# GPT-5 MiniHigh

> Source: Benchize (https://benchize.com) — https://benchize.com/models/gpt-5-mini-high. When citing or reusing this content, credit "Benchize" and link to https://benchize.com/models/gpt-5-mini-high.

OpenAI

Canonical URL: https://benchize.com/models/gpt-5-mini-high
Last updated: Thu, 22 Oct 2026 07:32:33 GMT

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

OpenAI

## Benchmarks

| Benchmark | Score | ± | Rank | Cost | Source |  |
| --- | --- | --- | --- | --- | --- | --- |
| [Arena vision style control / captioning](https://benchize.com/benchmarks/lmarena%3Avision_style_control%3Acaptioning.md) | 1,175.17 | — | 16 / 24 | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/vision_style_control/latest) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1175.1710880182416 \| rating \| reported \| Higher is better \| ### Configuration category captioning config vision_style_control Reasoning effort high thinkingEnabled true ### Reported statistics lower 1132.3016498833047 rank 22 upper 1218.0405261531785 variance 478.4090658749028 votes 283 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/vision_style_control/latest) Source Arena Original model label GPT-5 mini (High) Observed 2026-10-22T06:45:03.380Z Evidence SHA-256 `38568936995f36625aae49e9ea05557d55c1b1df9b2954f5c50cee523f26fe92` Source locator `/rows/188/row` |  |  |  |  |  |  |
| [Arena text style control / multi turn](https://benchize.com/benchmarks/lmarena%3Atext_style_control%3Amulti_turn.md) | 1,372.82 | — | 120 / 173 | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1372.8218186236838 \| rating \| reported \| Higher is better \| ### Configuration category multi_turn config text_style_control Reasoning effort high thinkingEnabled true ### Reported statistics lower 1363.431010616411 rank 194 upper 1382.2126266309567 variance 22.956714921527198 votes 4394 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label GPT-5 mini (High) Observed 2026-10-22T06:45:03.380Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/9509/row` |  |  |  |  |  |  |
| [Apex](https://benchize.com/benchmarks/matharena%3Aapex--apex_2025.md) | 1.04% | 95% CI -0.4–2.48% | 22 / 31 | 0.07usd per problem | [matharena · apex--apex_2025](https://matharena.ai/competition_tables/apex--apex_2025) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 1.04 \| percent \| competition \| Higher is better \| \| `cost_per_problem` \| 0.070 \| usd_per_problem \| competition \| Lower is better \| ### Configuration competition apex--apex_2025 predicted false Reasoning effort high sourceModelName GPT-5-mini (high) sourceModelVersion openai/gpt-5-mini thinkingEnabled true ### Reported statistics Uncertainty 95% confidence interval: -0.4–2.48% confidenceInterval95 1.44 problems 12 ### Source [Original source](https://matharena.ai/competition_tables/apex--apex_2025) Source matharena Original model label GPT-5-mini (high) Source version apex--apex_2025 Observed 2026-10-22T05:30:13.849Z Evidence SHA-256 `20b28370d9d7f5a15a19fc9e4226c9857cdb07bc42b32ccec508e687b7b9f3fc` Source locator `/table/rows/36` |  |  |  |  |  |  |
| [Arena vision style control / overall](https://benchize.com/benchmarks/lmarena%3Avision_style_control%3Aoverall.md) | 1,184.32 | — | 76 / 92 | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/vision_style_control/latest) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1184.315668593404 \| rating \| reported \| Higher is better \| ### Configuration category overall config vision_style_control Reasoning effort high thinkingEnabled true ### Reported statistics lower 1176.2198712850536 rank 104 upper 1192.4114659017546 variance 17.061730222075205 votes 28943 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/vision_style_control/latest) Source Arena Original model label GPT-5 mini (High) Observed 2026-10-22T06:45:03.380Z Evidence SHA-256 `38568936995f36625aae49e9ea05557d55c1b1df9b2954f5c50cee523f26fe92` Source locator `/rows/103/row` |  |  |  |  |  |  |
| [Arena text / creative writing](https://benchize.com/benchmarks/lmarena%3Atext%3Acreative_writing.md) | 1,325.21 | — | 124 / 173 | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1325.2074368477136 \| rating \| reported \| Higher is better \| ### Configuration category creative_writing config text Reasoning effort high thinkingEnabled true ### Reported statistics lower 1314.9940231126093 rank 196 upper 1335.4208505828178 variance 27.154741204688836 votes 3522 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) Source Arena Original model label GPT-5 mini (High) Observed 2026-10-22T06:45:03.380Z Evidence SHA-256 `8e027ef69b8de06c4b2a8b217bfe816b1f1536269bb257fd295b4ef1ba8246ac` Source locator `/rows/1417/row` |  |  |  |  |  |  |
