# Gemini 3.1 Pro Preview

> Source: Benchize (https://benchize.com) — https://benchize.com/models/gemini-3-1-pro-preview. When citing or reusing this content, credit "Benchize" and link to https://benchize.com/models/gemini-3-1-pro-preview.

Google

Canonical URL: https://benchize.com/models/gemini-3-1-pro-preview
Last updated: Wed, 21 Oct 2026 18:05:10 GMT

Reproduction and quotation must name Benchize, link to the canonical HTML URL, and retain individual source citations.

Google

## Benchmarks

| Benchmark | Score | ± | Rank | Cost | Latency | Source |  |
| --- | --- | --- | --- | --- | --- | --- | --- |
| [Arena text style control / industry writing and literature and language](https://benchize.com/benchmarks/lmarena%3Atext_style_control%3Aindustry_writing_and_literature_and_language.md) | 1,481.93 | — | 12 / 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` \| 1481.930799668101 \| rating \| reported \| Higher is better \| ### Configuration category industry_writing_and_literature_and_language config text_style_control ### Reported statistics lower 1477.258043524814 rank 12 upper 1486.603555811388 variance 5.683947425650471 votes 33206 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label Gemini 3.1 Pro Preview Observed 2026-10-21T16:40:19.533Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/7129/row` |  |  |  |  |  |  |  |
| [Arena text style control / exclude ties](https://benchize.com/benchmarks/lmarena%3Atext_style_control%3Aexclude_ties.md) | 1,501.45 | — | 17 / 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` \| 1501.4536269922735 \| rating \| reported \| Higher is better \| ### Configuration category exclude_ties config text_style_control ### Reported statistics lower 1497.4843311462355 rank 19 upper 1505.4229228383115 variance 4.101387063815253 votes 97303 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label Gemini 3.1 Pro Preview Observed 2026-10-21T16:40:19.533Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/2072/row` |  |  |  |  |  |  |  |
| [Arena text / industry writing and literature and language](https://benchize.com/benchmarks/lmarena%3Atext%3Aindustry_writing_and_literature_and_language.md) | 1,481.1 | — | 13 / 151 | — | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1481.0975739897083 \| rating \| reported \| Higher is better \| ### Configuration category industry_writing_and_literature_and_language config text ### Reported statistics lower 1476.44620837879 rank 13 upper 1485.7489396006263 variance 5.632027585427078 votes 33206 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) Source Arena Original model label Gemini 3.1 Pro Preview Observed 2026-10-21T16:40:19.533Z Evidence SHA-256 `8e027ef69b8de06c4b2a8b217bfe816b1f1536269bb257fd295b4ef1ba8246ac` Source locator `/rows/7130/row` |  |  |  |  |  |  |  |
| [Arena text / chinese](https://benchize.com/benchmarks/lmarena%3Atext%3Achinese.md) | 1,527.49 | — | 20 / 146 | — | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1527.4942473427725 \| rating \| reported \| Higher is better \| ### Configuration category chinese config text ### Reported statistics lower 1520.2980829723165 rank 24 upper 1534.6904117132285 variance 13.480498962439677 votes 8966 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) Source Arena Original model label Gemini 3.1 Pro Preview Observed 2026-10-21T16:40:19.533Z Evidence SHA-256 `8e027ef69b8de06c4b2a8b217bfe816b1f1536269bb257fd295b4ef1ba8246ac` Source locator `/rows/440/row` |  |  |  |  |  |  |  |
| [Arena text style control / industry software and it services](https://benchize.com/benchmarks/lmarena%3Atext_style_control%3Aindustry_software_and_it_services.md) | 1,513.01 | — | 25 / 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` \| 1513.006399138717 \| rating \| reported \| Higher is better \| ### Configuration category industry_software_and_it_services config text_style_control ### Reported statistics lower 1508.9571890083107 rank 28 upper 1517.0556092691234 variance 4.26819691307351 votes 50815 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label Gemini 3.1 Pro Preview Observed 2026-10-21T16:40:19.533Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/6728/row` |  |  |  |  |  |  |  |
| [Short Story Writing — Pairwise Comparison](https://benchize.com/benchmarks/lechmazur-short-story%3Apairwise.md) | -2.17 | 95% CI -2.27–-2.07 | 43 / 50 | — | — | [lechmazur short story · 8ba548d1cffefa5c472d3832e05f64e119a88fa4](https://api.github.com/repos/lechmazur/writing/contents/data/writing_gemini_argon_20261013/ratings.csv?ref=8ba548d1cffefa5c472d3832e05f64e119a88fa4) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `thurstone_rating` \| -2.169608572429032 \| index \| pooled_observed_panel \| Higher is better \| \| `win_probability` \| 0.19859238875107632 \| score_fraction \| comparison_pool \| Higher is better \| ### Configuration benchmarkScope data/writing_gemini_argon_20261013 ### Reported statistics Uncertainty 95% confidence interval: -2.27–-2.07 bootstrapSamples 300 confidenceInterval95 ["-2.2710552684989196","-2.071592808223834"] sourceRank 50 ### Source [Original source](https://api.github.com/repos/lechmazur/writing/contents/data/writing_gemini_argon_20261013/ratings.csv?ref=8ba548d1cffefa5c472d3832e05f64e119a88fa4) Source lechmazur short story Original model label Gemini 3.1 Pro Preview Source version 8ba548d1cffefa5c472d3832e05f64e119a88fa4 Observed 2026-10-21T16:34:21.130Z Evidence SHA-256 `c36baebed9f302ff7ad8fe97907d72e1757a015a39b6a3b23437597cf8e3bff6` Source locator `/rows/49` |  |  |  |  |  |  |  |
| [Arena text / spanish](https://benchize.com/benchmarks/lmarena%3Atext%3Aspanish.md) | 1,480.57 | — | 15 / 134 | — | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1480.5713296619592 \| rating \| reported \| Higher is better \| ### Configuration category spanish config text ### Reported statistics lower 1470.0129131417411 rank 15 upper 1491.1297461821778 variance 29.020266679384502 votes 4141 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) Source Arena Original model label Gemini 3.1 Pro Preview Observed 2026-10-21T16:40:19.533Z Evidence SHA-256 `8e027ef69b8de06c4b2a8b217bfe816b1f1536269bb257fd295b4ef1ba8246ac` Source locator `/rows/10779/row` |  |  |  |  |  |  |  |
| [Apex Shortlist](https://benchize.com/benchmarks/matharena%3Aapex--shortlist_2025.md) | 92.02% | 95% CI 88.15–95.89% | 2 / 24 | 0.37usd per problem | — | [matharena · apex--shortlist_2025](https://matharena.ai/competition_tables/apex--shortlist_2025) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 92.02 \| percent \| competition \| Higher is better \| \| `cost_per_problem` \| 0.37 \| usd_per_problem \| competition \| Lower is better \| ### Configuration competition apex--shortlist_2025 predicted false sourceModelName Gemini 3.1 Pro Preview sourceModelVersion gemini/gemini-31-pro ### Reported statistics Uncertainty 95% confidence interval: 88.15–95.89% confidenceInterval95 3.87 problems 47 ### Source [Original source](https://matharena.ai/competition_tables/apex--shortlist_2025) Source matharena Original model label Gemini 3.1 Pro Preview Source version apex--shortlist_2025 Observed 2026-10-21T16:52:39.300Z Evidence SHA-256 `74513abecacb4d230d741f4d6df425ce878fb450220e88a1a6823524476c2989` Source locator `/table/rows/1` |  |  |  |  |  |  |  |
| [SimpleBench](https://benchize.com/benchmarks/simplebench%3Aavg-at-5.md) | 79.6% | — | 8 / 62 | — | — | [simplebench](https://simple-bench.com/static/js/leaderboard-data.js) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 79.6 \| percent \| average_at_5 \| Higher is better \| ### Configuration Reasoning effort unknown Model configuration Gemini 3.1 Pro Preview thinkingEnabled Not reported ### Reported statistics rank 10th ### Source [Original source](https://simple-bench.com/static/js/leaderboard-data.js) Source simplebench Original model label Gemini 3.1 Pro Preview Observed 2026-10-21T16:32:13.183Z Evidence SHA-256 `b2d0285ad3e4e15750ed20d39897e7558d1c05e8962e90c861b06f93c8019dc9` Source locator `/rows/11` |  |  |  |  |  |  |  |
| [Arena vision / entity recognition (config: vision)](https://benchize.com/benchmarks/benchmark%3Avision%3Aentity_recognition--config-vision.md) | 1,329.7 | — | 3 / 34 | — | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/vision/latest) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1329.7022623203447 \| rating \| reported \| Higher is better \| ### Configuration category entity_recognition config vision ### Reported statistics lower 1300.794250958198 rank 3 upper 1358.6102736824912 variance 217.54056464491646 votes 388 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/vision/latest) Source Arena Original model label Gemini 3.1 Pro Preview Observed 2026-10-21T16:40:19.533Z Evidence SHA-256 `06e61305486dce3fec5dc776ac2fd8321104e84c346cf9e08fa6f8e8a66ce0d7` Source locator `/rows/759/row` |  |  |  |  |  |  |  |
| [Arena text / english](https://benchize.com/benchmarks/lmarena%3Atext%3Aenglish.md) | 1,478.19 | — | 21 / 151 | — | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1478.1879229369558 \| rating \| reported \| Higher is better \| ### Configuration category english config text ### Reported statistics lower 1474.297032920746 rank 24 upper 1482.0788129531657 variance 3.9409572833858815 votes 56774 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) Source Arena Original model label Gemini 3.1 Pro Preview Observed 2026-10-21T16:40:19.533Z Evidence SHA-256 `8e027ef69b8de06c4b2a8b217bfe816b1f1536269bb257fd295b4ef1ba8246ac` Source locator `/rows/1660/row` |  |  |  |  |  |  |  |
| [Arena text / hard prompts english](https://benchize.com/benchmarks/lmarena%3Atext%3Ahard_prompts_english.md) | 1,480.41 | — | 28 / 151 | — | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1480.4084893290928 \| rating \| reported \| Higher is better \| ### Configuration category hard_prompts_english config text ### Reported statistics lower 1475.9265392689995 rank 36 upper 1484.8904393891858 variance 5.2292312058521535 votes 37705 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) Source Arena Original model label Gemini 3.1 Pro Preview Observed 2026-10-21T16:40:19.533Z Evidence SHA-256 `8e027ef69b8de06c4b2a8b217bfe816b1f1536269bb257fd295b4ef1ba8246ac` Source locator `/rows/3903/row` |  |  |  |  |  |  |  |
| [Arena text / japanese](https://benchize.com/benchmarks/lmarena%3Atext%3Ajapanese.md) | 1,491.49 | — | 10 / 120 | — | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1491.4928609830217 \| rating \| reported \| Higher is better \| ### Configuration category japanese config text ### Reported statistics lower 1474.3222838208223 rank 12 upper 1508.663438145221 variance 76.74915542365956 votes 1582 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) Source Arena Original model label Gemini 3.1 Pro Preview Observed 2026-10-21T16:40:19.533Z Evidence SHA-256 `8e027ef69b8de06c4b2a8b217bfe816b1f1536269bb257fd295b4ef1ba8246ac` Source locator `/rows/7962/row` |  |  |  |  |  |  |  |
