T08:47:06.231402+00:00 Observed 2026-10-21T16:35:04.972Z Evidence SHA-256 `16925b79d955a1cacef4d2ac91b696e73f976a4a3ceb45122544a9cf661b04de` Source locator `/results/13` | | | | | | | | [DesignArena Browser game generation](https://benchize.com/benchmarks/designarena%3Agame-dev.md) | 838elo | — | 116 / 117 | — | [designarena · public](https://www.designarena.ai/api/leaderboard#board=game-dev) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `elo` \| 838 \| elo \| game-dev \| Higher is better \| ### Configuration arenaType models category gamedev inputModality Not reported sourceModelVersion llama-4-maverick variationName public ### Reported statistics averageGenerationTimeMs 14339 battles 205 losses 136 standardError Not reported winRate 33.7 wins 69 ### Source [Original source](https://www.designarena.ai/api/leaderboard#board=game-dev) Source designarena Original model label Llama 4 Maverick Source version public Observed 2026-10-21T16:38:01.100Z Evidence SHA-256 `53db6a89112ce8cdf644568c666d4b8309aece764cfcedb291ffd52ae3934e30` Source locator `/data/179` | | | | | | | | [Creative Writing v3](https://benchize.com/benchmarks/eq-bench%3Acreative-writing-v3.md) | 860.1elo | — | 80 / 90 | — | [eq bench · creative-writing-v3](https://eqbench.com/creative_writing.js) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `elo_score` \| 860.1 \| elo \| overall \| Higher is better \| \| `creative_writing_score` \| 10.50 \| rubric_score \| overall \| Higher is better \| ### Configuration interactiveAdjustments none protocol creative-writing-v3 sourceModelVersion meta-llama/Llama-4-Maverick-17B-128E-Instruct ### Source [Original source](https://eqbench.com/creative_writing.js) Source eq bench Original model label meta-llama/Llama-4-Maverick-17B-128E-Instruct Source version creative-writing-v3 Observed 2026-10-21T16:35:01.421Z Evidence SHA-256 `722ddb132e8d3a5e5c39b8d445f8475f3f7e24893a007260c6f3e3cce5c1ee18` Source locator `/leaderboardDataCreativeWritingV3/123` | | | | | | | | [DistressBench](https://benchize.com/benchmarks/scale%3Adistressbench.md) | 41.25source score | CI 40.05–42.45 | 27 / 27 | — | [scale](https://labs.scale.com/leaderboard/distressbench) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `score` \| 41.25 \| source_score \| reported \| Higher is better \| ### Configuration Reasoning effort unknown Model configuration llama-4-maverick sourceModelVersion llama4-maverick-17b-instruct-v1:0 thinkingEnabled Not reported ### Reported statistics Uncertainty Confidence interval: 40.05–42.45 contaminationWarning Not reported rank 34 reportedConfidenceHalfWidth 1.2 ### Source [Original source](https://labs.scale.com/leaderboard/distressbench) Source scale Original model label llama-4-maverick Observed 2026-10-21T16:35:27.403Z Evidence SHA-256 `6ca6a76569e51fde037c8e2610bdf7bc39d99b54c69b6b4dc0dba9ec2a4e24da` Source locator `/rows/32` | | | | | | | | [ARC-AGI-2](https://benchize.com/benchmarks/arc-prize%3Av2_Semi_Private.md) | 0% | — | 200 / 212 | 0.01usd per task | [arc prize · v2](https://arcprize.org/media/data/leaderboard/v2.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `score` \| 0 \| score_fraction \| v2_Semi_Private \| Higher is better \| \| `cost_per_task` \| 0.0121 \| usd_per_task \| v2_Semi_Private \| Lower is better \| ### Configuration evaluationSplit v2_Semi_Private harness Not reported modelGroup Llama 4 modelType Base LLM sourceModelVersion Llama-4-Maverick-17B-128E-Instruct-FP8-together ### Source [Original source](https://arcprize.org/media/data/leaderboard/v2.json) Source arc prize Original model label Llama 4 Maverick Source version v2 Observed 2026-10-21T16:34:20.750Z Evidence SHA-256 `bca68e12cc9a01954ae21b641844c1ecbabe146cb24b87f0f8e9b1db27433c29` Source locator `/evaluations/15` | | | | | | | | [Arena text style control / german](https://benchize.com/benchmarks/lmarena%3Atext_style_control%3Agerman.md) | 1,331.32 | — | 100 / 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` \| 1331.3235271628687 \| rating \| reported \| Higher is better \| ### Configuration category german config text_style_control ### Reported statistics lower 1312.2981303718457 rank 189 upper 1350.3489239538917 variance 94.22611043126295 votes 1028 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label Llama 4 Maverick 17B 128E Instruct Observed 2026-10-21T18:45:05.190Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/3325/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) | 1,295.32 | — | 121 / 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` \| 1295.3242230545948 \| rating \| reported \| Higher is better \| ### Configuration category industry_entertainment_and_sports_and_media config text_style_control ### Reported statistics lower 1287.7380723093409 rank 241 upper 1302.9103737998485 variance 14.9812052701678 votes 6924 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label Llama 4 Maverick 17B 128E Instruct Observed 2026-10-21T18:45:05.190Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/4933/row` | | | | | | | | [Arena text style control / industry life and physical and social science](https://benchize.com/benchmarks/lmarena%3Atext_style_control%3Aindustry_life_and_physical_and_social_science.md) | 1,341.9 | — | 124 / 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` \| 1341.9041342214086 \| rating \| reported \| Higher is better \| ### Configuration category industry_life_and_physical_and_social_science config text_style_control ### Reported statistics lower 1334.0061894967307 rank 251 upper 1349.8020789460866 variance 16.237979836732027 votes 6714 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label Llama 4 Maverick 17B 128E Instruct Observed 2026-10-21T18:45:05.190Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/5748/row` | | | | | | | | [Arena text style control / industry software and it services](https://benchize.com/benchmarks/lmarena%3Atext_style_control%3Aindustry_software_and_it_services.md) | 1,357.97 | — | 124 / 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` \| 1357.970230084882 \| rating \| reported \| Higher is better \| ### Configuration category industry_software_and_it_services config text_style_control ### Reported statistics lower 1351.808249178879 rank 245 upper 1364.1322109908847 variance 9.884268049783204 votes 12286 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label Llama 4 Maverick 17B 128E Instruct Observed 2026-10-21T18:45:05.190Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/6945/row` | | | | | | | | [Arena vision style control / humor](https://benchize.com/benchmarks/lmarena%3Avision_style_control%3Ahumor.md) | 1,097.71 | — | 62 / 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` \| 1097.7137992426283 \| rating \| reported \| Higher is better \| ### Configuration category humor config vision_style_control ### Reported statistics lower 1057.439877290719 rank 92 upper 1137.9877211945375 variance 422.23250725759266 votes 216 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/vision_style_control/latest) Source Arena Original model label Llama 4 Maverick 17B 128E Instruct Observed 2026-10-21T18:45:05.190Z Evidence SHA-256 `38568936995f36625aae49e9ea05557d55c1b1df9b2954f5c50cee523f26fe92` Source locator `/rows/1017/row` | | | | | | | | [Arena text style control / industry mathematical](https://benchize.com/benchmarks/lmarena%3Atext_style_control%3Aindustry_mathematical.md) | 1,318.56 | — | 126 / 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` \| 1318.5634473160603 \| rating \| reported \| Higher is better \| ### Configuration category industry_mathematical config text_style_control ### Reported statistics lower 1306.9785365316495 rank 245 upper 1330.1483581004711 variance 34.937289229748124 votes 2569 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label Llama 4 Maverick 17B 128E Instruct Observed 2026-10-21T18:45:05.190Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/6157/row` | | | | | | | | [SimpleBench](https://benchize.com/benchmarks/simplebench%3Aavg-at-5.md) | 27.7% | — | 49 / 62 | — | [simplebench](https://simple-bench.com/static/js/leaderboard-data.js) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 27.7 \| percent \| average_at_5 \| Higher is better \| ### Configuration Reasoning effort unknown Model configuration Llama 4 Maverick thinkingEnabled Not reported ### Reported statistics rank 84th ### Source [Original source](https://simple-bench.com/static/js/leaderboard-data.js) Source simplebench Original model label Llama 4 Maverick Observed 2026-10-21T16:32:13.183Z Evidence SHA-256 `b2d0285ad3e4e15750ed20d39897e7558d1c05e8962e90c861b06f93c8019dc9` Source locator `/rows/85` | | | | | | | | [Arena text style control / longer query](https://benchize.com/benchmarks/lmarena%3Atext_style_control%3Alonger_query.md) | 1,335.02 | — | 124 / 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` \| 1335.0155362587811 \| rating \| reported \| Higher is better \| ### Configuration category longer_query config text_style_control ### Reported statistics lower 1327.5317624622369 rank 245 upper 1342.4993100553252 variance 14.57958365611757 votes 7073 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label Llama 4 Maverick 17B 128E Instruct Observed 2026-10-21T18:45:05.190Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/8762/row` | | | | | | | | [Humanity’s