| [Arena vision style control / diagram](https://benchize.com/benchmarks/lmarena%3Avision_style_control%3Adiagram.md) | 1,213.01 | — | 75 / 84 | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/vision_style_control/latest) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1213.0128085079127 \| rating \| reported \| Higher is better \| ### Configuration category diagram config vision_style_control Reasoning effort high thinkingEnabled true ### Reported statistics lower 1197.7105421889146 rank 96 upper 1228.3150748269104 variance 60.95584136841663 votes 1936 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/vision_style_control/latest) Source Arena Original model label GPT-5 mini (High) Observed 2026-10-22T06:45:03.380Z Evidence SHA-256 `38568936995f36625aae49e9ea05557d55c1b1df9b2954f5c50cee523f26fe92` Source locator `/rows/562/row` |  |  |  |  |  |  |
| [Arena vision / overall (config: vision)](https://benchize.com/benchmarks/benchmark%3Avision%3Aoverall--config-vision.md) | 1,202.23 | — | 75 / 92 | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/vision/latest) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1202.226332986973 \| rating \| reported \| Higher is better \| ### Configuration category overall config vision Reasoning effort high thinkingEnabled true ### Reported statistics lower 1194.4235813474256 rank 93 upper 1210.0290846265202 variance 15.848909487322556 votes 28943 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/vision/latest) Source Arena Original model label GPT-5 mini (High) Observed 2026-10-22T06:45:03.380Z Evidence SHA-256 `06e61305486dce3fec5dc776ac2fd8321104e84c346cf9e08fa6f8e8a66ce0d7` Source locator `/rows/92/row` |  |  |  |  |  |  |
| [Arena text style control / chinese](https://benchize.com/benchmarks/lmarena%3Atext_style_control%3Achinese.md) | 1,403.23 | — | 122 / 168 | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1403.2318832917767 \| rating \| reported \| Higher is better \| ### Configuration category chinese config text_style_control Reasoning effort high thinkingEnabled true ### Reported statistics lower 1389.1892459257538 rank 184 upper 1417.2745206578 variance 51.33353587739274 votes 1949 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label GPT-5 mini (High) Observed 2026-10-22T06:45:03.380Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/600/row` |  |  |  |  |  |  |
| [Arena vision / ocr (config: vision)](https://benchize.com/benchmarks/benchmark%3Avision%3Aocr--config-vision.md) | 1,198.57 | — | 76 / 84 | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/vision/latest) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1198.569579963165 \| rating \| reported \| Higher is better \| ### Configuration category ocr config vision Reasoning effort high thinkingEnabled true ### Reported statistics lower 1188.2596432261182 rank 94 upper 1208.8795167002122 variance 27.67042430581207 votes 7999 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/vision/latest) Source Arena Original model label GPT-5 mini (High) Observed 2026-10-22T06:45:03.380Z Evidence SHA-256 `06e61305486dce3fec5dc776ac2fd8321104e84c346cf9e08fa6f8e8a66ce0d7` Source locator `/rows/1112/row` |  |  |  |  |  |  |
| [SMT 2025](https://benchize.com/benchmarks/matharena%3Asmt--smt_2025.md) | 89.15% | 95% CI 84.96–93.34% | 10 / 26 | 0.02usd per problem | [matharena · smt--smt_2025](https://matharena.ai/competition_tables/smt--smt_2025) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 89.15 \| percent \| competition \| Higher is better \| \| `cost_per_problem` \| 0.024 \| usd_per_problem \| competition \| Lower is better \| ### Configuration competition smt--smt_2025 predicted false Reasoning effort high sourceModelName GPT-5-mini (high) sourceModelVersion openai/gpt-5-mini thinkingEnabled true ### Reported statistics Uncertainty 95% confidence interval: 84.96–93.34% confidenceInterval95 4.19 problems 53 ### Source [Original source](https://matharena.ai/competition_tables/smt--smt_2025) Source matharena Original model label GPT-5-mini (high) Source version smt--smt_2025 Observed 2026-10-22T05:30:12.647Z Evidence SHA-256 `1b4f6f8bafc1688e4557a024513f68befa31aff48fd0623fb4892a61263433b0` Source locator `/table/rows/12` |  |  |  |  |  |  |
| [Arena text style control / industry medicine and healthcare](https://benchize.com/benchmarks/lmarena%3Atext_style_control%3Aindustry_medicine_and_healthcare.md) | 1,407.23 | — | 114 / 173 | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1407.2338447181376 \| rating \| reported \| Higher is better \| ### Configuration category industry_medicine_and_healthcare config text_style_control Reasoning effort high thinkingEnabled true ### Reported statistics lower 1391.104876495216 rank 180 upper 1423.3628129410592 variance 67.72000640345506 votes 1436 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label GPT-5 mini (High) Observed 2026-10-22T06:45:03.380Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/6492/row` |  |  |  |  |  |  |