| [DesignArena Agentic game development](https://benchize.com/benchmarks/designarena%3Aagentic-game-dev.md) | 1,114elo | SE ±8.86 | 16 / 17 | — | — | [designarena · public](https://www.designarena.ai/api/leaderboard#board=agentic-game-dev) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `elo` \| 1114 \| elo \| agentic-game-dev \| Higher is better \| ### Configuration arenaType agents category agentic_gamedev inputModality Not reported sourceModelVersion gemini-3.1-pro-preview variationName public ### Reported statistics Uncertainty Standard error: ±8.86 averageGenerationTimeMs Not reported battles 1870 losses 1045 standardError 8.8576 winRate 44.1 wins 825 ### Source [Original source](https://www.designarena.ai/api/leaderboard#board=agentic-game-dev) Source designarena Original model label Gemini 3.1 Pro Preview Source version public Observed 2026-10-21T16:38:01.564Z Evidence SHA-256 `2bb291527289cec897df421c3c59427ce53230a312bf61790ba7ac6ca436bb4b` Source locator `/data/23` |  |  |  |  |  |  |  |
| [Arena vision / humor (config: vision)](https://benchize.com/benchmarks/benchmark%3Avision%3Ahumor--config-vision.md) | 1,322.39 | — | 3 / 63 | — | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/vision/latest) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1322.3917899316255 \| rating \| reported \| Higher is better \| ### Configuration category humor config vision ### Reported statistics lower 1308.1768047282706 rank 4 upper 1336.6067751349804 variance 52.60131990561954 votes 1885 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/vision/latest) Source Arena Original model label Gemini 3.1 Pro Preview Observed 2026-10-21T16:40:19.533Z Evidence SHA-256 `06e61305486dce3fec5dc776ac2fd8321104e84c346cf9e08fa6f8e8a66ce0d7` Source locator `/rows/929/row` |  |  |  |  |  |  |  |
| [DesignArena 3D design generation](https://benchize.com/benchmarks/designarena%3A3d-design.md) | 1,235elo | — | 31 / 110 | — | — | [designarena · public](https://www.designarena.ai/api/leaderboard#board=3d-design) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `elo` \| 1235 \| elo \| 3d-design \| Higher is better \| ### Configuration arenaType models category 3d inputModality Not reported sourceModelVersion gemini-3.1-pro-preview variationName public ### Reported statistics averageGenerationTimeMs 88762 battles 9108 losses 3790 standardError Not reported winRate 58.4 wins 5318 ### Source [Original source](https://www.designarena.ai/api/leaderboard#board=3d-design) Source designarena Original model label Gemini 3.1 Pro Preview Source version public Observed 2026-10-21T16:37:58.515Z Evidence SHA-256 `bcc0267f7bc7e9ec112306b3a35413cf78bbccbfaa838356232d5d5ed0b83d0f` Source locator `/data/50` |  |  |  |  |  |  |  |
| [Arena text style control / coding](https://benchize.com/benchmarks/lmarena%3Atext_style_control%3Acoding.md) | 1,521.43 | — | 26 / 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` \| 1521.4261492468727 \| rating \| reported \| Higher is better \| ### Configuration category coding config text_style_control ### Reported statistics lower 1516.8836393777651 rank 32 upper 1525.96865911598 variance 5.371499962404761 votes 35474 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label Gemini 3.1 Pro Preview Observed 2026-10-21T16:40:19.533Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/841/row` |  |  |  |  |  |  |  |
| [Arena text style control / russian](https://benchize.com/benchmarks/lmarena%3Atext_style_control%3Arussian.md) | 1,501.83 | — | 11 / 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` \| 1501.828510502814 \| rating \| reported \| Higher is better \| ### Configuration category russian config text_style_control ### Reported statistics lower 1495.9578182655123 rank 11 upper 1507.6992027401152 variance 8.971859117543058 votes 14843 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label Gemini 3.1 Pro Preview Observed 2026-10-21T16:40:19.533Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/10394/row` |  |  |  |  |  |  |  |
| [Arena webdev / webdev](https://benchize.com/benchmarks/lmarena%3Awebdev%3Awebdev.md) | 1,446.92 | — | 49 / 90 | — | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/webdev/latest) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1446.920737117052 \| rating \| reported \| Higher is better \| ### Configuration category webdev config webdev ### Reported statistics lower 1441.8604368885435 rank 76 upper 1451.9810373455607 variance 6.6658630478345176 votes 24199 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/webdev/latest) Source Arena Original model label Gemini 3.1 Pro Preview Observed 2026-10-21T16:40:19.533Z Evidence SHA-256 `f82507859808110820a4ab6df15561b8864137ddefc1f6fb0c552af2e58ea738` Source locator `/rows/287/row` |  |  |  |  |  |  |  |
| [Arena vision / ocr (config: vision)](https://benchize.com/benchmarks/benchmark%3Avision%3Aocr--config-vision.md) | 1,303.57 | — | 22 / 74 | — | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/vision/latest) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1303.5654298960042 \| rating \| reported \| Higher is better \| ### Configuration category ocr config vision ### Reported statistics lower 1298.6180011465146 rank 23 upper 1308.5128586454937 variance 6.371811432525523 votes 32719 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/vision/latest) Source Arena Original model label Gemini 3.1 Pro Preview Observed 2026-10-21T16:40:19.533Z Evidence SHA-256 `06e61305486dce3fec5dc776ac2fd8321104e84c346cf9e08fa6f8e8a66ce0d7` Source locator `/rows/1041/row` |  |  |  |  |  |  |  |
| [Arena webdev / overall](https://benchize.com/benchmarks/lmarena%3Awebdev%3Aoverall.md) | 1,446.92 | — | 49 / 90 | — | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/webdev/latest) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1446.920737117052 \| rating \| reported \| Higher is better \| ### Configuration category overall config webdev ### Reported statistics lower 1441.8604368885435 rank 76 upper 1451.9810373455607 variance 6.6658630478345176 votes 24199 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/webdev/latest) Source Arena Original model label Gemini 3.1 Pro Preview Observed 2026-10-21T16:40:19.533Z Evidence SHA-256 `f82507859808110820a4ab6df15561b8864137ddefc1f6fb0c552af2e58ea738` Source locator `/rows/75/row` |  |  |  |  |  |  |  |
| [Arena text style control / spanish](https://benchize.com/benchmarks/lmarena%3Atext_style_control%3Aspanish.md) | 1,483.58 | — | 12 / 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` \| 1483.584246759589 \| rating \| reported \| Higher is better \| ### Configuration category spanish config text_style_control ### Reported statistics lower 1472.9960409446498 rank 13 upper 1494.172452574528 variance 29.18425202830927 votes 4141 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label Gemini 3.1 Pro Preview Observed 2026-10-21T16:40:19.533Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/10777/row` |  |  |  |  |  |  |  |
| [Kangaroo 2025 1-2](https://benchize.com/benchmarks/matharena%3Akangaroo--kangaroo_2025_1-2.md) | 86.46% | 95% CI 79.62–93.3% | 5 / 16 | 0.16usd per problem | — | [matharena · kangaroo--kangaroo_2025_1-2](https://matharena.ai/competition_tables/kangaroo--kangaroo_2025_1-2) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 86.46 \| percent \| competition \| Higher is better \| \| `cost_per_problem` \| 0.16 \| usd_per_problem \| competition \| Lower is better \| ### Configuration competition kangaroo--kangaroo_2025_1-2 predicted false sourceModelName Gemini 3.1 Pro Preview sourceModelVersion gemini/gemini-31-pro ### Reported statistics Uncertainty 95% confidence interval: 79.62–93.3% confidenceInterval95 6.84 problems 24 ### Source [Original source](https://matharena.ai/competition_tables/kangaroo--kangaroo_2025_1-2) Source matharena Original model label Gemini 3.1 Pro Preview Source version kangaroo--kangaroo_2025_1-2 Observed 2026-10-21T16:52:31.513Z Evidence SHA-256 `a59a4c362e2d87350330706a01dd330e9a1ac7cc64a4de0bacbf1a439d8fcf90` Source locator `/table/rows/5` |  |  |  |  |  |  |  |
| [BrokenArXiv 03/2026](https://benchize.com/benchmarks/matharena%3Aarxiv_false--march.md) | 13.84% | 95% CI 7.44–20.24% | 7 / 14 | 0.31usd per problem | — | [matharena · arxiv_false--march](https://matharena.ai/competition_tables/arxiv_false--march) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 13.84 \| percent \| competition \| Higher is better \| \| `cost_per_problem` \| 0.31 \| usd_per_problem \| competition \| Lower is better \| ### Configuration competition arxiv_false--march predicted false sourceModelName Gemini 3.1 Pro Preview sourceModelVersion gemini/gemini-31-pro ### Reported statistics Uncertainty 95% confidence interval: 7.44–20.24% confidenceInterval95 6.40 problems 56 ### Source [Original source](https://matharena.ai/competition_tables/arxiv_false--march) Source matharena Original model label Gemini 3.1 Pro Preview Source version arxiv_false--march Observed 2026-10-21T16:52:24.043Z Evidence SHA-256 `b2ea8c773acad8b54736938938d6ee37fa533bfc5b985eefc303733bfcb0c6f0` Source locator `/table/rows/7` |  |  |  |  |  |  |  |
| [Arena vision style control / homework](https://benchize.com/benchmarks/lmarena%3Avision_style_control%3Ahomework.md) | 1,310.24 | — | 22 / 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` \| 1310.2358960798308 \| rating \| reported \| Higher is better \| ### Configuration category homework config vision_style_control ### Reported statistics lower 1301.7666997363451 rank 23 upper 1318.7050924233165 variance 18.67188743976987 votes 6293 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/vision_style_control/latest) Source Arena Original model label Gemini 3.1 Pro Preview Observed 2026-10-21T16:40:19.533Z Evidence SHA-256 `38568936995f36625aae49e9ea05557d55c1b1df9b2954f5c50cee523f26fe92` Source locator `/rows/830/row` |  |  |  |  |  |  |  |
| [GPQA Diamond](https://benchize.com/benchmarks/gpqa-diamond.md) | 94.1% | SE ±1.7 pp | 10 / 125 | — | — | [epoch ai · GPQA diamond](https://epoch.ai/data/benchmark_data.zip#file=gpqa_diamond.csv) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `score` \| 0.941 \| score_fraction \| Best score (across scorers) \| Higher is better \| \| `mean_score` \| 0.941 \| score_fraction \| mean_score \| Higher is better \| ### Configuration benchmarkVersion GPQA diamond reasoningBudget Not reported Reasoning effort Not reported sourceModelVersion gemini-3.1-pro-preview ### Reported statistics Uncertainty Standard error: ±1.7 pp standardError 0.017 ### Source [Original source](https://epoch.ai/data/benchmark_data.zip#file=gpqa_diamond.csv) Source epoch ai Original model label gemini-3.1-pro-preview Source version GPQA diamond Evaluated 2026-02-20T05:01:02.541Z Observed 2026-10-21T16:30:24.199Z Evidence SHA-256 `4b2dd8376cdd249a2c3065603575208fa726c15eabbb1622689a9abc146ba29a` Source locator `/rows/176` |  |  |  |  |  |  |  |