Last Exam (HLE)](https://benchize.com/benchmarks/hle.md) | 5.68source score | CI 4.77–6.59 | 13 / 17 | — | [scale](https://labs.scale.com/leaderboard/humanitys_last_exam) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `score` \| 5.68 \| source_score \| reported \| Higher is better \| ### Configuration Reasoning effort unknown Model configuration Llama 4 Maverick sourceModelVersion Not reported thinkingEnabled Not reported ### Reported statistics Uncertainty Confidence interval: 4.77–6.59 contaminationWarning Potential contamination warning: This model was evaluated after the public release of HLE, allowing model builder access to the prompts and solutions. rank 46 reportedConfidenceHalfWidth 0.91 ### Source [Original source](https://labs.scale.com/leaderboard/humanitys_last_exam) Source scale Original model label Llama 4 Maverick Observed 2026-10-21T16:35:32.694Z Evidence SHA-256 `9970bf9ee4f6b6b167633a94634adae7ac9c906447d6db087a8dc9877c1b71e0` Source locator `/rows/45` | | | | | | | | [Arena vision / humor (config: vision)](https://benchize.com/benchmarks/benchmark%3Avision%3Ahumor--config-vision.md) | 1,100.04 | — | 63 / 63 | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/vision/latest) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1100.0399205814513 \| rating \| reported \| Higher is better \| ### Configuration category humor config vision ### Reported statistics lower 1059.6193042718778 rank 93 upper 1140.4605368910247 variance 425.3140015569732 votes 216 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/vision/latest) Source Arena Original model label Llama 4 Maverick 17B 128E Instruct Observed 2026-10-21T18:45:05.190Z Evidence SHA-256 `06e61305486dce3fec5dc776ac2fd8321104e84c346cf9e08fa6f8e8a66ce0d7` Source locator `/rows/1018/row` | | | | | | | | [DesignArena 3D design generation](https://benchize.com/benchmarks/designarena%3A3d-design.md) | 901elo | — | 104 / 110 | — | [designarena · public](https://www.designarena.ai/api/leaderboard#board=3d-design) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `elo` \| 901 \| elo \| 3d-design \| Higher is better \| ### Configuration arenaType models category 3d inputModality Not reported sourceModelVersion llama-4-maverick variationName public ### Reported statistics averageGenerationTimeMs 9460 battles 164 losses 98 standardError Not reported winRate 40.2 wins 66 ### Source [Original source](https://www.designarena.ai/api/leaderboard#board=3d-design) Source designarena Original model label Llama 4 Maverick Source version public Observed 2026-10-21T16:37:58.515Z Evidence SHA-256 `bcc0267f7bc7e9ec112306b3a35413cf78bbccbfaa838356232d5d5ed0b83d0f` Source locator `/data/161` | | | | | | | | [Arena text / multi turn](https://benchize.com/benchmarks/lmarena%3Atext%3Amulti_turn.md) | 1,289.38 | — | 127 / 151 | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1289.3793109596393 \| rating \| reported \| Higher is better \| ### Configuration category multi_turn config text ### Reported statistics lower 1281.5544098244648 rank 255 upper 1297.204212094814 variance 15.939017085231418 votes 6678 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) Source Arena Original model label Llama 4 Maverick 17B 128E Instruct Observed 2026-10-21T18:45:05.190Z Evidence SHA-256 `8e027ef69b8de06c4b2a8b217bfe816b1f1536269bb257fd295b4ef1ba8246ac` Source locator `/rows/9570/row` | | | | | | | | [MultiNRC](https://benchize.com/benchmarks/scale%3Amultinrc.md) | 8.44source score | CI 6.76–10.12 | 15 / 15 | — | [scale](https://labs.scale.com/leaderboard/multinrc) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `score` \| 8.44 \| source_score \| reported \| Higher is better \| ### Configuration Reasoning effort unknown Model configuration Llama-4-Maverick sourceModelVersion Not reported thinkingEnabled Not reported ### Reported statistics Uncertainty Confidence interval: 6.76–10.12 contaminationWarning Not reported rank 44 reportedConfidenceHalfWidth 1.68 ### Source [Original source](https://labs.scale.com/leaderboard/multinrc) Source scale Original model label Llama-4-Maverick Observed 2026-10-21T16:35:36.736Z Evidence SHA-256 `a4931a13575ec92cd4993e96d4e87f8ef58149c485b7b54bb8558d7762620f8a` Source locator `/rows/43` | | | | | | | | [Arena text / korean](https://benchize.com/benchmarks/lmarena%3Atext%3Akorean.md) | 1,203.29 | — | 115 / 124 | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1203.292536501943 \| rating \| reported \| Higher is better \| ### Configuration category korean config text ### Reported statistics lower 1181.362630006146 rank 216 upper 1225.22244299774 variance 125.19223070247507 votes 796 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) Source Arena Original model label Llama 4 Maverick 17B 128E Instruct Observed 2026-10-21T18:45:05.190Z Evidence SHA-256 `8e027ef69b8de06c4b2a8b217bfe816b1f1536269bb257fd295b4ef1ba8246ac` Source locator `/rows/8449/row` | | | | | | | | [DesignArena Website generation](https://benchize.com/benchmarks/designarena%3Awebsite.md) | 871elo | — | 118 / 123 | — | [designarena · public](https://www.designarena.ai/api/leaderboard#board=website) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `elo` \| 871 \| elo \| website \| Higher is better \| ### Configuration arenaType models category website inputModality text sourceModelVersion llama-4-maverick variationName public ### Reported statistics averageGenerationTimeMs 13594 battles 1039 losses 682 standardError Not reported winRate 34.4 wins 357 ### Source [Original source](https://www.designarena.ai/api/leaderboard#board=website) Source designarena Original model label Llama 4 Maverick Source version public Observed 2026-10-21T16:37:57.757Z Evidence SHA-256 `51873e97776a3c5ae706b24cc2c60384793dd18398df970e213a8e7c276d8ac0` Source locator `/data/185` | | | | | | | | [Arena text style control / polish](https://benchize.com/benchmarks/lmarena%3Atext_style_control%3Apolish.md) | 1,330.22 | — | 102 / 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` \| 1330.222706778456 \| rating \| reported \| Higher is better \| ### Configuration category polish config text_style_control ### Reported statistics lower 1317.5417435636957 rank 193 upper 1342.9036699932165 variance 41.860875141451686 votes 2675 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label Llama 4 Maverick 17B 128E Instruct Observed 2026-10-21T18:45:05.190Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/10340/row` | | | | | | | | [Arena text style control / exclude ties](https://benchize.com/benchmarks/lmarena%3Atext_style_control%3Aexclude_ties.md) | 1,278.19 | — | 125 / 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` \| 1278.1869681318922 \| rating \| reported \| Higher is better \| ### Configuration category exclude_ties config text_style_control ### Reported statistics lower 1272.1414726884784 rank 249 upper 1284.232463575306 variance 9.51409786288775 votes 28106 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label Llama 4 Maverick 17B 128E Instruct Observed 2026-10-21T18:45:05.190Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/2302/row` | | | | | | | | [Arena vision style control / overall](https://benchize.com/benchmarks/lmarena%3Avision_style_control%3Aoverall.md) | 1,145.45 | — | 74 / 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` \| 1145.449476306153 \| rating \| reported \| Higher is better \| ### Configuration category overall config vision_style_control ### Reported statistics lower 1136.3319252937638 rank 121 upper 1154.5670273185422 variance 21.640147752123305 votes 6923 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/vision_style_control/latest) Source Arena Original model label Llama 4 Maverick 17B 128E Instruct Observed 2026-10-21T18:45:05.190Z Evidence SHA-256 `38568936995f36625aae49e9ea05557d55c1b1df9b2954f5c50cee523f26fe92` Source locator `/rows/120/row` | | | | | | | | [Arena text style control / korean](https://benchize.com/benchmarks/lmarena%3Atext_style_control%3Akorean.md) | 1,262.06 | — | 110 / 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` \| 1262.0618536010747 \| rating \| reported \| Higher is better \| ### Configuration category korean config text_style_control ### Reported statistics lower 1240.137622026697 rank 211 upper 1283.986085175452 variance 125.1274457342937 votes 796 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label Llama 4 Maverick 17B 128E Instruct Observed 2026-10-21T18:45:05.190Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/8444/row` | | | | | | | | [Spiral-Bench v1.2](https://benchize.com/benchmarks/eq-bench%3Aspiral-bench-v1.2.md) | 38.2% | CI 38.2–38.2% | 8 / 16 | — | [eq bench · spiral-bench-v1.2](https://eqbench.com/spiral-bench.js) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `score_norm` \| 38.2 \| percent \| overall \| Higher is better \| ### Configuration interactiveAdjustments none protocol spiral-bench-v1.2 sourceModelVersion llama-4-maverick ### Reported statistics Uncertainty Confidence interval: 38.2–38.2% confidenceIntervalHigh 38.2 confidenceIntervalLow 38.2 ### Source [Original source](https://eqbench.com/spiral-bench.js) Source eq bench Original model label llama-4-maverick Source version spiral-bench-v1.2 Observed 2026-10-21T16:35:04.308Z Evidence SHA-256 `2f0402654b01e7363c0d02bbc708afd7849e669dc5da63d9f85c995ed8f0a97f` Source