| [Rapidata SVG generation — Alignment](https://benchize.com/benchmarks/rapidata%3Asvg%3Arlb_1MFkk9yZHssERh.md) | 1,134.75elo | CI 1,120.46–1,149.03 | 14 / 37 | — | — | [rapidata · v1](https://api.rapidata.ai/benchmark/bmk_1MFkc3sXfbKCqf/standings/query?leaderboard_id%5Beq%5D=rlb_1MFkk9yZHssERh) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `elo` \| 1134.7476026325153 \| elo \| rlb_1MFkk9yZHssERh \| Higher is better \| ### Configuration benchmarkId bmk_1MFkc3sXfbKCqf criterion rlb_1MFkk9yZHssERh participantId par_1MFl49p61xwRyK sourceModelVersion gemini-3.1-pro-preview weighted false ### Reported statistics Uncertainty Confidence interval: 1,120.46–1,149.03 confidenceIntervalLowerOffset 14.287045676733896 confidenceIntervalUpperOffset 14.287045676733896 totalMatches 14898 wins 9713 ### Source [Original source](https://api.rapidata.ai/benchmark/bmk_1MFkc3sXfbKCqf/standings/query?leaderboard_id%5Beq%5D=rlb_1MFkk9yZHssERh) Source rapidata Original model label gemini-3.1-pro-preview Source version v1 Observed 2026-10-21T16:37:40.342Z Evidence SHA-256 `2f5c8d08728735790b500d930d71b66f04253f1209f7c1c3da0db0846c163fcf` Source locator `/items/20` |  |  |  |  |  |  |  |
| [Arena text / industry business and management and financial operations](https://benchize.com/benchmarks/lmarena%3Atext%3Aindustry_business_and_management_and_financial_operations.md) | 1,459.28 | — | 28 / 151 | — | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1459.2783422646755 \| rating \| reported \| Higher is better \| ### Configuration category industry_business_and_management_and_financial_operations config text ### Reported statistics lower 1454.3343024248052 rank 34 upper 1464.2223821045457 variance 6.36308524421655 votes 25105 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) Source Arena Original model label Gemini 3.1 Pro Preview Observed 2026-10-21T16:40:19.533Z Evidence SHA-256 `8e027ef69b8de06c4b2a8b217bfe816b1f1536269bb257fd295b4ef1ba8246ac` Source locator `/rows/4316/row` |  |  |  |  |  |  |  |
| [Arena vision style control / captioning](https://benchize.com/benchmarks/lmarena%3Avision_style_control%3Acaptioning.md) | 1,281.62 | — | 1 / 22 | — | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/vision_style_control/latest) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1281.6156265182872 \| rating \| reported \| Higher is better \| ### Configuration category captioning config vision_style_control ### Reported statistics lower 1233.305276376888 rank 1 upper 1329.925976659686 variance 607.5530260045458 votes 137 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/vision_style_control/latest) Source Arena Original model label Gemini 3.1 Pro Preview Observed 2026-10-21T16:40:19.533Z Evidence SHA-256 `38568936995f36625aae49e9ea05557d55c1b1df9b2954f5c50cee523f26fe92` Source locator `/rows/167/row` |  |  |  |  |  |  |  |
| [ArXivMath 05/2026](https://benchize.com/benchmarks/matharena%3Aarxiv--may.md) | 51.67% | 95% CI 42.73–60.61% | 17 / 21 | 0.34usd per problem | — | [matharena · arxiv--may](https://matharena.ai/competition_tables/arxiv--may) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 51.67 \| percent \| competition \| Higher is better \| \| `cost_per_problem` \| 0.34 \| usd_per_problem \| competition \| Lower is better \| ### Configuration competition arxiv--may predicted false sourceModelName Gemini 3.1 Pro Preview sourceModelVersion gemini/gemini-31-pro ### Reported statistics Uncertainty 95% confidence interval: 42.73–60.61% confidenceInterval95 8.94 problems 40 ### Source [Original source](https://matharena.ai/competition_tables/arxiv--may) Source matharena Original model label Gemini 3.1 Pro Preview Source version arxiv--may Observed 2026-10-21T16:52:29.369Z Evidence SHA-256 `758e1bba77e36f4ced2a51b4bc0d46bd956ed94ef6f57e93e1a974b75e76a4ce` Source locator `/table/rows/19` |  |  |  |  |  |  |  |
| [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) | 1,509.99 | — | 16 / 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` \| 1509.989689991 \| rating \| reported \| Higher is better \| ### Configuration category industry_life_and_physical_and_social_science config text_style_control ### Reported statistics lower 1504.8239561007924 rank 17 upper 1515.1554238812075 variance 6.946529396771405 votes 21617 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label Gemini 3.1 Pro Preview Observed 2026-10-21T16:40:19.533Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/5514/row` |  |  |  |  |  |  |  |
| [Arena text / industry medicine and healthcare](https://benchize.com/benchmarks/lmarena%3Atext%3Aindustry_medicine_and_healthcare.md) | 1,486.02 | — | 18 / 151 | — | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1486.016665889948 \| rating \| reported \| Higher is better \| ### Configuration category industry_medicine_and_healthcare config text ### Reported statistics lower 1478.9445251008005 rank 21 upper 1493.088806679095 variance 13.019838992438597 votes 9660 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) Source Arena Original model label Gemini 3.1 Pro Preview Observed 2026-10-21T16:40:19.533Z Evidence SHA-256 `8e027ef69b8de06c4b2a8b217bfe816b1f1536269bb257fd295b4ef1ba8246ac` Source locator `/rows/6333/row` |  |  |  |  |  |  |  |
| [EQ-Bench 4](https://benchize.com/benchmarks/eq-bench%3Aeqbench4.md) | 1,142.3elo | CI 1,130–1,153.9 | 21 / 26 | — | — | [eq bench · eqbench4](https://eqbench.com/eqbench4/eqbench4_data.js) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `elo` \| 1142.3 \| elo \| overall \| Higher is better \| ### Configuration protocol eqbench4 ### Reported statistics Uncertainty Confidence interval: 1,130–1,153.9 confidenceIntervalHigh 1153.9 confidenceIntervalLow 1130 scenarios 120 ### Source [Original source](https://eqbench.com/eqbench4/eqbench4_data.js) Source eq bench Original model label gemini-3.1-pro-preview Source version eqbench4 Observed 2026-10-21T16:35:00.261Z Evidence SHA-256 `188d8ea4a393978063a6c24dff6c92ce185169827038bfa558091212a68c29d8` Source locator `/models/20` |  |  |  |  |  |  |  |
| [Arena text style control / polish](https://benchize.com/benchmarks/lmarena%3Atext_style_control%3Apolish.md) | 1,495.99 | — | 14 / 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` \| 1495.9948183179138 \| rating \| reported \| Higher is better \| ### Configuration category polish config text_style_control ### Reported statistics lower 1483.6189910717258 rank 14 upper 1508.370645564102 variance 39.87055625909736 votes 2473 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label Gemini 3.1 Pro Preview Observed 2026-10-21T16:40:19.533Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/10161/row` |  |  |  |  |  |  |  |
| [ArXivMath 06/2026](https://benchize.com/benchmarks/matharena%3Aarxiv--june.md) | 66.67% | 95% CI 58.97–74.37% | 14 / 22 | 0.37usd per problem | — | [matharena · arxiv--june](https://matharena.ai/competition_tables/arxiv--june) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 66.67 \| percent \| competition \| Higher is better \| \| `cost_per_problem` \| 0.37 \| usd_per_problem \| competition \| Lower is better \| ### Configuration competition arxiv--june predicted false sourceModelName Gemini 3.1 Pro Preview sourceModelVersion gemini/gemini-31-pro ### Reported statistics Uncertainty 95% confidence interval: 58.97–74.37% confidenceInterval95 7.70 problems 48 ### Source [Original source](https://matharena.ai/competition_tables/arxiv--june) Source matharena Original model label Gemini 3.1 Pro Preview Source version arxiv--june Observed 2026-10-21T16:52:29.905Z Evidence SHA-256 `6832faff9be7e16a6c646c59017e30a2caedebe8cf02caf617a5ed9d8fb03bab` Source locator `/table/rows/18` |  |  |  |  |  |  |  |
| [Arena vision style control / overall](https://benchize.com/benchmarks/lmarena%3Avision_style_control%3Aoverall.md) | 1,279.55 | — | 27 / 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` \| 1279.5484049752495 \| rating \| reported \| Higher is better \| ### Configuration category overall config vision_style_control ### Reported statistics lower 1274.4178440085032 rank 28 upper 1284.6789659419958 variance 6.852255109881344 votes 47114 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/vision_style_control/latest) Source Arena Original model label Gemini 3.1 Pro Preview Observed 2026-10-21T16:40:19.533Z Evidence SHA-256 `38568936995f36625aae49e9ea05557d55c1b1df9b2954f5c50cee523f26fe92` Source locator `/rows/27/row` |  |  |  |  |  |  |  |
| [Arena text / non english](https://benchize.com/benchmarks/lmarena%3Atext%3Anon_english.md) | 1,476.31 | — | 14 / 151 | — | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1476.3105577898873 \| rating \| reported \| Higher is better \| ### Configuration category non_english config text ### Reported statistics lower 1472.7075594077376 rank 14 upper 1479.9135561720368 variance 3.379340492169208 votes 72740 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) Source Arena Original model label Gemini 3.1 Pro Preview Observed 2026-10-21T16:40:19.533Z Evidence SHA-256 `8e027ef69b8de06c4b2a8b217bfe816b1f1536269bb257fd295b4ef1ba8246ac` Source locator `/rows/9744/row` |  |  |  |  |  |  |  |
| [DesignArena Native Android development](https://benchize.com/benchmarks/designarena%3Aandroid.md) | 1,056elo | — | 22 / 23 | — | — | [designarena · public](https://www.designarena.ai/api/leaderboard#board=android) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `elo` \| 1056 \| elo \| android \| Higher is better \| ### Configuration arenaType agents category nativeapps inputModality Not reported sourceModelVersion gemini-3.1-pro-preview variationName public ### Reported statistics averageGenerationTimeMs Not reported battles 5364 losses 3147 standardError Not reported winRate 41.3 wins 2217 ### Source [Original source](https://www.designarena.ai/api/leaderboard#board=android) Source designarena Original model label Gemini 3.1 Pro Preview Source version public Observed 2026-10-21T16:38:03.000Z Evidence SHA-256 `d9d0cd4bea54b696c28f907a98ba42ebf8dd4da9da201b6c70c95f76de35f525` Source locator `/data/33` |  |  |  |  |  |  |  |
| [Arena vision style control / ocr](https://benchize.com/benchmarks/lmarena%3Avision_style_control%3Aocr.md) | 1,294.2 | — | 26 / 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` \| 1294.1983479852643 \| rating \| reported \| Higher is better \| ### Configuration category ocr config vision_style_control ### Reported statistics lower 1289.212063868414 rank 27 upper 1299.1846321021144 variance 6.472288381698778 votes 32719 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/vision_style_control/latest) Source Arena Original model label Gemini 3.1 Pro Preview Observed 2026-10-21T16:40:19.533Z Evidence SHA-256 `38568936995f36625aae49e9ea05557d55c1b1df9b2954f5c50cee523f26fe92` Source locator `/rows/1045/row` |  |  |  |  |  |  |  |
| [OfficeQA Pro — Oracle PDF + Web Search](https://benchize.com/benchmarks/officeqa-pro%3Aoracle.md) | 63.91% | — | 11 / 12 | — | — | [officeqa pro · sha256:4ea6f6e46bf4afc28634ec4b9abb54837c58c284e71ba077f6b8fbe11aa3be30](https://api.github.com/repos/databricks/officeqa/git/blobs/a9992a78b86a0d400f1e3af8027fe5d3166eef97) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `correctness` \| 63.91 \| percent \| oracle_pdf_web_search \| Higher is better \| ### Configuration absoluteRelativeErrorPercent 0.1 harness Oracle PDF + Web Search oraclePages true webSearch true ### Reported statistics sampleSize 133 ### Source [Original source](https://api.github.com/repos/databricks/officeqa/git/blobs/a9992a78b86a0d400f1e3af8027fe5d3166eef97) Source officeqa pro Original model label Gemini 3.1 Pro Preview Source version sha256:4ea6f6e46bf4afc28634ec4b9abb54837c58c284e71ba077f6b8fbe11aa3be30 Observed 2026-10-21T16:34:42.039Z Evidence SHA-256 `cdd236761e2f624c8101365ba5094ad77fc80c32b05567db37384360b230f76a` Source locator `/chart-labels/6` |  |  |  |  |  |  |  |
| [Arena text / industry software and it services](https://benchize.com/benchmarks/lmarena%3Atext%3Aindustry_software_and_it_services.md) | 1,486.86 | — | 30 / 151 | — | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1486.8635013387693 \| rating \| reported \| Higher is better \| ### Configuration category industry_software_and_it_services config text ### Reported statistics lower 1482.8382298567876 rank 36 upper 1490.8887728207515 variance 4.217879524406956 votes 50815 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) Source Arena Original model label Gemini 3.1 Pro Preview Observed 2026-10-21T16:40:19.533Z Evidence SHA-256 `8e027ef69b8de06c4b2a8b217bfe816b1f1536269bb257fd295b4ef1ba8246ac` Source locator `/rows/6736/row` |  |  |  |  |  |  |  |
| [Arena vision style control / chinese](https://benchize.com/benchmarks/lmarena%3Avision_style_control%3Achinese.md) | 1,339.16 | — | 16 / 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` \| 1339.1615329208664 \| rating \| reported \| Higher is better \| ### Configuration category chinese config vision_style_control ### Reported statistics lower 1325.776481431936 rank 16 upper 1352.5465844097969 variance 46.63842871259689 votes 3186 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/vision_style_control/latest) Source Arena Original model label Gemini 3.1 Pro Preview Observed 2026-10-21T16:40:19.533Z Evidence SHA-256 `38568936995f36625aae49e9ea05557d55c1b1df9b2954f5c50cee523f26fe92` Source locator `/rows/216/row` |  |  |  |  |  |  |  |
| [OTIS Mock AIME 2024–2025](https://benchize.com/benchmarks/epoch-ai%3Aotis_mock_aime_2024_2025.md) | 95.6% | SE ±3.1 pp | 27 / 123 | — | — | [epoch ai · OTIS Mock AIME 2024-2025](https://epoch.ai/data/benchmark_data.zip#file=otis_mock_aime_2024_2025.csv) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `score` \| 0.956 \| score_fraction \| Best score (across scorers) \| Higher is better \| \| `mean_score` \| 0.956 \| score_fraction \| mean_score \| Higher is better \| ### Configuration benchmarkVersion OTIS Mock AIME 2024-2025 reasoningBudget Not reported Reasoning effort Not reported sourceModelVersion gemini-3.1-pro-preview ### Reported statistics Uncertainty Standard error: ±3.1 pp standardError 0.031 ### Source [Original source](https://epoch.ai/data/benchmark_data.zip#file=otis_mock_aime_2024_2025.csv) Source epoch ai Original model label gemini-3.1-pro-preview Source version OTIS Mock AIME 2024-2025 Evaluated 2026-02-20T04:39:36.998Z Observed 2026-10-21T16:30:24.199Z Evidence SHA-256 `5b411612f91e155dff4b09d09b548b42f7936482ea8b3c00b510bd46e2f6bc2c` Source locator `/rows/183` |  |  |  |  |  |  |  |
| [Arena text style control / math](https://benchize.com/benchmarks/lmarena%3Atext_style_control%3Amath.md) | 1,488.83 | — | 28 / 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` \| 1488.8336045156698 \| rating \| reported \| Higher is better \| ### Configuration category math config text_style_control ### Reported statistics lower 1480.91706856346 rank 31 upper 1496.7501404678796 variance 16.314516023188276 votes 6734 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label Gemini 3.1 Pro Preview Observed 2026-10-21T16:40:19.533Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/8943/row` |  |  |  |  |  |  |  |
| [OfficeQA Pro — Agent Harness](https://benchize.com/benchmarks/officeqa-pro%3Aagent.md) | 19.6% | — | 11 / 13 | — | — | [officeqa pro · sha256:07c23a70c189c84ab808067929402d3b636ce81e46520faca981a178e02065ad](https://api.github.com/repos/databricks/officeqa/git/blobs/125bf765bb37397a7a6b41a49ea04e6117eb95b8) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `correctness` \| 19.6 \| percent \| agent_full_tools \| Higher is better \| ### Configuration harness Gemini CLI ### Reported statistics sampleSize 133 ### Source [Original source](https://api.github.com/repos/databricks/officeqa/git/blobs/125bf765bb37397a7a6b41a49ea04e6117eb95b8) Source officeqa pro Original model label Gemini 3.1 Pro Preview Source version sha256:07c23a70c189c84ab808067929402d3b636ce81e46520faca981a178e02065ad Observed 2026-10-21T16:34:41.697Z Evidence SHA-256 `094af719408a1dea8ccb110965da3cc1b83056de87ba0b95e99bf603955f42b1` Source locator `/chart-labels/1` |  |  |  |  |  |  |  |
| [DesignArena Image to web application](https://benchize.com/benchmarks/designarena%3Aimage-to-webapp.md) | 1,118elo | SE ±11.83 | 21 / 24 | — | — | [designarena · public](https://www.designarena.ai/api/leaderboard#board=image-to-webapp) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `elo` \| 1118 \| elo \| image-to-webapp \| Higher is better \| ### Configuration arenaType agents category agon_webapps inputModality image sourceModelVersion gemini-3.1-pro-preview variationName public ### Reported statistics Uncertainty Standard error: ±11.83 averageGenerationTimeMs Not reported battles 1010 losses 559 standardError 11.8318 winRate 44.6 wins 451 ### Source [Original source](https://www.designarena.ai/api/leaderboard#board=image-to-webapp) Source designarena Original model label Gemini 3.1 Pro Preview Source version public Observed 2026-10-21T16:37:59.412Z Evidence SHA-256 `cc4e49fc057d3b786184ff44b697422e2420a174e8a98a80a77aa65021921ab4` Source locator `/data/25` |  |  |  |  |  |  |  |
| [DesignArena Data visualization generation](https://benchize.com/benchmarks/designarena%3Adata-viz.md) | 1,209elo | — | 45 / 99 | — | — | [designarena · public](https://www.designarena.ai/api/leaderboard#board=data-viz) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `elo` \| 1209 \| elo \| data-viz \| Higher is better \| ### Configuration arenaType models category dataviz inputModality Not reported sourceModelVersion gemini-3.1-pro-preview variationName public ### Reported statistics averageGenerationTimeMs 80390 battles 2418 losses 1157 standardError Not reported winRate 52.1 wins 1261 ### Source [Original source](https://www.designarena.ai/api/leaderboard#board=data-viz) Source designarena Original model label Gemini 3.1 Pro Preview Source version public Observed 2026-10-21T16:37:58.264Z Evidence SHA-256 `a895f6f1a25fa8eb01f821c2097ddec4f884de7bd22f1b8a22e82e6679b71849` Source locator `/data/69` |  |  |  |  |  |  |  |
| [ARC-AGI-2](https://benchize.com/benchmarks/arc-prize%3Av2_Semi_Private.md) | 77.08% | — | 42 / 212 | 0.96usd per task | — | [arc prize · v2](https://arcprize.org/media/data/leaderboard/v2.json) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `score` \| 0.7708 \| score_fraction \| v2_Semi_Private \| Higher is better \| \| `cost_per_task` \| 0.9622 \| usd_per_task \| v2_Semi_Private \| Lower is better \| ### Configuration evaluationSplit v2_Semi_Private harness Not reported modelGroup Not reported modelType CoT sourceModelVersion gemini-3-1-pro-preview ### Source [Original source](https://arcprize.org/media/data/leaderboard/v2.json) Source arc prize Original model label Gemini 3.1 Pro (Preview) Source version v2 Observed 2026-10-21T16:34:20.750Z Evidence SHA-256 `bca68e12cc9a01954ae21b641844c1ecbabe146cb24b87f0f8e9b1db27433c29` Source locator `/evaluations/126` |  |  |  |  |  |  |  |
| [Rapidata SVG generation — Preference](https://benchize.com/benchmarks/rapidata%3Asvg%3Arlb_1MFkkEMFnCNyKl.md) | 1,145.27elo | CI 1,130.84–1,159.69 | 14 / 37 | — | — | [rapidata · v1](https://api.rapidata.ai/benchmark/bmk_1MFkc3sXfbKCqf/standings/query?leaderboard_id%5Beq%5D=rlb_1MFkkEMFnCNyKl) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `elo` \| 1145.2653371815616 \| elo \| rlb_1MFkkEMFnCNyKl \| Higher is better \| ### Configuration benchmarkId bmk_1MFkc3sXfbKCqf criterion rlb_1MFkkEMFnCNyKl participantId par_1MFl49p61xwRyK sourceModelVersion gemini-3.1-pro-preview weighted false ### Reported statistics Uncertainty Confidence interval: 1,130.84–1,159.69 confidenceIntervalLowerOffset 14.427478595599268 confidenceIntervalUpperOffset 14.427478595599268 totalMatches 15027 wins 9955 ### Source [Original source](https://api.rapidata.ai/benchmark/bmk_1MFkc3sXfbKCqf/standings/query?leaderboard_id%5Beq%5D=rlb_1MFkkEMFnCNyKl) Source rapidata Original model label gemini-3.1-pro-preview Source version v1 Observed 2026-10-21T16:37:40.980Z Evidence SHA-256 `b70f07a4924c82499996aba613ca8ec2d0aee9ec9ebd404e45c8bf250206cf40` Source locator `/items/20` |  |  |  |  |  |  |  |
| [DesignArena Browser game generation](https://benchize.com/benchmarks/designarena%3Agame-dev.md) | 1,202elo | — | 45 / 117 | — | — | [designarena · public](https://www.designarena.ai/api/leaderboard#board=game-dev) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `elo` \| 1202 \| elo \| game-dev \| Higher is better \| ### Configuration arenaType models category gamedev inputModality Not reported sourceModelVersion gemini-3.1-pro-preview variationName public ### Reported statistics averageGenerationTimeMs 102888 battles 7075 losses 3385 standardError Not reported winRate 52.2 wins 3690 ### Source [Original source](https://www.designarena.ai/api/leaderboard#board=game-dev) Source designarena Original model label Gemini 3.1 Pro Preview Source version public Observed 2026-10-21T16:38:01.100Z Evidence SHA-256 `53db6a89112ce8cdf644568c666d4b8309aece764cfcedb291ffd52ae3934e30` Source locator `/data/71` |  |  |  |  |  |  |  |