locator `/leaderboardDataDelusion/14` | | | | | | | | [Arena text / russian](https://benchize.com/benchmarks/lmarena%3Atext%3Arussian.md) | 1,286.01 | — | 126 / 150 | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1286.0114955329398 \| rating \| reported \| Higher is better \| ### Configuration category russian config text ### Reported statistics lower 1275.5863190558164 rank 242 upper 1296.436672010063 variance 28.29245597887894 votes 3104 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) Source Arena Original model label Llama 4 Maverick 17B 128E Instruct Observed 2026-10-21T18:45:05.190Z Evidence SHA-256 `8e027ef69b8de06c4b2a8b217bfe816b1f1536269bb257fd295b4ef1ba8246ac` Source locator `/rows/10625/row` | | | | | | | | [Arena text style control / math](https://benchize.com/benchmarks/lmarena%3Atext_style_control%3Amath.md) | 1,316.68 | — | 125 / 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` \| 1316.683164925002 \| rating \| reported \| Higher is better \| ### Configuration category math config text_style_control ### Reported statistics lower 1305.806771784604 rank 235 upper 1327.5595580653999 variance 30.794532302996124 votes 2825 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label Llama 4 Maverick 17B 128E Instruct Observed 2026-10-21T18:45:05.190Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/9147/row` | | | | | | | | [Humanity's Last Exam Text Only (Preview)](https://benchize.com/benchmarks/scale%3Ahumanitys_last_exam_text_only_preview.md) | 6.24source score | CI 5.27–7.21 | 3 / 9 | — | [scale](https://labs.scale.com/leaderboard/humanitys_last_exam_text_only_preview) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `score` \| 6.24 \| source_score \| reported \| Higher is better \| ### Configuration Reasoning effort unknown Model configuration Llama 4 Maverick sourceModelVersion Not reported thinkingEnabled Not reported ### Reported statistics Uncertainty Confidence interval: 5.27–7.21 contaminationWarning Potential contamination warning: This model was evaluated after the public release of HLE, allowing model builder access to the prompts and solutions. rank 11 reportedConfidenceHalfWidth 0.97 ### Source [Original source](https://labs.scale.com/leaderboard/humanitys_last_exam_text_only_preview) Source scale Original model label Llama 4 Maverick Observed 2026-10-21T16:35:41.566Z Evidence SHA-256 `4d23bf746c160370d6a729032cb829dd9d2b40f12bad31ca5723d121464988b7` Source locator `/rows/10` | | | | | | | | [Arena text / coding](https://benchize.com/benchmarks/lmarena%3Atext%3Acoding.md) | 1,301.34 | — | 128 / 151 | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1301.3421728478017 \| rating \| reported \| Higher is better \| ### Configuration category coding config text ### Reported statistics lower 1293.8846898030906 rank 258 upper 1308.7996558925129 variance 14.477326442381234 votes 6939 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) Source Arena Original model label Llama 4 Maverick 17B 128E Instruct Observed 2026-10-21T18:45:05.190Z Evidence SHA-256 `8e027ef69b8de06c4b2a8b217bfe816b1f1536269bb257fd295b4ef1ba8246ac` Source locator `/rows/1067/row` | | | | | | | | [Arena text style control / hard prompts english](https://benchize.com/benchmarks/lmarena%3Atext_style_control%3Ahard_prompts_english.md) | 1,350.63 | — | 126 / 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` \| 1350.6339390513942 \| rating \| reported \| Higher is better \| ### Configuration category hard_prompts_english config text_style_control ### Reported statistics lower 1343.3350868236848 rank 250 upper 1357.9327912791036 variance 13.867972124275122 votes 7690 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label Llama 4 Maverick 17B 128E Instruct Observed 2026-10-21T18:45:05.190Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/4117/row` | | | | | | | | [DesignArena Overall frontend coding](https://benchize.com/benchmarks/designarena%3Acode.md) | 880elo | SE ±9.41 | 114 / 116 | — | [designarena · public](https://www.designarena.ai/api/leaderboard#board=code) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `elo` \| 880 \| elo \| code \| Higher is better \| ### Configuration arenaType models category allcategories inputModality text sourceModelVersion llama-4-maverick variationName public ### Reported statistics Uncertainty Standard error: ±9.41 averageGenerationTimeMs 13055 battles 1678 losses 1078 standardError 9.413 winRate 35.8 wins 600 ### Source [Original source](https://www.designarena.ai/api/leaderboard#board=code) Source designarena Original model label Llama 4 Maverick Source version public Observed 2026-10-21T16:37:57.301Z Evidence SHA-256 `0c897b58670f5e352bd123db999a40c0d1781a443964c502b90774a76a3a7758` Source locator `/data/177` | | | | | | | | [Arena vision style control / ocr](https://benchize.com/benchmarks/lmarena%3Avision_style_control%3Aocr.md) | 1,153.13 | — | 72 / 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` \| 1153.1256553740561 \| rating \| reported \| Higher is better \| ### Configuration category ocr config vision_style_control ### Reported statistics lower 1141.3304137383604 rank 115 upper 1164.9208970097518 variance 36.217419407169245 votes 3083 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/vision_style_control/latest) Source Arena Original model label Llama 4 Maverick 17B 128E Instruct Observed 2026-10-21T18:45:05.190Z Evidence SHA-256 `38568936995f36625aae49e9ea05557d55c1b1df9b2954f5c50cee523f26fe92` Source locator `/rows/1133/row` | | | | | | | | [Arena text / industry business and management and financial operations](https://benchize.com/benchmarks/lmarena%3Atext%3Aindustry_business_and_management_and_financial_operations.md) | 1,260.47 | — | 134 / 151 | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1260.4710036333677 \| rating \| reported \| Higher is better \| ### Configuration category industry_business_and_management_and_financial_operations config text ### Reported statistics lower 1252.3543594727248 rank 263 upper 1268.58764779401 variance 17.149711998888435 votes 6123 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) Source Arena Original model label Llama 4 Maverick 17B 128E Instruct Observed 2026-10-21T18:45:05.190Z Evidence SHA-256 `8e027ef69b8de06c4b2a8b217bfe816b1f1536269bb257fd295b4ef1ba8246ac` Source locator `/rows/4545/row` | | | | | | | | [Arena vision style control / chinese](https://benchize.com/benchmarks/lmarena%3Avision_style_control%3Achinese.md) | 1,147.33 | — | 67 / 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` \| 1147.3298418407862 \| rating \| reported \| Higher is better \| ### Configuration category chinese config vision_style_control ### Reported statistics lower 1112.8131741728698 rank 103 upper 1181.8465095087026 variance 310.1426834199691 votes 294 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/vision_style_control/latest) Source Arena Original model label Llama 4 Maverick 17B 128E Instruct Observed 2026-10-21T18:45:05.190Z Evidence SHA-256 `38568936995f36625aae49e9ea05557d55c1b1df9b2954f5c50cee523f26fe92` Source locator `/rows/303/row` | | | | | | | | [Arena text style control / industry medicine and healthcare](https://benchize.com/benchmarks/lmarena%3Atext_style_control%3Aindustry_medicine_and_healthcare.md) | 1,344.37 | — | 123 / 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` \| 1344.3736273509353 \| rating \| reported \| Higher is better \| ### Configuration category industry_medicine_and_healthcare config text_style_control ### Reported statistics lower 1331.1225712564055 rank 240 upper 1357.6246834454653 variance 45.70932445623638 votes 2292 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label Llama 4 Maverick 17B 128E Instruct Observed 2026-10-21T18:45:05.190Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/6552/row` | | | | | | | | [Arena vision / creative writing vision (config: vision)](https://benchize.com/benchmarks/benchmark%3Avision%3Acreative_writing_vision--config-vision.md) | 1,099.04 | — | 70 / 70 | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/vision/latest) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1099.0434373975943 \| rating \| reported \| Higher is better \| ### Configuration category creative_writing_vision config vision ### Reported statistics lower 1056.3253806798286 rank 104 upper 1141.76149411536 variance 475.0362960841295 votes 214 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/vision/latest) Source Arena Original model label Llama 4 Maverick 17B 128E Instruct Observed 2026-10-21T18:45:05.190Z Evidence SHA-256 `06e61305486dce3fec5dc776ac2fd8321104e84c346cf9e08fa6f8e8a66ce0d7` Source locator `/rows/466/row` | | | | | | | | [Arena text / industry writing and literature and language](https://benchize.com/benchmarks/lmarena%3Atext%3Aindustry_writing_and_literature_and_language.md) | 1,277.24 | — | 132 / 151 | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1277.24399095494 \| rating \| reported \| Higher is better \| ### Configuration category industry_writing_and_literature_and_language config text ### Reported statistics lower 1270.3518129969304 rank 258 upper 1284.1361689129499 variance 12.365645246274287 votes 8727 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) Source Arena Original model label Llama 4 Maverick 17B 128E Instruct Observed 2026-10-21T18:45:05.190Z Evidence SHA-256 `8e027ef69b8de06c4b2a8b217bfe816b1f1536269bb257fd295b4ef1ba8246ac` Source locator `/rows/7375/row` | | | | | | | | [Arena vision / english (config: vision)](https://benchize.com/benchmarks/benchmark%3Avision%3Aenglish--config-vision.md) | 1,149.99 | — | 75 / 82 | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/vision/latest) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1149.9864262416813 \| rating \| reported \| Higher is better \| ### Configuration category english config vision ### Reported statistics lower 1138.2677477934112 rank 123 upper 1161.7051046899514 variance 35.74876914836653 votes 3387 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/vision/latest) Source Arena Original model label Llama 4 Maverick 17B 128E Instruct Observed 2026-10-21T18:45:05.190Z Evidence SHA-256 `06e61305486dce3fec5dc776ac2fd8321104e84c346cf9e08fa6f8e8a66ce0d7` Source locator `/rows/712/row` | | | | | | | | [Arena text style control / hard prompts](https://benchize.com/benchmarks/lmarena%3Atext_style_control%3Ahard_prompts.md) | 1,338.51 | — | 124 / 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` \| 1338.514368720665 \| rating \| reported \| Higher is better \| ### Configuration category hard_prompts config text_style_control ### Reported statistics lower 1332.7934679547725 rank 245 upper 1344.2352694865572 variance 8.519863703048712 votes 15865 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label Llama 4 Maverick 17B 128E Instruct Observed 2026-10-21T18:45:05.190Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/3695/row` | | | | | | | | [DesignArena UI component generation](https://benchize.com/benchmarks/designarena%3Aui-components.md) | 899elo | — | 109 / 112 | — | [designarena · public](https://www.designarena.ai/api/leaderboard#board=ui-components) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `elo` \| 899 \| elo \| ui-components \| Higher is better \| ### Configuration arenaType models category uicomponent inputModality Not reported sourceModelVersion llama-4-maverick variationName public ### Reported statistics averageGenerationTimeMs 12741 battles 184 losses 109 standardError Not reported winRate 40.8 wins 75 ### Source [Original source](https://www.designarena.ai/api/leaderboard#board=ui-components) Source designarena Original model label Llama 4 Maverick Source version public Observed 2026-10-21T16:37:57.993Z Evidence SHA-256 `46482ec1b4012638eace65493daea4750e2088098018fd9d5fc46126fc1f8557` Source locator `/data/167` | | | | | | | | [Arena text style control / multi turn](https://benchize.com/benchmarks/lmarena%3Atext_style_control%3Amulti_turn.md) | 1,326.41 | — | 123 / 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` \| 1326.4119261655976 \| rating \| reported \| Higher is better \| ### Configuration category multi_turn config text_style_control ### Reported statistics lower 1318.5649256009215 rank 242 upper 1334.2589267302735 variance 16.02917556484392 votes 6678 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label Llama 4 Maverick 17B 128E Instruct Observed 2026-10-21T18:45:05.190Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/9557/row` | | | | | | | | [Arena text / longer query](https://benchize.com/benchmarks/lmarena%3Atext%3Alonger_query.md) | 1,279.69 | — | 134 / 150 | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1279.6912048400898 \| rating \| reported \| Higher is better \| ### Configuration category longer_query config text ### Reported statistics lower 1272.2454649351434 rank 267 upper 1287.136944745036 variance 14.43176806515733 votes 7073 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) Source Arena Original model label Llama 4 Maverick 17B 128E Instruct Observed 2026-10-21T18:45:05.190Z Evidence SHA-256 `8e027ef69b8de06c4b2a8b217bfe816b1f1536269bb257fd295b4ef1ba8246ac` Source locator `/rows/8784/row` | | | | | | | | [Arena text style control / instruction following](https://benchize.com/benchmarks/lmarena%3Atext_style_control%3Ainstruction_following.md) | 1,313.62 | — | 126 / 151 | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1313.6157730182144 \| rating \| reported \| Higher is better \| ### Configuration category instruction_following config text_style_control ### Reported statistics lower 1307.1443179256808 rank 251 upper 1320.0872281107481 variance 10.902038254079992 votes 10499 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label Llama 4 Maverick 17B 128E Instruct Observed 2026-10-21T18:45:05.190Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/7784/row` | | | | | | | | [Arena text / industry legal and government](https://benchize.com/benchmarks/lmarena%3Atext%3Aindustry_legal_and_government.md) | 1,285.72 | — | 134 / 151 | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1285.7223811851059 \| rating \| reported \| Higher is better \| ### Configuration category industry_legal_and_government config text ### Reported statistics lower 1273.591562074347 rank 263 upper 1297.8532002958648 variance 38.30752304442599 votes 2582 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) Source Arena Original model label Llama 4 Maverick 17B 128E Instruct Observed 2026-10-21T18:45:05.190Z Evidence SHA-256 `8e027ef69b8de06c4b2a8b217bfe816b1f1536269bb257fd295b4ef1ba8246ac` Source locator `/rows/5370/row` | | | | | | | | [Arena text / japanese](https://benchize.com/benchmarks/lmarena%3Atext%3Ajapanese.md) | 1,206.31 | — | 110 / 120 | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1206.3054731567734 \| rating \| reported \| Higher is better \| ### Configuration category japanese config text ### Reported statistics lower 1185.0841694422309 rank 210 upper 1227.5267768713159 variance 117.23247660988312 votes 935 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) Source Arena Original model label Llama 4 Maverick 17B 128E Instruct Observed 2026-10-21T18:45:05.190Z Evidence SHA-256 `8e027ef69b8de06c4b2a8b217bfe816b1f1536269bb257fd295b4ef1ba8246ac` Source locator `/rows/8160/row` | | | | | | | | [Arena text style control / chinese](https://benchize.com/benchmarks/lmarena%3Atext_style_control%3Achinese.md) | 1,333.98 | — | 125 / 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` \| 1333.983440142418 \| rating \| reported \| Higher is better \| ### Configuration category chinese config text_style_control ### Reported statistics lower 1321.7366167925884 rank 249 upper 1346.2302634922473 variance 39.043678238577634 votes 2597 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label Llama 4 Maverick 17B 128E Instruct Observed 2026-10-21T18:45:05.190Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/665/row` | | | | | | | | [Humanity's Last Exam (Text Only)](https://benchize.com/benchmarks/scale%3Ahumanitys_last_exam_text_only.md) | 5.34source score | CI 4.39–6.29 | 22 / 25 | — | [scale](https://labs.scale.com/leaderboard/humanitys_last_exam_text_only) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `score` \| 5.34 \| source_score \| reported \| Higher is better \| ### Configuration Reasoning effort unknown Model configuration Llama 4 Maverick sourceModelVersion Not reported thinkingEnabled Not reported ### Reported statistics Uncertainty Confidence interval: 4.39–6.29 contaminationWarning Potential contamination warning: This model was evaluated after the public release of HLE, allowing model builder access to the prompts and solutions. rank 55 reportedConfidenceHalfWidth 0.95 ### Source [Original source](https://labs.scale.com/leaderboard/humanitys_last_exam_text_only) Source scale Original model label Llama 4 Maverick Observed 2026-10-21T16:35:33.193Z Evidence SHA-256 `4004825ae58bdcc249c0d26dab811842c6d172b2a67bc35e69949fbf12ead757` Source locator `/rows/54` | | | | | | | | [Arena text / non english](https://benchize.com/benchmarks/lmarena%3Atext%3Anon_english.md) | 1,269.07 | — | 130 / 151 | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1269.0741768583582 \| rating \| reported \| Higher is better \| ### Configuration category non_english config text ### Reported statistics lower 1263.822171246057 rank 256 upper 1274.3261824706592 variance 7.180491641104903 votes 20518 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) Source Arena Original model label Llama 4 Maverick 17B 128E Instruct Observed 2026-10-21T18:45:05.190Z Evidence SHA-256 `8e027ef69b8de06c4b2a8b217bfe816b1f1536269bb257fd295b4ef1ba8246ac` Source locator `/rows/9986/row` | | | | | | | | [Humanity's Last Exam (Preview)](https://benchize.com/benchmarks/scale%3Ahumanitys_last_exam_preview.md) | 6.78source score | CI 5.83–7.73 | 2 / 6 | — | [scale](https://labs.scale.com/leaderboard/humanitys_last_exam_preview) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `score` \| 6.78 \| source_score \| reported \| Higher is better \| ### Configuration Reasoning effort unknown Model configuration Llama 4 Maverick sourceModelVersion Not reported thinkingEnabled Not reported ### Reported statistics Uncertainty Confidence interval: 5.83–7.73 contaminationWarning Potential contamination warning: This model was evaluated after the public release of HLE, allowing model builder access to the prompts and solutions. rank 7 reportedConfidenceHalfWidth 0.95 ### Source [Original source](https://labs.scale.com/leaderboard/humanitys_last_exam_preview) Source scale Original model label Llama 4 Maverick Observed 