| [Arena text / polish](https://benchize.com/benchmarks/lmarena%3Atext%3Apolish.md) | 1,497.68 | — | 10 / 117 | — | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1497.6810845879886 \| rating \| reported \| Higher is better \| ### Configuration category polish config text ### Reported statistics lower 1485.3608249682575 rank 10 upper 1510.0013442077197 variance 39.513321418385324 votes 2473 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) Source Arena Original model label Gemini 3.1 Pro Preview Observed 2026-10-21T16:40:19.533Z Evidence SHA-256 `8e027ef69b8de06c4b2a8b217bfe816b1f1536269bb257fd295b4ef1ba8246ac` Source locator `/rows/10157/row` |  |  |  |  |  |  |  |
| [Arena text style control / german](https://benchize.com/benchmarks/lmarena%3Atext_style_control%3Agerman.md) | 1,493.44 | — | 13 / 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` \| 1493.436984518109 \| rating \| reported \| Higher is better \| ### Configuration category german config text_style_control ### Reported statistics lower 1479.074010464508 rank 16 upper 1507.79995857171 variance 53.70226085806099 votes 2146 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label Gemini 3.1 Pro Preview Observed 2026-10-21T16:40:19.533Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/3152/row` |  |  |  |  |  |  |  |
| [Longform Creative Writing](https://benchize.com/benchmarks/eq-bench%3Alongform-writing.md) | 68.2% | — | 40 / 93 | — | — | [eq bench · longform-writing](https://eqbench.com/creative_writing_longform.js) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `overall_score_100` \| 68.2 \| percent \| overall \| Higher is better \| \| `chapter1_avg` \| 15.57 \| rubric_score \| overall \| Higher is better \| \| `chapter2_avg` \| 14.76 \| rubric_score \| overall \| Higher is better \| \| `chapter3_avg` \| 14.45 \| rubric_score \| overall \| Higher is better \| \| `chapter4_avg` \| 14.57 \| rubric_score \| overall \| Higher is better \| \| `chapter5_avg` \| 14.23 \| rubric_score \| overall \| Higher is better \| \| `chapter6_avg` \| 14.45 \| rubric_score \| overall \| Higher is better \| \| `chapter7_avg` \| 14.10 \| rubric_score \| overall \| Higher is better \| \| `chapter8_avg` \| 13.92 \| rubric_score \| overall \| Higher is better \| \| `final_judgement_avg` \| 13.15 \| rubric_score \| overall \| Higher is better \| ### Configuration interactiveAdjustments none protocol longform-writing sourceModelVersion gemini-3.1-pro-preview ### Source [Original source](https://eqbench.com/creative_writing_longform.js) Source eq bench Original model label gemini-3.1-pro-preview Source version longform-writing Observed 2026-10-21T16:35:02.575Z Evidence SHA-256 `3ba283ce357ac7620e16db640a961879c30fe3ddc50a27de9a8ed4290784825c` Source locator `/leaderboardDataLongformV3/89` |  |  |  |  |  |  |  |
| [NC Bench](https://benchize.com/benchmarks/nc-bench%3Aoverall.md) | 94.08% | — | 15 / 144 | — | — | [nc bench](https://www.nc-bench.com/models) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `score` \| 94.08 \| percent \| reported \| Higher is better \| \| `tooling` \| 99.92 \| percent \| category \| Higher is better \| \| `creative_writing` \| 85.44 \| percent \| category \| Higher is better \| \| `language` \| 94.9 \| percent \| category \| Higher is better \| \| `utility` \| 99.91 \| percent \| category \| Higher is better \| \| `reasoning` \| 88.2 \| percent \| category \| Higher is better \| \| `text_editing` \| 98.51 \| percent \| category \| Higher is better \| \| `rule_following` \| 91.21 \| percent \| category \| Higher is better \| \| `hallucination` \| 94.53 \| percent \| category \| Higher is better \| ### Configuration Reasoning effort unknown Model configuration Gemini 3.1 Pro (Preview) thinkingEnabled Not reported ### Source [Original source](https://www.nc-bench.com/models) Source nc bench Original model label Gemini 3.1 Pro (Preview) Observed 2026-10-21T16:31:48.370Z Evidence SHA-256 `ec261022458543624b08a136d01f5a2f0666cd52ffb49c64d6ca983e8543d1b5` Source locator `/rows/19` |  |  |  |  |  |  |  |
| [ArXivMath 12/2025](https://benchize.com/benchmarks/matharena%3Aarxiv--december.md) | 66.18% | 95% CI 58.23–74.13% | 1 / 12 | 0.33usd per problem | — | [matharena · arxiv--december](https://matharena.ai/competition_tables/arxiv--december) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 66.18 \| percent \| competition \| Higher is better \| \| `cost_per_problem` \| 0.33 \| usd_per_problem \| competition \| Lower is better \| ### Configuration competition arxiv--december predicted false sourceModelName Gemini 3.1 Pro Preview sourceModelVersion gemini/gemini-31-pro ### Reported statistics Uncertainty 95% confidence interval: 58.23–74.13% confidenceInterval95 7.95 problems 17 ### Source [Original source](https://matharena.ai/competition_tables/arxiv--december) Source matharena Original model label Gemini 3.1 Pro Preview Source version arxiv--december Observed 2026-10-21T16:52:26.934Z Evidence SHA-256 `6bbceef2706ad55e793e81bd959f7c1ec869f0ad04c6aa9013b2ad7b1a0820e3` Source locator `/table/rows/0` |  |  |  |  |  |  |  |
| [Arena text style control / expert](https://benchize.com/benchmarks/lmarena%3Atext_style_control%3Aexpert.md) | 1,508.65 | — | 28 / 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` \| 1508.6475217723935 \| rating \| reported \| Higher is better \| ### Configuration category expert config text_style_control ### Reported statistics lower 1502.4560395153708 rank 31 upper 1514.839004029416 variance 9.979139261500197 votes 13461 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label Gemini 3.1 Pro Preview Observed 2026-10-21T16:40:19.533Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/2501/row` |  |  |  |  |  |  |  |
| [Arena text / overall](https://benchize.com/benchmarks/lmarena%3Atext.md) | 1,480.07 | — | 19 / 151 | — | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1480.065736470125 \| rating \| reported \| Higher is better \| ### Configuration category overall config text ### Reported statistics lower 1477.1374902637838 rank 19 upper 1482.9939826764664 variance 2.232127492493376 votes 129523 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) Source Arena Original model label Gemini 3.1 Pro Preview Observed 2026-10-21T16:40:19.533Z Evidence SHA-256 `8e027ef69b8de06c4b2a8b217bfe816b1f1536269bb257fd295b4ef1ba8246ac` Source locator `/rows/18/row` |  |  |  |  |  |  |  |
| [Rapidata SVG generation — Coherence](https://benchize.com/benchmarks/rapidata%3Asvg%3Arlb_1MFkkBzpuU8fTG.md) | 922.23elo | CI 908.62–935.85 | 22 / 37 | — | — | [rapidata · v1](https://api.rapidata.ai/benchmark/bmk_1MFkc3sXfbKCqf/standings/query?leaderboard_id%5Beq%5D=rlb_1MFkkBzpuU8fTG) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `elo` \| 922.2308013422187 \| elo \| rlb_1MFkkBzpuU8fTG \| Higher is better \| ### Configuration benchmarkId bmk_1MFkc3sXfbKCqf criterion rlb_1MFkkBzpuU8fTG participantId par_1MFl49p61xwRyK sourceModelVersion gemini-3.1-pro-preview weighted false ### Reported statistics Uncertainty Confidence interval: 908.62–935.85 confidenceIntervalLowerOffset 13.614601573391496 confidenceIntervalUpperOffset 13.61460157339161 totalMatches 13753 wins 6514 ### Source [Original source](https://api.rapidata.ai/benchmark/bmk_1MFkc3sXfbKCqf/standings/query?leaderboard_id%5Beq%5D=rlb_1MFkkBzpuU8fTG) Source rapidata Original model label gemini-3.1-pro-preview Source version v1 Observed 2026-10-21T16:37:39.715Z Evidence SHA-256 `aa3cb94ff16f544c58adeea35b9087d281c785058b8ce1ae0f98a7ff84920930` Source locator `/items/47` |  |  |  |  |  |  |  |
| [OfficeQA Pro — Oracle PDF + Web Search](https://benchize.com/benchmarks/officeqa-pro%3Aoracle.md) | 68.42% | — | 9 / 12 | — | — | [officeqa pro · sha256:4ea6f6e46bf4afc28634ec4b9abb54837c58c284e71ba077f6b8fbe11aa3be30](https://api.github.com/repos/databricks/officeqa/git/blobs/a9992a78b86a0d400f1e3af8027fe5d3166eef97) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `correctness` \| 68.42 \| percent \| oracle_pdf_web_search \| Higher is better \| ### Configuration absoluteRelativeErrorPercent 1 harness Oracle PDF + Web Search oraclePages true webSearch true ### Reported statistics sampleSize 133 ### Source [Original source](https://api.github.com/repos/databricks/officeqa/git/blobs/a9992a78b86a0d400f1e3af8027fe5d3166eef97) Source officeqa pro Original model label Gemini 3.1 Pro Preview Source version sha256:4ea6f6e46bf4afc28634ec4b9abb54837c58c284e71ba077f6b8fbe11aa3be30 Observed 2026-10-21T16:34:42.039Z Evidence SHA-256 `cdd236761e2f624c8101365ba5094ad77fc80c32b05567db37384360b230f76a` Source locator `/chart-labels/5` |  |  |  |  |  |  |  |
| [Arena vision style control / humor](https://benchize.com/benchmarks/lmarena%3Avision_style_control%3Ahumor.md) | 1,299.96 | — | 3 / 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` \| 1299.9575798264525 \| rating \| reported \| Higher is better \| ### Configuration category humor config vision_style_control ### Reported statistics lower 1285.7189350986969 rank 4 upper 1314.196224554208 variance 52.776565660700136 votes 1885 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/vision_style_control/latest) Source Arena Original model label Gemini 3.1 Pro Preview Observed 2026-10-21T16:40:19.533Z Evidence SHA-256 `38568936995f36625aae49e9ea05557d55c1b1df9b2954f5c50cee523f26fe92` Source locator `/rows/929/row` |  |  |  |  |  |  |  |
| [Arena text style control / longer query](https://benchize.com/benchmarks/lmarena%3Atext_style_control%3Alonger_query.md) | 1,499.25 | — | 15 / 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` \| 1499.2450169606261 \| rating \| reported \| Higher is better \| ### Configuration category longer_query config text_style_control ### Reported statistics lower 1495.0921363126731 rank 16 upper 1503.3978976085793 variance 4.4895490180022835 votes 57242 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label Gemini 3.1 Pro Preview Observed 2026-10-21T16:40:19.533Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/8533/row` |  |  |  |  |  |  |  |
| [DesignArena Mobile application development](https://benchize.com/benchmarks/designarena%3Amobileapps.md) | 1,093elo | SE ±6.97 | 28 / 33 | — | — | [designarena · public](https://www.designarena.ai/api/leaderboard#board=mobileapps) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `elo` \| 1093 \| elo \| mobileapps \| Higher is better \| ### Configuration arenaType agents category mobileapps inputModality Not reported sourceModelVersion gemini-3.1-pro-preview variationName public ### Reported statistics Uncertainty Standard error: ±6.97 averageGenerationTimeMs Not reported battles 2925 losses 1669 standardError 6.9747 winRate 42.9 wins 1256 ### Source [Original source](https://www.designarena.ai/api/leaderboard#board=mobileapps) Source designarena Original model label Gemini 3.1 Pro Preview Source version public Observed 2026-10-21T16:38:02.538Z Evidence SHA-256 `40af33d0e93e729486da375cbe954633e2458af0dd6ca6d9fbdcda90da650f7d` Source locator `/data/43` |  |  |  |  |  |  |  |