2026-10-21T16:35:41.114Z Evidence SHA-256 `cc993dfe2ce4fc1640be10f28c7c8ab5c1db9071f780ac20ed11dd4f026105a5` Source locator `/rows/6` | | | | | | | | [Arena text / industry life and physical and social science](https://benchize.com/benchmarks/lmarena%3Atext%3Aindustry_life_and_physical_and_social_science.md) | 1,287.61 | — | 133 / 151 | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1287.6064692765926 \| rating \| reported \| Higher is better \| ### Configuration category industry_life_and_physical_and_social_science config text ### Reported statistics lower 1279.7430009662198 rank 267 upper 1295.4699375869657 variance 16.096523939065683 votes 6714 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) Source Arena Original model label Llama 4 Maverick 17B 128E Instruct Observed 2026-10-21T18:45:05.190Z Evidence SHA-256 `8e027ef69b8de06c4b2a8b217bfe816b1f1536269bb257fd295b4ef1ba8246ac` Source locator `/rows/5764/row` | | | | | | | | [Fortress](https://benchize.com/benchmarks/scale%3Afortress.md) | 40.09source score | CI 36.73–43.45 | 11 / 31 | — | [scale](https://labs.scale.com/leaderboard/fortress) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `score` \| 40.09 \| source_score \| reported \| Higher is better \| ### Configuration Reasoning effort unknown Model configuration Llama 4 Maverick sourceModelVersion Not reported thinkingEnabled Not reported ### Reported statistics Uncertainty Confidence interval: 36.73–43.45 contaminationWarning ORS score: 4.95 rank 50 reportedConfidenceHalfWidth 3.36 ### Source [Original source](https://labs.scale.com/leaderboard/fortress) Source scale Original model label Llama 4 Maverick Observed 2026-10-21T16:35:37.552Z Evidence SHA-256 `875f1c5b1112c4b84f3d17df72771ebee5c293c542cbb8ab3399e35c4f82ffa5` Source locator `/rows/49` | | | | | | | | [Arena text / english](https://benchize.com/benchmarks/lmarena%3Atext%3Aenglish.md) | 1,302.53 | — | 133 / 151 | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1302.5329881443236 \| rating \| reported \| Higher is better \| ### Configuration category english config text ### Reported statistics lower 1297.1931418471706 rank 266 upper 1307.8728344414762 variance 7.42269013105393 votes 18914 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) Source Arena Original model label Llama 4 Maverick 17B 128E Instruct Observed 2026-10-21T18:45:05.190Z Evidence SHA-256 `8e027ef69b8de06c4b2a8b217bfe816b1f1536269bb257fd295b4ef1ba8246ac` Source locator `/rows/1902/row` | | | | | | | | [Arena text / industry medicine and healthcare](https://benchize.com/benchmarks/lmarena%3Atext%3Aindustry_medicine_and_healthcare.md) | 1,275.42 | — | 134 / 151 | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1275.4237958120168 \| rating \| reported \| Higher is better \| ### Configuration category industry_medicine_and_healthcare config text ### Reported statistics lower 1262.219598879094 rank 260 upper 1288.6279927449395 variance 45.386616069960866 votes 2292 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) Source Arena Original model label Llama 4 Maverick 17B 128E Instruct Observed 2026-10-21T18:45:05.190Z Evidence SHA-256 `8e027ef69b8de06c4b2a8b217bfe816b1f1536269bb257fd295b4ef1ba8246ac` Source locator `/rows/6572/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) | 1,312.14 | — | 121 / 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` \| 1312.1375735832526 \| rating \| reported \| Higher is better \| ### Configuration category industry_writing_and_literature_and_language config text_style_control ### Reported statistics lower 1305.2015839382855 rank 240 upper 1319.0735632282197 variance 12.523354954615122 votes 8727 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label Llama 4 Maverick 17B 128E Instruct Observed 2026-10-21T18:45:05.190Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/7357/row` | | | | | | | | [Arena text style control / industry business and management and financial operations](https://benchize.com/benchmarks/lmarena%3Atext_style_control%3Aindustry_business_and_management_and_financial_operations.md) | 1,317.22 | — | 129 / 151 | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1317.2246634301127 \| rating \| reported \| Higher is better \| ### Configuration category industry_business_and_management_and_financial_operations config text_style_control ### Reported statistics lower 1309.0906367790215 rank 254 upper 1325.3586900812043 variance 17.223245815950424 votes 6123 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label Llama 4 Maverick 17B 128E Instruct Observed 2026-10-21T18:45:05.190Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/4536/row` | | | | | | | | [Arena text / exclude ties](https://benchize.com/benchmarks/lmarena%3Atext%3Aexclude_ties.md) | 1,220.53 | — | 132 / 151 | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1220.5259035997408 \| rating \| reported \| Higher is better \| ### Configuration category exclude_ties config text ### Reported statistics lower 1214.5745944303846 rank 260 upper 1226.477212769097 variance 9.219955876778743 votes 28106 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) Source Arena Original model label Llama 4 Maverick 17B 128E Instruct Observed 2026-10-21T18:45:05.190Z Evidence SHA-256 `8e027ef69b8de06c4b2a8b217bfe816b1f1536269bb257fd295b4ef1ba8246ac` Source locator `/rows/2313/row` | | | | | | | | [Arena text style control / industry legal and government](https://benchize.com/benchmarks/lmarena%3Atext_style_control%3Aindustry_legal_and_government.md) | 1,341.07 | — | 124 / 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` \| 1341.0663687626916 \| rating \| reported \| Higher is better \| ### Configuration category industry_legal_and_government config text_style_control ### Reported statistics lower 1328.924248388577 rank 240 upper 1353.208489136806 variance 38.378932083110605 votes 2582 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label Llama 4 Maverick 17B 128E Instruct Observed 2026-10-21T18:45:05.190Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/5347/row` | | | | | | | | [Arena text / german](https://benchize.com/benchmarks/lmarena%3Atext%3Agerman.md) | 1,291.17 | — | 106 / 129 | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1291.165944348941 \| rating \| reported \| Higher is better \| ### Configuration category german config text ### Reported statistics lower 1272.165945734725 rank 200 upper 1310.1659429631568 variance 93.97470184906992 votes 1028 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) Source Arena Original model label Llama 4 Maverick 17B 128E Instruct Observed 2026-10-21T18:45:05.190Z Evidence SHA-256 `8e027ef69b8de06c4b2a8b217bfe816b1f1536269bb257fd295b4ef1ba8246ac` Source locator `/rows/3336/row` | | | | | | | | [Arena text / polish](https://benchize.com/benchmarks/lmarena%3Atext%3Apolish.md) | 1,275.23 | — | 109 / 117 | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1275.231467754459 \| rating \| reported \| Higher is better \| ### Configuration category polish config text ### Reported statistics lower 1262.7008951266946 rank 210 upper 1287.7620403822234 variance 40.873860090293675 votes 2675 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) Source Arena Original model label Llama 4 Maverick 17B 128E Instruct Observed 2026-10-21T18:45:05.190Z Evidence SHA-256 `8e027ef69b8de06c4b2a8b217bfe816b1f1536269bb257fd295b4ef1ba8246ac` Source locator `/rows/10357/row` | | | | | | | | [Arena vision style control / homework](https://benchize.com/benchmarks/lmarena%3Avision_style_control%3Ahomework.md) | 1,164.7 | — | 71 / 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` \| 1164.7017828401313 \| rating \| reported \| Higher is better \| ### Configuration category homework config vision_style_control ### Reported statistics lower 1139.4239191542756 rank 111 upper 1189.979646525987 variance 166.33534871662147 votes 526 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/vision_style_control/latest) Source Arena Original model label Llama 4 Maverick 17B 128E Instruct Observed 2026-10-21T18:45:05.190Z Evidence SHA-256 `38568936995f36625aae49e9ea05557d55c1b1df9b2954f5c50cee523f26fe92` Source locator `/rows/918/row` | | | | | | | | [Arena text / creative writing](https://benchize.com/benchmarks/lmarena%3Atext%3Acreative_writing.md) | 1,266.13 | — | 130 / 151 | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1266.1310231935936 \| rating \| reported \| Higher is better \| ### Configuration category creative_writing config text ### Reported statistics lower 1257.5846038715913 rank 255 upper 1274.6774425155957 variance 19.013944086557775 votes 5152 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) Source Arena Original model label Llama 4 Maverick 17B 128E Instruct Observed 2026-10-21T18:45:05.190Z Evidence SHA-256 `8e027ef69b8de06c4b2a8b217bfe816b1f1536269bb257fd295b4ef1ba8246ac` Source locator `/rows/1476/row` | | | | | | | | [Longform Creative Writing](https://benchize.com/benchmarks/eq-bench%3Alongform-writing.md) | 31.9% | — | 88 / 93 | — | [eq bench · longform-writing](https://eqbench.com/creative_writing_longform.js) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `overall_score_100` \| 31.9 \| percent \| overall \| Higher is better \| \| `chapter1_avg` \| 8.02 \| rubric_score \| overall \| Higher is better \| \| `chapter2_avg` \| 8.00 \| rubric_score \| overall \| Higher is better \| \| `chapter3_avg` \| 6.94 \| rubric_score \| overall \| Higher is better \| \| `chapter4_avg` \| 6.30 \| rubric_score \| overall \| Higher is better \| \| `chapter5_avg` \| 6.43 \| rubric_score \| overall \| Higher is better \| \| `chapter6_avg` \| 6.28 \| rubric_score \| overall \| Higher is better \| \| `chapter7_avg` \| 5.57 \| rubric_score \| overall \| Higher is better \| \| `chapter8_avg` \| 4.40 \| rubric_score \| overall \| Higher is better \| \| `final_judgement_avg` \| 5.26 \| rubric_score \| overall \| Higher is better \| ### Configuration interactiveAdjustments none protocol longform-writing sourceModelVersion meta-llama/Llama-4-Maverick-17B-128E-Instruct ### Source [Original source](https://eqbench.com/creative_writing_longform.js) Source eq bench Original model label meta-llama/Llama-4-Maverick-17B-128E-Instruct Source version longform-writing Observed 2026-10-21T16:35:02.575Z Evidence SHA-256 `3ba283ce357ac7620e16db640a961879c30fe3ddc50a27de9a8ed4290784825c` Source locator `/leaderboardDataLongformV3/78` | | | | | | | | [Arena vision style control / creative writing vision](https://benchize.com/benchmarks/lmarena%3Avision_style_control%3Acreative_writing_vision.md) | 1,110.98 | — | 69 / 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` \| 1110.9755984756027 \| rating \| reported \| Higher is better \| ### Configuration category creative_writing_vision config vision_style_control ### Reported statistics lower 1068.4187982296735 rank 102 upper 1153.532398721532 variance 471.45663449925365 votes 214 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/vision_style_control/latest) Source Arena Original model label Llama 4 Maverick 17B 128E Instruct Observed 2026-10-21T18:45:05.190Z Evidence SHA-256 `38568936995f36625aae49e9ea05557d55c1b1df9b2954f5c50cee523f26fe92` Source locator `/rows/464/row` | | | | | | | | [Arena vision / diagram (config: vision)](https://benchize.com/benchmarks/benchmark%3Avision%3Adiagram--config-vision.md) | 1,133.52 | — | 72 / 74 | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/vision/latest) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1133.5211210518692 \| rating \| reported \| Higher is better \| ### Configuration category diagram config vision ### Reported statistics lower 1114.2388623948705 rank 118 upper 1152.8033797088679 variance 96.7875789563237 votes 947 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/vision/latest) Source Arena Original model label Llama 4 Maverick 17B 128E Instruct Observed 2026-10-21T18:45:05.190Z Evidence SHA-256 `06e61305486dce3fec5dc776ac2fd8321104e84c346cf9e08fa6f8e8a66ce0d7` Source locator `/rows/584/row` | | | | | | | | [EQ-Bench 3](https://benchize.com/benchmarks/eq-bench%3Aeqbench3.md) | 806.8elo | CI 780.4–833.2 | 46 / 50 | — | [eq bench · eqbench3](https://eqbench.com/eqbench3.js) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `elo_norm` \| 806.8 \| elo \| overall \| Higher is better \| \| `rubric_0_100` \| 36.3 \| percent \| overall \| Higher is better \| ### Configuration interactiveAdjustments none protocol eqbench3 sourceModelVersion meta-llama/Llama-4-Maverick-17B-128E-Instruct ### Reported statistics Uncertainty Confidence interval: 780.4–833.2 confidenceIntervalHigh 833.2 confidenceIntervalLow 780.4 ### Source [Original source](https://eqbench.com/eqbench3.js) Source eq bench Original model label meta-llama/Llama-4-Maverick-17B-128E-Instruct Source version eqbench3 Observed 2026-10-21T16:35:00.608Z Evidence SHA-256 `3672ff093e739f07ff664a2e6013bc38a6977a146e4092b4cef80ba1780542b2` Source locator `/leaderboardDataEQBench3/70` | | | | | | | | [ARC-AGI-1](https://benchize.com/benchmarks/arc-prize%3Av1_Semi_Private.md) | 4.38% | — | 208 / 213 | 0.0078usd per task | [arc prize · v1](https://arcprize.org/media/data/leaderboard/v1.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `score` \| 0.0438 \| score_fraction \| v1_Semi_Private \| Higher is better \| \| `cost_per_task` \| 0.0078 \| usd_per_task \| v1_Semi_Private \| Lower is better \| ### Configuration evaluationSplit v1_Semi_Private harness Not reported modelGroup Llama 4 modelType Base LLM sourceModelVersion Llama-4-Maverick-17B-128E-Instruct-FP8-together ### Source [Original source](https://arcprize.org/media/data/leaderboard/v1.json) Source arc prize Original model label Llama 4 Maverick Source version v1 Observed 2026-10-21T16:34:20.378Z Evidence SHA-256 `302d8267c0522bf450ec1deeac4d060e2cf2fb444ba0a4269014d9535de0bd1f` Source locator `/evaluations/13` | | | | | | | | [Arena vision / ocr (config: vision)](https://benchize.com/benchmarks/benchmark%3Avision%3Aocr--config-vision.md) | 1,142.94 | — | 72 / 74 | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/vision/latest) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1142.9432053739358 \| rating \| reported \| Higher is better \| ### Configuration category ocr config vision ### Reported statistics lower 1131.2010191492632 rank 117 upper 1154.6853915986085 variance 35.8923377213191 votes 3083 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/vision/latest) Source Arena Original model label Llama 4 Maverick 17B 128E Instruct Observed 2026-10-21T18:45:05.190Z Evidence SHA-256 `06e61305486dce3fec5dc776ac2fd8321104e84c346cf9e08fa6f8e8a66ce0d7` Source locator `/rows/1135/row` | | | | | | | | [Arena text style control / non english](https://benchize.com/benchmarks/lmarena%3Atext_style_control%3Anon_english.md) | 1,311.04 | — | 126 / 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` \| 1311.0357633343178 \| rating \| reported \| Higher is better \| ### Configuration category non_english config text_style_control ### Reported statistics lower 1305.7675047968617 rank 243 upper 1316.304021871774 variance 7.2250020924250045 votes 20518 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label Llama 4 Maverick 17B 128E Instruct Observed 2026-10-21T18:45:05.190Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/9973/row` | | | | | | | | [Arena vision / homework (config: vision)](https://benchize.com/benchmarks/benchmark%3Avision%3Ahomework--config-vision.md) | 1,164.18 | — | 69 / 73 | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/vision/latest) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1164.1770917372469 \| rating \| reported \| Higher is better \| ### Configuration category homework config vision ### Reported statistics lower 1139.0143485294036 rank 108 upper 1189.3398349450902 variance 164.8237493352731 votes 526 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/vision/latest) Source Arena Original model label Llama 4 Maverick 17B 128E Instruct Observed 2026-10-21T18:45:05.190Z Evidence SHA-256 `06e61305486dce3fec5dc776ac2fd8321104e84c346cf9e08fa6f8e8a66ce0d7` Source locator `/rows/915/row` | | | | | | | | [Arena text style control / japanese](https://benchize.com/benchmarks/lmarena%3Atext_style_control%3Ajapanese.md) | 1,257.32 | — | 103 / 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` \| 1257.3193035198142 \| rating \| reported \| Higher is better \| ### Configuration category japanese config text_style_control ### Reported statistics lower 1236.1158363762672 rank 193 upper 1278.522770663361 variance 117.0354909144208 votes 935 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label Llama 4 Maverick 17B 128E Instruct Observed 2026-10-21T18:45:05.190Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/8143/row` | | | | | | | | [MASK](https://benchize.com/benchmarks/scale%3Amask.md) | 49.73source score | CI 48.13–51.33 | 17 / 25 | — | [scale](https://labs.scale.com/leaderboard/mask) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `score` \| 49.73 \| source_score \| reported \| Higher is better \| ### Configuration Reasoning effort unknown Model configuration Llama 4 Maverick sourceModelVersion llama-4-17b-omni-instruct-fp8-128e-final-vllm thinkingEnabled Not reported ### Reported statistics Uncertainty Confidence interval: 48.13–51.33 contaminationWarning Not reported rank 52 reportedConfidenceHalfWidth 1.6 ### Source [Original source](https://labs.scale.com/leaderboard/mask) Source scale Original model label Llama 4 Maverick Observed 2026-10-21T16:35:38.046Z Evidence SHA-256 `506198f10b9789b267cc2a11dcdfedc27067703da430d78b374b2c5dffb8ec7d` Source locator `/rows/51` | | | | | | | | [Arena text / math](https://benchize.com/benchmarks/lmarena%3Atext%3Amath.md) | 1,299.33 | — | 127 / 149 | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1299.331322868639 \| rating \| reported \| Higher is better \| ### Configuration category math config text ### Reported statistics lower 1288.5182302988103 rank 243 upper 1310.1444154384678 variance 30.437127242863138 votes 2825 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) Source Arena Original model label Llama 4 Maverick 17B 128E Instruct Observed 2026-10-21T18:45:05.190Z Evidence SHA-256 `8e027ef69b8de06c4b2a8b217bfe816b1f1536269bb257fd295b4ef1ba8246ac` Source locator `/rows/9155/row` | | | | | | | | [Arena text style control / french](https://benchize.com/benchmarks/lmarena%3Atext_style_control%3Afrench.md) | 1,298.79 | — | 127 / 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` \| 1298.7866076493115 \| rating \| reported \| Higher is better \| ### Configuration category french config text_style_control ### Reported