| [Arena text / expert](https://benchize.com/benchmarks/lmarena%3Atext%3Aexpert.md) | 1,483.36 | — | 36 / 148 | — | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1483.3576869819694 \| rating \| reported \| Higher is better \| ### Configuration category expert config text ### Reported statistics lower 1477.2040697758855 rank 46 upper 1489.5113041880536 variance 9.857454286643055 votes 13461 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) Source Arena Original model label Gemini 3.1 Pro Preview Observed 2026-10-21T16:40:19.533Z Evidence SHA-256 `8e027ef69b8de06c4b2a8b217bfe816b1f1536269bb257fd295b4ef1ba8246ac` Source locator `/rows/2516/row` |  |  |  |  |  |  |  |
| [OfficeQA Pro — Oracle PDF + Web Search](https://benchize.com/benchmarks/officeqa-pro%3Aoracle.md) | 58.65% | — | 12 / 12 | — | — | [officeqa pro · sha256:4ea6f6e46bf4afc28634ec4b9abb54837c58c284e71ba077f6b8fbe11aa3be30](https://api.github.com/repos/databricks/officeqa/git/blobs/a9992a78b86a0d400f1e3af8027fe5d3166eef97) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `correctness` \| 58.65 \| percent \| oracle_pdf_web_search \| Higher is better \| ### Configuration absoluteRelativeErrorPercent 0 harness Oracle PDF + Web Search oraclePages true webSearch true ### Reported statistics sampleSize 133 ### Source [Original source](https://api.github.com/repos/databricks/officeqa/git/blobs/a9992a78b86a0d400f1e3af8027fe5d3166eef97) Source officeqa pro Original model label Gemini 3.1 Pro Preview Source version sha256:4ea6f6e46bf4afc28634ec4b9abb54837c58c284e71ba077f6b8fbe11aa3be30 Observed 2026-10-21T16:34:42.039Z Evidence SHA-256 `cdd236761e2f624c8101365ba5094ad77fc80c32b05567db37384360b230f76a` Source locator `/chart-labels/7` |  |  |  |  |  |  |  |
| [Arena text style control / korean](https://benchize.com/benchmarks/lmarena%3Atext_style_control%3Akorean.md) | 1,455.1 | — | 14 / 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` \| 1455.0953029275443 \| rating \| reported \| Higher is better \| ### Configuration category korean config text_style_control ### Reported statistics lower 1440.8531822074688 rank 17 upper 1469.3374236476202 variance 52.802336839461596 votes 2277 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label Gemini 3.1 Pro Preview Observed 2026-10-21T16:40:19.533Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/8250/row` |  |  |  |  |  |  |  |
| [FrontierMath (2025-02-28 private)](https://benchize.com/benchmarks/epoch-ai%3Afrontiermath.md) | 36.9% | SE ±2.8 pp | 6 / 18 | — | — | [epoch ai · FrontierMath-2025-02-28-Private](https://epoch.ai/data/benchmark_data.zip#file=frontiermath.csv) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `score` \| 0.369 \| score_fraction \| Best score (across scorers) \| Higher is better \| \| `mean_score` \| 0.369 \| score_fraction \| mean_score \| Higher is better \| ### Configuration benchmarkVersion FrontierMath-2025-02-28-Private reasoningBudget Not reported Reasoning effort Not reported sourceModelVersion gemini-3.1-pro-preview ### Reported statistics Uncertainty Standard error: ±2.8 pp standardError 0.028 ### Source [Original source](https://epoch.ai/data/benchmark_data.zip#file=frontiermath.csv) Source epoch ai Original model label gemini-3.1-pro-preview Source version FrontierMath-2025-02-28-Private Evaluated 2026-02-19T18:54:42.570Z Observed 2026-10-21T16:30:24.199Z Evidence SHA-256 `f5c92f0f0b9103abb02308fd428c0806e7c21b91e8a14d43edb8af77ce941598` Source locator `/rows/20` |  |  |  |  |  |  |  |
| [Arena text / exclude ties](https://benchize.com/benchmarks/lmarena%3Atext%3Aexclude_ties.md) | 1,489.75 | — | 20 / 151 | — | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1489.7506436568299 \| rating \| reported \| Higher is better \| ### Configuration category exclude_ties config text ### Reported statistics lower 1485.8382190805426 rank 20 upper 1493.6630682331174 variance 3.984701328224003 votes 97303 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) Source Arena Original model label Gemini 3.1 Pro Preview Observed 2026-10-21T16:40:19.533Z Evidence SHA-256 `8e027ef69b8de06c4b2a8b217bfe816b1f1536269bb257fd295b4ef1ba8246ac` Source locator `/rows/2073/row` |  |  |  |  |  |  |  |
| [TapTap Maker public](https://benchize.com/benchmarks/taptap-maker%3Apublic.md) | 59.48% | Range 58.62–60.4% | 24 / 26 | $0.7 | — | [taptap maker](https://maker.taptap.cn/leaderboard/data/editions/2026-10-18-v6-voxel.json) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `l2_pass_rate` \| 0.5948 \| score_fraction \| reported \| Higher is better \| \| `cost_per_case` \| 0.7007 \| USD \| per_case \| Lower is better \| ### Configuration datasetVersion 0.2.3 edition 2026-10-18-v6-voxel harness claude Reasoning effort unknown reasoningMode model-managed ### Reported statistics Uncertainty Reported interval: 58.62–60.4% interval [0.5862,0.604] intervalMethod bootstrap-case rank 32 rankInterval [32,32] ### Source [Original source](https://maker.taptap.cn/leaderboard/data/editions/2026-10-18-v6-voxel.json) Source taptap maker Original model label gemini-3.1-pro-preview Observed 2026-10-21T16:33:19.620Z Evidence SHA-256 `ad2d7f1adeae0548a4edc0b5e75d11449b443449ff76533d04bc1fb1b6d7035e` Source locator `/public/31` |  |  |  |  |  |  |  |
| [Arena vision style control / entity recognition](https://benchize.com/benchmarks/lmarena%3Avision_style_control%3Aentity_recognition.md) | 1,283.98 | — | 3 / 34 | — | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/vision_style_control/latest) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1283.9787158045426 \| rating \| reported \| Higher is better \| ### Configuration category entity_recognition config vision_style_control ### Reported statistics lower 1254.8697178950629 rank 3 upper 1313.0877137140226 variance 220.57603604377425 votes 388 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/vision_style_control/latest) Source Arena Original model label Gemini 3.1 Pro Preview Observed 2026-10-21T16:40:19.533Z Evidence SHA-256 `38568936995f36625aae49e9ea05557d55c1b1df9b2954f5c50cee523f26fe92` Source locator `/rows/759/row` |  |  |  |  |  |  |  |
| [Arena text style control / hard prompts](https://benchize.com/benchmarks/lmarena%3Atext_style_control%3Ahard_prompts.md) | 1,507.67 | — | 18 / 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` \| 1507.6733893220871 \| rating \| reported \| Higher is better \| ### Configuration category hard_prompts config text_style_control ### Reported statistics lower 1504.1030840564104 rank 19 upper 1511.2436945877637 variance 3.31829137968337 votes 84197 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label Gemini 3.1 Pro Preview Observed 2026-10-21T16:40:19.533Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/3469/row` |  |  |  |  |  |  |  |
| [Earthborne Rangers (EBR-bench)](https://benchize.com/benchmarks/epoch-ai%3Aebr_bench.md) | 14.29% | — | 12 / 13 | — | — | [epoch ai · EBR-bench](https://epoch.ai/data/benchmark_data.zip#file=ebr_bench.csv) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `score` \| 0.14285714285714285 \| score_fraction \| Best score (across scorers) \| Higher is better \| \| `mean_score` \| 0.14285714285714285 \| score_fraction \| mean_score \| Higher is better \| ### Configuration benchmarkVersion EBR-bench reasoningBudget Not reported Reasoning effort Not reported sourceModelVersion gemini-3.1-pro-preview ### Source [Original source](https://epoch.ai/data/benchmark_data.zip#file=ebr_bench.csv) Source epoch ai Original model label gemini-3.1-pro-preview Source version EBR-bench Evaluated 2026-06-25T01:42:49.000Z Observed 2026-10-21T16:30:24.199Z Evidence SHA-256 `15ec96ff8e424623e6a7452956d849312f595f2b5cb4ebe70ec47831f9087b44` Source locator `/rows/26` |  |  |  |  |  |  |  |
| [Arena vision / overall (config: vision)](https://benchize.com/benchmarks/benchmark%3Avision%3Aoverall--config-vision.md) | 1,295.78 | — | 21 / 82 | — | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/vision/latest) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1295.7822786391075 \| rating \| reported \| Higher is better \| ### Configuration category overall config vision ### Reported statistics lower 1290.6742454998869 rank 22 upper 1300.890311778328 variance 6.792211961460016 votes 47114 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/vision/latest) Source Arena Original model label Gemini 3.1 Pro Preview Observed 2026-10-21T16:40:19.533Z Evidence SHA-256 `06e61305486dce3fec5dc776ac2fd8321104e84c346cf9e08fa6f8e8a66ce0d7` Source locator `/rows/21/row` |  |  |  |  |  |  |  |
| [Vals Multimodal Index / swebench](https://benchize.com/benchmarks/vals-ai%3Avals_multimodal_index%3Aswebench.md) | 72.55% | SE ±4.42 pp | 15 / 20 | $0.82 | 329.2source duration | [Vals AI · 1.2](https://www.vals.ai/_astro/benchmark_view_vals_multimodal_index.virVpWMs.json) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 72.549 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.820116 \| USD \| per_test \| Lower is better \| \| `latency` \| 329.202 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens Not reported provider Not reported reasoning Not reported Reasoning effort unknown Temperature Not reported topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±4.42 pp sourcePopulation 33 stderr 4.419 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_vals_multimodal_index.virVpWMs.json) Source Vals AI Original model label google/gemini-3.1-pro-preview Source version 1.2 Observed 2026-10-21T16:45:51.881Z Evidence SHA-256 `077b22575f6e075b7b78157d000ec8f94d7ead409c7dcbcf04887630ed572a2d` Source locator `/tasks/swebench/google~1gemini-3.1-pro-preview` |  |  |  |  |  |  |  |
| [Arena vision / creative writing vision (config: vision)](https://benchize.com/benchmarks/benchmark%3Avision%3Acreative_writing_vision--config-vision.md) | 1,324.19 | — | 6 / 70 | — | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/vision/latest) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1324.1943654824238 \| rating \| reported \| Higher is better \| ### Configuration category creative_writing_vision config vision ### Reported statistics lower 1313.0189276173105 rank 7 upper 1335.3698033475368 variance 32.51119361327359 votes 3296 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/vision/latest) Source Arena Original model label Gemini 3.1 Pro Preview Observed 2026-10-21T16:40:19.533Z Evidence SHA-256 `06e61305486dce3fec5dc776ac2fd8321104e84c346cf9e08fa6f8e8a66ce0d7` Source locator `/rows/369/row` |  |  |  |  |  |  |  |