statistics lower 1273.2914576189946 rank 243 upper 1324.2817576796283 variance 169.20724792538897 votes 597 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label Llama 4 Maverick 17B 128E Instruct Observed 2026-10-21T18:45:05.190Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/3080/row` | | | | | | | | [Arena text / hard prompts english](https://benchize.com/benchmarks/lmarena%3Atext%3Ahard_prompts_english.md) | 1,295.42 | — | 128 / 151 | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1295.4223729392888 \| rating \| reported \| Higher is better \| ### Configuration category hard_prompts_english config text ### Reported statistics lower 1288.1457842669638 rank 255 upper 1302.6989616116139 variance 13.783498711731491 votes 7690 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) Source Arena Original model label Llama 4 Maverick 17B 128E Instruct Observed 2026-10-21T18:45:05.190Z Evidence SHA-256 `8e027ef69b8de06c4b2a8b217bfe816b1f1536269bb257fd295b4ef1ba8246ac` Source locator `/rows/4122/row` | | | | | | | | [Arena text / instruction following](https://benchize.com/benchmarks/lmarena%3Atext%3Ainstruction_following.md) | 1,267.04 | — | 129 / 151 | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1267.037364906254 \| rating \| reported \| Higher is better \| ### Configuration category instruction_following config text ### Reported statistics lower 1260.5835886670245 rank 259 upper 1273.4911411454832 variance 10.842554792378156 votes 10499 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) Source Arena Original model label Llama 4 Maverick 17B 128E Instruct Observed 2026-10-21T18:45:05.190Z Evidence SHA-256 `8e027ef69b8de06c4b2a8b217bfe816b1f1536269bb257fd295b4ef1ba8246ac` Source locator `/rows/7792/row` | | | | | | | | [Arena text style control / russian](https://benchize.com/benchmarks/lmarena%3Atext_style_control%3Arussian.md) | 1,327.74 | — | 122 / 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` \| 1327.7404353990746 \| rating \| reported \| Higher is better \| ### Configuration category russian config text_style_control ### Reported statistics lower 1317.2904517911722 rank 233 upper 1338.1904190069768 variance 28.427262272641798 votes 3104 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label Llama 4 Maverick 17B 128E Instruct Observed 2026-10-21T18:45:05.190Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/10616/row` | | | | | | | | [VISTA](https://benchize.com/benchmarks/scale%3Avisual_language_understanding.md) | 38.33source score | CI 37.78–38.88 | 10 / 16 | — | [scale](https://labs.scale.com/leaderboard/visual_language_understanding) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `score` \| 38.33 \| source_score \| reported \| Higher is better \| ### Configuration Reasoning effort unknown Model configuration Llama 4 Maverick sourceModelVersion Not reported thinkingEnabled Not reported ### Reported statistics Uncertainty Confidence interval: 37.78–38.88 contaminationWarning Not reported rank 46 reportedConfidenceHalfWidth 0.55 ### Source [Original source](https://labs.scale.com/leaderboard/visual_language_understanding) Source scale Original model label Llama 4 Maverick Observed 2026-10-21T16:35:38.974Z Evidence SHA-256 `469e2d64808796dc35f1a8b8b0abe7daefeb7c5ee06fa9b6ba8b34c42d4b19b5` Source locator `/rows/45` | | | | | | | | [Arena text / overall](https://benchize.com/benchmarks/lmarena%3Atext.md) | 1,287.24 | — | 132 / 151 | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1287.2440286949166 \| rating \| reported \| Higher is better \| ### Configuration category overall config text ### Reported statistics lower 1282.9893664756767 rank 262 upper 1291.4986909141564 variance 4.712311505803484 votes 39442 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) Source Arena Original model label Llama 4 Maverick 17B 128E Instruct Observed 2026-10-21T18:45:05.190Z Evidence SHA-256 `8e027ef69b8de06c4b2a8b217bfe816b1f1536269bb257fd295b4ef1ba8246ac` Source locator `/rows/261/row` | | | | | | | | [Arena text style control / expert](https://benchize.com/benchmarks/lmarena%3Atext_style_control%3Aexpert.md) | 1,326.01 | — | 124 / 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` \| 1326.0072658168199 \| rating \| reported \| Higher is better \| ### Configuration category expert config text_style_control ### Reported statistics lower 1312.6556845662371 rank 240 upper 1339.3588470674026 variance 46.40547516235042 votes 2016 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label Llama 4 Maverick 17B 128E Instruct Observed 2026-10-21T18:45:05.190Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/2710/row` | | | | | | | | [Arena vision style control / creative writing](https://benchize.com/benchmarks/lmarena%3Avision_style_control%3Acreative_writing.md) | 1,127.8 | — | 13 / 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` \| 1127.8039604923083 \| rating \| reported \| Higher is better \| ### Configuration category creative_writing config vision_style_control ### Reported statistics lower 1090.048890623918 rank 33 upper 1165.559030360699 variance 371.06874427186034 votes 250 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/vision_style_control/latest) Source Arena Original model label llama-4-maverick-17b-128e-instruct Observed 2026-10-21T18:45:05.190Z Evidence SHA-256 `38568936995f36625aae49e9ea05557d55c1b1df9b2954f5c50cee523f26fe92` Source locator `/rows/361/row` | | | | | | | | [Arena text style control / overall](https://benchize.com/benchmarks/lmarena%3Atext_style_control%3Aoverall.md) | 1,327.01 | — | 125 / 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` \| 1327.0096942989721 \| rating \| reported \| Higher is better \| ### Configuration category overall config text_style_control ### Reported statistics lower 1322.7302405200435 rank 250 upper 1331.2891480779008 variance 4.767387990033863 votes 39442 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label Llama 4 Maverick 17B 128E Instruct Observed 2026-10-21T18:45:05.190Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/249/row` | | | | | | | | [Arena vision / chinese (config: vision)](https://benchize.com/benchmarks/benchmark%3Avision%3Achinese--config-vision.md) | 1,140.83 | — | 66 / 74 | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/vision/latest) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1140.8315081016071 \| rating \| reported \| Higher is better \| ### Configuration category chinese config vision ### Reported statistics lower 1106.7598156130064 rank 101 upper 1174.903200590208 variance 302.1977543489606 votes 294 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/vision/latest) Source Arena Original model label Llama 4 Maverick 17B 128E Instruct Observed 2026-10-21T18:45:05.190Z Evidence SHA-256 `06e61305486dce3fec5dc776ac2fd8321104e84c346cf9e08fa6f8e8a66ce0d7` Source locator `/rows/301/row` | | | | | | | | [Arena text / chinese](https://benchize.com/benchmarks/lmarena%3Atext%3Achinese.md) | 1,276.89 | — | 129 / 146 | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1276.8919036724465 \| rating \| reported \| Higher is better \| ### Configuration category chinese config text ### Reported statistics lower 1264.7188366120959 rank 255 upper 1289.0649707327973 variance 38.57481456198954 votes 2597 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) Source Arena Original model label Llama 4 Maverick 17B 128E Instruct Observed 2026-10-21T18:45:05.190Z Evidence SHA-256 `8e027ef69b8de06c4b2a8b217bfe816b1f1536269bb257fd295b4ef1ba8246ac` Source locator `/rows/671/row` | | | | | | | | [Arena text style control / creative writing](https://benchize.com/benchmarks/lmarena%3Atext_style_control%3Acreative_writing.md) | 1,306.93 | — | 118 / 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` \| 1306.9282043665257 \| rating \| reported \| Higher is better \| ### Configuration category creative_writing config text_style_control ### Reported statistics lower 1298.3449682825317 rank 227 upper 1315.51144045052 variance 19.17811568790119 votes 5152 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label Llama 4 Maverick 17B 128E Instruct Observed 2026-10-21T18:45:05.190Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/1448/row` | | | | | | | | [Arena text / industry mathematical](https://benchize.com/benchmarks/lmarena%3Atext%3Aindustry_mathematical.md) | 1,294.55 | — | 126 / 148 | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1294.5512308749264 \| rating \| reported \| Higher is better \| ### Configuration category industry_mathematical config text ### Reported statistics lower 1283.0245867658152 rank 245 upper 1306.0778749840374 variance 34.586736607031966 votes 2569 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) Source Arena Original model label Llama 4 Maverick 17B 128E Instruct Observed 2026-10-21T18:45:05.190Z Evidence SHA-256 `8e027ef69b8de06c4b2a8b217bfe816b1f1536269bb257fd295b4ef1ba8246ac` Source locator `/rows/6157/row` | | | | | | | | [Arena vision / overall (config: vision)](https://benchize.com/benchmarks/benchmark%3Avision%3Aoverall--config-vision.md) | 1,141.71 | — | 73 / 82 | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/vision/latest) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1141.7080159614773 \| rating \| reported \| Higher is better \| ### Configuration category overall config vision ### Reported statistics lower 1132.6595232044056 rank 122 upper 1150.7565087185492 variance 21.31357512768733 votes 6923 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/vision/latest) Source Arena Original model label Llama 4 Maverick 17B 128E Instruct Observed 2026-10-21T18:45:05.190Z Evidence SHA-256 `06e61305486dce3fec5dc776ac2fd8321104e84c346cf9e08fa6f8e8a66ce0d7` Source locator `/rows/121/row` | | | | | | | | [Arena text / industry software and it services](https://benchize.com/benchmarks/lmarena%3Atext%3Aindustry_software_and_it_services.md) | 1,298.69 | — | 131 / 151 | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1298.6881126439494 \| rating \| reported \| Higher is better \| ### Configuration category industry_software_and_it_services config text ### Reported statistics lower 1292.556937411378 rank 261 upper 1304.8192878765208 variance 9.78568598210461 votes 12286 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) Source Arena Original model label Llama 4 Maverick 17B 128E Instruct Observed 2026-10-21T18:45:05.190Z Evidence SHA-256 `8e027ef69b8de06c4b2a8b217bfe816b1f1536269bb257fd295b4ef1ba8246ac` Source locator `/rows/6961/row` | | | | | | | | [Arena vision style control / english](https://benchize.com/benchmarks/lmarena%3Avision_style_control%3Aenglish.md) | 1,150.87 | — | 75 / 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` \| 1150.8741600778847 \| rating \| reported \| Higher is better \| ### Configuration category english config vision_style_control ### Reported statistics lower 1139.072103915868 rank 124 upper 1162.6762162399016 variance 36.25927965205371 votes 3387 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/vision_style_control/latest) Source Arena Original model label Llama 4 Maverick 17B 128E Instruct Observed 2026-10-21T18:45:05.190Z Evidence SHA-256 `38568936995f36625aae49e9ea05557d55c1b1df9b2954f5c50cee523f26fe92` Source locator `/rows/713/row` | | | | | | | | [Arena text / french](https://benchize.com/benchmarks/lmarena%3Atext%3Afrench.md) | 1,259.35 | — | 126 / 132 | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1259.3533352934492 \| rating \| reported \| Higher is better \| ### Configuration category french config text ### Reported statistics lower 1233.911775034315 rank 241 upper 1284.7948955525833 variance 168.4966619796258 votes 597 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) Source Arena Original model label Llama 4 Maverick 17B 128E Instruct Observed 2026-10-21T18:45:05.190Z Evidence SHA-256 `8e027ef69b8de06c4b2a8b217bfe816b1f1536269bb257fd295b4ef1ba8246ac` Source locator `/rows/3078/row` | | | | | | | | [Arena text / expert](https://benchize.com/benchmarks/lmarena%3Atext%3Aexpert.md) | 1,259 | — | 125 / 148 | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1258.9998969731 \| rating \| reported \| Higher is better \| ### Configuration category expert config text ### Reported statistics lower 1245.6654521492214 rank 248 upper 1272.3343417969782 variance 46.286431030628165 votes 2016 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) Source Arena Original model label Llama 4 Maverick 17B 128E Instruct Observed 2026-10-21T18:45:05.190Z Evidence SHA-256 `8e027ef69b8de06c4b2a8b217bfe816b1f1536269bb257fd295b4ef1ba8246ac` Source locator `/rows/2718/row` | | | | | | | | [Arena text / spanish](https://benchize.com/benchmarks/lmarena%3Atext%3Aspanish.md) | 1,293.12 | — | 118 / 134 | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1293.1232035887494 \| rating \| reported \| Higher is better \| ### Configuration category spanish config text ### Reported statistics lower 1271.706761281762 rank 217 upper 1314.539645895737 variance 119.39839068889084 votes 820 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) Source Arena Original model label Llama 4 Maverick 17B 128E Instruct Observed 2026-10-21T18:45:05.190Z Evidence SHA-256 `8e027ef69b8de06c4b2a8b217bfe816b1f1536269bb257fd295b4ef1ba8246ac` Source locator `/rows/10981/row` | | | | | | | | [Spiral-Bench v1.0](https://benchize.com/benchmarks/eq-bench%3Aspiral-bench-v1.0.md) | 48.1% | CI 48.1–48.1% | 7 / 11 | — | [eq bench · spiral-bench-v1.0](https://eqbench.com/spiral-bench_v1.0.js) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `score_norm` \| 48.1 \| percent \| overall \| Higher is better \| ### Configuration interactiveAdjustments none protocol spiral-bench-v1.0 sourceModelVersion llama-4-maverick ### Reported statistics Uncertainty Confidence interval: 48.1–48.1% confidenceIntervalHigh 48.1 confidenceIntervalLow 48.1 ### Source [Original source](https://eqbench.com/spiral-bench_v1.0.js) Source eq bench Original model label llama-4-maverick Source version spiral-bench-v1.0 Observed 2026-10-21T16:35:04.619Z Evidence SHA-256 `d939ed9ba6d42226765fb4acf3e440127472566e1b5c2894d4ca25baa5ae75d2` Source locator `/leaderboardDataDelusion/10` | | | | | | | | [Arena text / hard prompts](https://benchize.com/benchmarks/lmarena%3Atext%3Ahard_prompts.md) | 1,280.59 | — | 130 / 151 | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1280.5903407565504 \| rating \| reported \| Higher is better \| ### Configuration category hard_prompts config text ### Reported statistics lower 1274.88345849096 rank 260 upper 1286.2972230221408 variance 8.478160697144919 votes 15865 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) Source Arena Original model label Llama 4 Maverick 17B 128E Instruct Observed 2026-10-21T18:45:05.190Z Evidence SHA-256 `8e027ef69b8de06c4b2a8b217bfe816b1f1536269bb257fd295b4ef1ba8246ac` Source locator `/rows/3710/row` | | | | | | | | [Arena text / industry entertainment and sports and media](https://benchize.com/benchmarks/lmarena%3Atext%3Aindustry_entertainment_and_sports_and_media.md) | 1,249.79 | — | 134 / 151 | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1249.7892650939816 \| rating \| reported \| Higher is better \| ### Configuration category industry_entertainment_and_sports_and_media config text ### Reported statistics lower 1242.2348226869665 rank 262 upper 1257.343707500997 variance 14.856231120706987 votes 6924 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) Source Arena Original model label Llama 4 Maverick 17B 128E Instruct Observed 2026-10-21T18:45:05.190Z Evidence SHA-256 `8e027ef69b8de06c4b2a8b217bfe816b1f1536269bb257fd295b4ef1ba8246ac` Source locator `/rows/4954/row` | | | | | | | | [Arena vision style control / diagram](https://benchize.com/benchmarks/lmarena%3Avision_style_control%3Adiagram.md) | 1,152.33 | — | 72 / 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` \| 1152.3328272695385 \| rating \| reported \| Higher is better \| ### Configuration category diagram config vision_style_control ### Reported statistics lower 1132.9051604054753 rank 116 upper 1171.7604941336012 variance 98.25284023552632 votes 947 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/vision_style_control/latest) Source Arena Original model label Llama 4 Maverick 17B 128E Instruct Observed 2026-10-21T18:45:05.190Z Evidence SHA-256 `38568936995f36625aae49e9ea05557d55c1b1df9b2954f5c50cee523f26fe92` Source locator `/rows/582/row` | | | | | | | | [Arena text style control / spanish](https://benchize.com/benchmarks/lmarena%3Atext_style_control%3Aspanish.md) | 1,325.94 | — | 117 / 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` \| 1325.9397915621444 \| rating \| reported \| Higher is better \| ### Configuration category spanish config text_style_control ### Reported statistics lower 1304.516983651167 rank 220 upper 1347.362599473122 variance 119.46937874703283 votes 820 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label Llama 4 Maverick 17B 128E Instruct Observed 2026-10-21T18:45:05.190Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/10984/row` | | | | | | | | [Arena vision / creative writing (config: vision)](https://benchize.com/benchmarks/benchmark%3Avision%3Acreative_writing--config-vision.md) | 1,112.91 | — | 13 / 13 | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/vision/latest) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1112.9129032575138 \| rating \| reported \| Higher is better \| ### Configuration category creative_writing config vision ### Reported statistics lower 1074.9475947680562 rank 34 upper 1150.8782117469716 variance 375.2128334514461 votes 250 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/vision/latest) Source Arena Original model label llama-4-maverick-17b-128e-instruct Observed 2026-10-21T18:45:05.190Z Evidence SHA-256 `06e61305486dce3fec5dc776ac2fd8321104e84c346cf9e08fa6f8e8a66ce0d7` Source locator `/rows/362/row` | | | | | | | | [Arena text style control / coding](https://benchize.com/benchmarks/lmarena%3Atext_style_control%3Acoding.md) | 1,372.43 | — | 121 / 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` \| 1372.430557011914 \| rating \| reported \| Higher is better \| ### Configuration category coding config text_style_control ### Reported statistics lower 1364.9376556061804 rank 242 upper 1379.9234584176477 variance 14.615169417825578 votes 6939 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label Llama 4 Maverick 17B 128E Instruct Observed 2026-10-21T18:45:05.190Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/1051/row` | | | | | | | --- Cite as: Llama 4 Maverick — Benchize, https://benchize.com/models/llama-4-maverick (retrieved 2026-10-21)