| [Arena vision / captioning (config: vision)](https://benchize.com/benchmarks/benchmark%3Avision%3Acaptioning--config-vision.md) | 1,344.89 | — | 1 / 22 | — | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/vision/latest) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1344.8857647933394 \| rating \| reported \| Higher is better \| ### Configuration category captioning config vision ### Reported statistics lower 1296.3373370450227 rank 1 upper 1393.434192541656 variance 613.5559293611411 votes 137 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/vision/latest) Source Arena Original model label Gemini 3.1 Pro Preview Observed 2026-10-21T16:40:19.533Z Evidence SHA-256 `06e61305486dce3fec5dc776ac2fd8321104e84c346cf9e08fa6f8e8a66ce0d7` Source locator `/rows/167/row` |  |  |  |  |  |  |  |
| [Arena vision / homework (config: vision)](https://benchize.com/benchmarks/benchmark%3Avision%3Ahomework--config-vision.md) | 1,316.25 | — | 22 / 73 | — | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/vision/latest) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1316.245485827796 \| rating \| reported \| Higher is better \| ### Configuration category homework config vision ### Reported statistics lower 1307.8752627212612 rank 23 upper 1324.615708934331 variance 18.23802834375058 votes 6293 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/vision/latest) Source Arena Original model label Gemini 3.1 Pro Preview Observed 2026-10-21T16:40:19.533Z Evidence SHA-256 `06e61305486dce3fec5dc776ac2fd8321104e84c346cf9e08fa6f8e8a66ce0d7` Source locator `/rows/830/row` |  |  |  |  |  |  |  |
| [Arena text / math](https://benchize.com/benchmarks/lmarena%3Atext%3Amath.md) | 1,485.86 | — | 25 / 149 | — | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1485.862512508663 \| rating \| reported \| Higher is better \| ### Configuration category math config text ### Reported statistics lower 1477.9486510442403 rank 29 upper 1493.7763739730858 variance 16.303494636123308 votes 6734 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) Source Arena Original model label Gemini 3.1 Pro Preview Observed 2026-10-21T16:40:19.533Z Evidence SHA-256 `8e027ef69b8de06c4b2a8b217bfe816b1f1536269bb257fd295b4ef1ba8246ac` Source locator `/rows/8941/row` |  |  |  |  |  |  |  |
| [DesignArena Agentic HTML slide generation](https://benchize.com/benchmarks/designarena%3Aagentic-html-slides.md) | 1,153elo | — | 8 / 13 | — | — | [designarena · public](https://www.designarena.ai/api/leaderboard#board=agentic-html-slides) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `elo` \| 1153 \| elo \| agentic-html-slides \| Higher is better \| ### Configuration arenaType agents category agon_slides_html inputModality Not reported sourceModelVersion gemini-3.1-pro-preview variationName public ### Reported statistics averageGenerationTimeMs 160039 battles 1979 losses 1017 standardError Not reported winRate 48.6 wins 962 ### Source [Original source](https://www.designarena.ai/api/leaderboard#board=agentic-html-slides) Source designarena Original model label Gemini 3.1 Pro Preview Source version public Observed 2026-10-21T16:38:04.391Z Evidence SHA-256 `02fccc0ebb2758ba116665bc1fcb2f049b9b2f1251c0f0bb29caed69ffaf0cb0` Source locator `/data/15` |  |  |  |  |  |  |  |
| [Arena text / instruction following](https://benchize.com/benchmarks/lmarena%3Atext%3Ainstruction_following.md) | 1,465.93 | — | 29 / 151 | — | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1465.9300308569264 \| rating \| reported \| Higher is better \| ### Configuration category instruction_following config text ### Reported statistics lower 1461.6955364035957 rank 36 upper 1470.164525310257 variance 4.6677431965932685 votes 44333 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) Source Arena Original model label Gemini 3.1 Pro Preview Observed 2026-10-21T16:40:19.533Z Evidence SHA-256 `8e027ef69b8de06c4b2a8b217bfe816b1f1536269bb257fd295b4ef1ba8246ac` Source locator `/rows/7569/row` |  |  |  |  |  |  |  |
| [Arena text style control / french](https://benchize.com/benchmarks/lmarena%3Atext_style_control%3Afrench.md) | 1,501.35 | — | 19 / 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` \| 1501.3545820061026 \| rating \| reported \| Higher is better \| ### Configuration category french config text_style_control ### Reported statistics lower 1490.2278784564464 rank 23 upper 1512.4812855557589 variance 32.2282595390566 votes 4283 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label Gemini 3.1 Pro Preview Observed 2026-10-21T16:40:19.533Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/2860/row` |  |  |  |  |  |  |  |
| [Arena text / german](https://benchize.com/benchmarks/lmarena%3Atext%3Agerman.md) | 1,490.03 | — | 13 / 129 | — | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1490.030116608607 \| rating \| reported \| Higher is better \| ### Configuration category german config text ### Reported statistics lower 1475.725415100958 rank 14 upper 1504.334818116256 variance 53.26739001355874 votes 2146 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) Source Arena Original model label Gemini 3.1 Pro Preview Observed 2026-10-21T16:40:19.533Z Evidence SHA-256 `8e027ef69b8de06c4b2a8b217bfe816b1f1536269bb257fd295b4ef1ba8246ac` Source locator `/rows/3150/row` |  |  |  |  |  |  |  |
| [Arena text style control / industry legal and government](https://benchize.com/benchmarks/lmarena%3Atext_style_control%3Aindustry_legal_and_government.md) | 1,498.59 | — | 14 / 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` \| 1498.5912864428342 \| rating \| reported \| Higher is better \| ### Configuration category industry_legal_and_government config text_style_control ### Reported statistics lower 1491.8352099922188 rank 16 upper 1505.3473628934498 variance 11.882092490663105 votes 10646 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label Gemini 3.1 Pro Preview Observed 2026-10-21T16:40:19.533Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/5123/row` |  |  |  |  |  |  |  |
| [Arena vision style control / english](https://benchize.com/benchmarks/lmarena%3Avision_style_control%3Aenglish.md) | 1,272.38 | — | 30 / 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` \| 1272.3793051619923 \| rating \| reported \| Higher is better \| ### Configuration category english config vision_style_control ### Reported statistics lower 1265.337307919501 rank 35 upper 1279.4213024044836 variance 12.90908675009403 votes 18497 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/vision_style_control/latest) Source Arena Original model label Gemini 3.1 Pro Preview Observed 2026-10-21T16:40:19.533Z Evidence SHA-256 `38568936995f36625aae49e9ea05557d55c1b1df9b2954f5c50cee523f26fe92` Source locator `/rows/624/row` |  |  |  |  |  |  |  |
| [Arena vision / diagram (config: vision)](https://benchize.com/benchmarks/benchmark%3Avision%3Adiagram--config-vision.md) | 1,310.54 | — | 24 / 74 | — | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/vision/latest) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1310.5356994499275 \| rating \| reported \| Higher is better \| ### Configuration category diagram config vision ### Reported statistics lower 1303.6659767213096 rank 25 upper 1317.405422178546 variance 12.28520012081332 votes 12416 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/vision/latest) Source Arena Original model label Gemini 3.1 Pro Preview Observed 2026-10-21T16:40:19.533Z Evidence SHA-256 `06e61305486dce3fec5dc776ac2fd8321104e84c346cf9e08fa6f8e8a66ce0d7` Source locator `/rows/491/row` |  |  |  |  |  |  |  |
| [DesignArena Website generation](https://benchize.com/benchmarks/designarena%3Awebsite.md) | 1,234elo | — | 43 / 123 | — | — | [designarena · public](https://www.designarena.ai/api/leaderboard#board=website) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `elo` \| 1234 \| elo \| website \| Higher is better \| ### Configuration arenaType models category website inputModality text sourceModelVersion gemini-3.1-pro-preview variationName public ### Reported statistics averageGenerationTimeMs 102333 battles 28255 losses 13048 standardError Not reported winRate 53.8 wins 15207 ### Source [Original source](https://www.designarena.ai/api/leaderboard#board=website) Source designarena Original model label Gemini 3.1 Pro Preview Source version public Observed 2026-10-21T16:37:57.757Z Evidence SHA-256 `51873e97776a3c5ae706b24cc2c60384793dd18398df970e213a8e7c276d8ac0` Source locator `/data/69` |  |  |  |  |  |  |  |
| [MultiChallenge](https://benchize.com/benchmarks/scale%3Amultichallenge.md) | 71.37source score | CI 69.63–73.11 | 3 / 11 | — | — | [scale](https://labs.scale.com/leaderboard/multichallenge) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `score` \| 71.37 \| source_score \| reported \| Higher is better \| ### Configuration Reasoning effort unknown Model configuration gemini-3.1-pro-preview sourceModelVersion Not reported thinkingEnabled Not reported ### Reported statistics Uncertainty Confidence interval: 69.63–73.11 contaminationWarning Not reported rank 4 reportedConfidenceHalfWidth 1.7366 ### Source [Original source](https://labs.scale.com/leaderboard/multichallenge) Source scale Original model label gemini-3.1-pro-preview Observed 2026-10-21T16:35:37.135Z Evidence SHA-256 `92e84e933979bccb14193567e45702ffc95189cc48216f6af220e7e235bfa3a0` Source locator `/rows/3` |  |  |  |  |  |  |  |
| [DesignArena Overall frontend coding](https://benchize.com/benchmarks/designarena%3Acode.md) | 1,231elo | SE ±1.78 | 41 / 116 | — | — | [designarena · public](https://www.designarena.ai/api/leaderboard#board=code) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `elo` \| 1231 \| elo \| code \| Higher is better \| ### Configuration arenaType models category allcategories inputModality text sourceModelVersion gemini-3.1-pro-preview variationName public ### Reported statistics Uncertainty Standard error: ±1.78 averageGenerationTimeMs 98288 battles 47246 losses 21557 standardError 1.7824 winRate 54.4 wins 25689 ### Source [Original source](https://www.designarena.ai/api/leaderboard#board=code) Source designarena Original model label Gemini 3.1 Pro Preview Source version public Observed 2026-10-21T16:37:57.301Z Evidence SHA-256 `0c897b58670f5e352bd123db999a40c0d1781a443964c502b90774a76a3a7758` Source locator `/data/66` |  |  |  |  |  |  |  |
| [Arena text style control / japanese](https://benchize.com/benchmarks/lmarena%3Atext_style_control%3Ajapanese.md) | 1,494.99 | — | 12 / 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` \| 1494.9853302853458 \| rating \| reported \| Higher is better \| ### Configuration category japanese config text_style_control ### Reported statistics lower 1477.8108845425122 rank 13 upper 1512.1597760281795 variance 76.78374293238919 votes 1582 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label Gemini 3.1 Pro Preview Observed 2026-10-21T16:40:19.533Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/7963/row` |  |  |  |  |  |  |  |
| [Arena text / industry legal and government](https://benchize.com/benchmarks/lmarena%3Atext%3Aindustry_legal_and_government.md) | 1,486.73 | — | 21 / 151 | — | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1486.7306016194632 \| rating \| reported \| Higher is better \| ### Configuration category industry_legal_and_government config text ### Reported statistics lower 1480.0280518875793 rank 22 upper 1493.4331513513473 variance 11.694560583695354 votes 10646 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) Source Arena Original model label Gemini 3.1 Pro Preview Observed 2026-10-21T16:40:19.533Z Evidence SHA-256 `8e027ef69b8de06c4b2a8b217bfe816b1f1536269bb257fd295b4ef1ba8246ac` Source locator `/rows/5129/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) | 1,469.54 | — | 13 / 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` \| 1469.53768319961 \| rating \| reported \| Higher is better \| ### Configuration category industry_entertainment_and_sports_and_media config text_style_control ### Reported statistics lower 1464.6181052572672 rank 13 upper 1474.4572611419528 variance 6.300275041452443 votes 30047 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label Gemini 3.1 Pro Preview Observed 2026-10-21T16:40:19.533Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/4705/row` |  |  |  |  |  |  |  |
| [Arena text / hard prompts](https://benchize.com/benchmarks/lmarena%3Atext%3Ahard_prompts.md) | 1,484.67 | — | 27 / 151 | — | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1484.6685727691902 \| rating \| reported \| Higher is better \| ### Configuration category hard_prompts config text ### Reported statistics lower 1481.1154976003245 rank 30 upper 1488.2216479380554 variance 3.2863408785226076 votes 84197 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) Source Arena Original model label Gemini 3.1 Pro Preview Observed 2026-10-21T16:40:19.533Z Evidence SHA-256 `8e027ef69b8de06c4b2a8b217bfe816b1f1536269bb257fd295b4ef1ba8246ac` Source locator `/rows/3480/row` |  |  |  |  |  |  |  |
| [DesignArena Agentic web applications](https://benchize.com/benchmarks/designarena%3Awebapps.md) | 1,125elo | SE ±4.9 | 29 / 39 | — | — | [designarena · public](https://www.designarena.ai/api/leaderboard#board=webapps) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `elo` \| 1125 \| elo \| webapps \| Higher is better \| ### Configuration arenaType agents category agon_webapps inputModality text sourceModelVersion gemini-3.1-pro-preview variationName public ### Reported statistics Uncertainty Standard error: ±4.9 averageGenerationTimeMs Not reported battles 6648 losses 3701 standardError 4.8982 winRate 44.3 wins 2947 ### Source [Original source](https://www.designarena.ai/api/leaderboard#board=webapps) Source designarena Original model label Gemini 3.1 Pro Preview Source version public Observed 2026-10-21T16:38:00.309Z Evidence SHA-256 `f955787274cf4ac627ada7cd33eaae2e08ef7297db92d3391340fcaa0b44a35f` Source locator `/data/39` |  |  |  |  |  |  |  |
| [BrokenArXiv 02/2026](https://benchize.com/benchmarks/matharena%3Aarxiv_false--february.md) | 18.55% | 95% CI 11.71–25.39% | 5 / 15 | 0.32usd per problem | — | [matharena · arxiv_false--february](https://matharena.ai/competition_tables/arxiv_false--february) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 18.55 \| percent \| competition \| Higher is better \| \| `cost_per_problem` \| 0.32 \| usd_per_problem \| competition \| Lower is better \| ### Configuration competition arxiv_false--february predicted false sourceModelName Gemini 3.1 Pro Preview sourceModelVersion gemini/gemini-31-pro ### Reported statistics Uncertainty 95% confidence interval: 11.71–25.39% confidenceInterval95 6.84 problems 31 ### Source [Original source](https://matharena.ai/competition_tables/arxiv_false--february) Source matharena Original model label Gemini 3.1 Pro Preview Source version arxiv_false--february Observed 2026-10-21T16:52:23.532Z Evidence SHA-256 `a6bc6fc18da7dd181ed727da924f9569d3e323c31c1aba9a4d9fa3bff492bee3` Source locator `/table/rows/4` |  |  |  |  |  |  |  |
| [MASK](https://benchize.com/benchmarks/scale%3Amask.md) | 42.4source score | CI 41.1–43.7 | 25 / 25 | — | — | [scale](https://labs.scale.com/leaderboard/mask) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `score` \| 42.4 \| source_score \| reported \| Higher is better \| ### Configuration Reasoning effort unknown Model configuration gemini-3.1-pro-preview sourceModelVersion gemini-3.1-pro-preview thinkingEnabled Not reported ### Reported statistics Uncertainty Confidence interval: 41.1–43.7 contaminationWarning Potential contamination warning: This model was evaluated after the public release of MASK, allowing model builder access to the prompts and solutions. rank 67 reportedConfidenceHalfWidth 1.3 ### Source [Original source](https://labs.scale.com/leaderboard/mask) Source scale Original model label gemini-3.1-pro-preview Observed 2026-10-21T16:35:38.046Z Evidence SHA-256 `506198f10b9789b267cc2a11dcdfedc27067703da430d78b374b2c5dffb8ec7d` Source locator `/rows/66` |  |  |  |  |  |  |  |
| [HMMT Feb 2026](https://benchize.com/benchmarks/matharena%3Ahmmt--hmmt_feb_2026.md) | 94.7% | 95% CI 90.88–98.52% | 7 / 21 | 0.2usd per problem | — | [matharena · hmmt--hmmt_feb_2026](https://matharena.ai/competition_tables/hmmt--hmmt_feb_2026) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 94.70 \| percent \| competition \| Higher is better \| \| `cost_per_problem` \| 0.20 \| usd_per_problem \| competition \| Lower is better \| ### Configuration competition hmmt--hmmt_feb_2026 predicted false sourceModelName Gemini 3.1 Pro Preview sourceModelVersion gemini/gemini-31-pro ### Reported statistics Uncertainty 95% confidence interval: 90.88–98.52% confidenceInterval95 3.82 problems 33 ### Source [Original source](https://matharena.ai/competition_tables/hmmt--hmmt_feb_2026) Source matharena Original model label Gemini 3.1 Pro Preview Source version hmmt--hmmt_feb_2026 Observed 2026-10-21T16:52:38.351Z Evidence SHA-256 `0dce922c33a54d29d4a1872a42d74077b491915c80d8433f4b379ea0b78bb979` Source locator `/table/rows/8` |  |  |  |  |  |  |  |
| [Arena text style control / overall](https://benchize.com/benchmarks/lmarena%3Atext_style_control%3Aoverall.md) | 1,486.84 | — | 17 / 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` \| 1486.8403016524562 \| rating \| reported \| Higher is better \| ### Configuration category overall config text_style_control ### Reported statistics lower 1483.897436106615 rank 19 upper 1489.7831671982976 variance 2.2544710291426973 votes 129523 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label Gemini 3.1 Pro Preview Observed 2026-10-21T16:40:19.533Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/18/row` |  |  |  |  |  |  |  |
| [DesignArena Agentic presentation generation](https://benchize.com/benchmarks/designarena%3Aagentic-slides.md) | 1,066elo | SE ±10.35 | 19 / 19 | — | — | [designarena · public](https://www.designarena.ai/api/leaderboard#board=agentic-slides) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `elo` \| 1066 \| elo \| agentic-slides \| Higher is better \| ### Configuration arenaType agents category agon_slides inputModality Not reported sourceModelVersion gemini-3.1-pro-preview variationName public ### Reported statistics Uncertainty Standard error: ±10.35 averageGenerationTimeMs 270196 battles 1359 losses 883 standardError 10.3498 winRate 35 wins 476 ### Source [Original source](https://www.designarena.ai/api/leaderboard#board=agentic-slides) Source designarena Original model label Gemini 3.1 Pro Preview Source version public Observed 2026-10-21T16:38:03.963Z Evidence SHA-256 `b732c5aba2e357cf6034f23084d5f95f8e8882f62b8bf3ee340f0cd5cd773724` Source locator `/data/28` |  |  |  |  |  |  |  |
| [Judgemark v4](https://benchize.com/benchmarks/eq-bench%3Ajudgemark-v4.md) | 78.69% | CI 73.89–85.14% | 8 / 38 | — | — | [eq bench · judgemark-v4](https://eqbench.com/judgemark-v4.js) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `score` \| 0.786853 \| score_fraction \| overall \| Higher is better \| ### Configuration interactiveAdjustments none protocol judgemark-v4 sourceModelVersion gemini-3.1-pro-preview ### Reported statistics Uncertainty Confidence interval: 73.89–85.14% confidenceIntervalHigh 0.851353 confidenceIntervalLow 0.738905 ### Source [Original source](https://eqbench.com/judgemark-v4.js) Source eq bench Original model label gemini-3.1-pro-preview Source version judgemark-v4 Observed 2026-10-21T16:35:03.901Z Evidence SHA-256 `2b0d42aef4f614dd199dc38399be7b88075a919db52020c3759f190defc92a4d` Source locator `/leaderboardDataJudgemarkV4/7` |  |  |  |  |  |  |  |
| [Arena text style control / english](https://benchize.com/benchmarks/lmarena%3Atext_style_control%3Aenglish.md) | 1,489.87 | — | 20 / 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` \| 1489.8673955495985 \| rating \| reported \| Higher is better \| ### Configuration category english config text_style_control ### Reported statistics lower 1485.9572393611472 rank 23 upper 1493.7775517380499 variance 3.980082081244576 votes 56774 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label Gemini 3.1 Pro Preview Observed 2026-10-21T16:40:19.533Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/1659/row` |  |  |  |  |  |  |  |
| [ArXivMath 04/2026](https://benchize.com/benchmarks/matharena%3Aarxiv--april.md) | 63.75% | 95% CI 53.22–74.28% | 6 / 19 | 0.32usd per problem | — | [matharena · arxiv--april](https://matharena.ai/competition_tables/arxiv--april) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 63.75 \| percent \| competition \| Higher is better \| \| `cost_per_problem` \| 0.32 \| usd_per_problem \| competition \| Lower is better \| ### Configuration competition arxiv--april predicted false sourceModelName Gemini 3.1 Pro Preview sourceModelVersion gemini/gemini-31-pro ### Reported statistics Uncertainty 95% confidence interval: 53.22–74.28% confidenceInterval95 10.53 problems 40 ### Source [Original source](https://matharena.ai/competition_tables/arxiv--april) Source matharena Original model label Gemini 3.1 Pro Preview Source version arxiv--april Observed 2026-10-21T16:52:28.840Z Evidence SHA-256 `5139c835884bfab38f18d23a248814af4680927310bc5cd2a86ea2eab779e0a7` Source locator `/table/rows/6` |  |  |  |  |  |  |  |

[Next page](https://benchize.com/models/gemini-3-1-pro-preview.md?cursor=90d64803732d6f5b789b04108512c6ee333977ea8701441969bb5857f5b12c7d)

---
Cite as: Gemini 3.1 Pro Preview — Benchize, https://benchize.com/models/gemini-3-1-pro-preview (retrieved 2026-10-21)