| [Arena vision style control / homework](https://benchize.com/benchmarks/lmarena%3Avision_style_control%3Ahomework.md) | 1,234.46 | — | 71 / 83 | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/vision_style_control/latest) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1234.4635126908158 \| rating \| reported \| Higher is better \| ### Configuration category homework config vision_style_control Reasoning effort high thinkingEnabled true ### Reported statistics lower 1214.7389126496678 rank 87 upper 1254.1881127319639 variance 101.27919234416335 votes 976 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/vision_style_control/latest) Source Arena Original model label GPT-5 mini (High) Observed 2026-10-22T06:45:03.380Z Evidence SHA-256 `38568936995f36625aae49e9ea05557d55c1b1df9b2954f5c50cee523f26fe92` Source locator `/rows/894/row` |  |  |  |  |  |  |
| [Arena text / polish](https://benchize.com/benchmarks/lmarena%3Atext%3Apolish.md) | 1,378.11 | — | 98 / 137 | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1378.1097256802334 \| rating \| reported \| Higher is better \| ### Configuration category polish config text Reasoning effort high thinkingEnabled true ### Reported statistics lower 1362.6539746708947 rank 144 upper 1393.565476689572 variance 62.184771570585184 votes 1562 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) Source Arena Original model label GPT-5 mini (High) Observed 2026-10-22T06:45:03.380Z Evidence SHA-256 `8e027ef69b8de06c4b2a8b217bfe816b1f1536269bb257fd295b4ef1ba8246ac` Source locator `/rows/10291/row` |  |  |  |  |  |  |
| [Arena text / english](https://benchize.com/benchmarks/lmarena%3Atext%3Aenglish.md) | 1,378.86 | — | 125 / 173 | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1378.8601967632826 \| rating \| reported \| Higher is better \| ### Configuration category english config text Reasoning effort high thinkingEnabled true ### Reported statistics lower 1372.6982654409162 rank 192 upper 1385.022128085649 variance 9.88410897886427 votes 11473 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) Source Arena Original model label GPT-5 mini (High) Observed 2026-10-22T06:45:03.380Z Evidence SHA-256 `8e027ef69b8de06c4b2a8b217bfe816b1f1536269bb257fd295b4ef1ba8246ac` Source locator `/rows/1828/row` |  |  |  |  |  |  |
| [Arena text / coding](https://benchize.com/benchmarks/lmarena%3Atext%3Acoding.md) | 1,405.84 | — | 113 / 173 | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1405.8398944330172 \| rating \| reported \| Higher is better \| ### Configuration category coding config text Reasoning effort high thinkingEnabled true ### Reported statistics lower 1397.5405109799613 rank 169 upper 1414.1392778860734 variance 17.930627117438505 votes 5516 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) Source Arena Original model label GPT-5 mini (High) Observed 2026-10-22T06:45:03.380Z Evidence SHA-256 `8e027ef69b8de06c4b2a8b217bfe816b1f1536269bb257fd295b4ef1ba8246ac` Source locator `/rows/978/row` |  |  |  |  |  |  |
| [Arena vision style control / ocr](https://benchize.com/benchmarks/lmarena%3Avision_style_control%3Aocr.md) | 1,198.95 | — | 76 / 84 | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/vision_style_control/latest) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1198.954279203454 \| rating \| reported \| Higher is better \| ### Configuration category ocr config vision_style_control Reasoning effort high thinkingEnabled true ### Reported statistics lower 1188.4052942133942 rank 98 upper 1209.5032641935136 variance 28.968443894550827 votes 7999 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/vision_style_control/latest) Source Arena Original model label GPT-5 mini (High) Observed 2026-10-22T06:45:03.380Z Evidence SHA-256 `38568936995f36625aae49e9ea05557d55c1b1df9b2954f5c50cee523f26fe92` Source locator `/rows/1116/row` |  |  |  |  |  |  |
| [Arena text / chinese](https://benchize.com/benchmarks/lmarena%3Atext%3Achinese.md) | 1,385.63 | — | 125 / 168 | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1385.6307950631779 \| rating \| reported \| Higher is better \| ### Configuration category chinese config text Reasoning effort high thinkingEnabled true ### Reported statistics lower 1371.938245888334 rank 191 upper 1399.3233442380215 variance 48.805912455840115 votes 1949 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) Source Arena Original model label GPT-5 mini (High) Observed 2026-10-22T06:45:03.380Z Evidence SHA-256 `8e027ef69b8de06c4b2a8b217bfe816b1f1536269bb257fd295b4ef1ba8246ac` Source locator `/rows/607/row` |  |  |  |  |  |  |
| [Arena text style control / french](https://benchize.com/benchmarks/lmarena%3Atext_style_control%3Afrench.md) | 1,410.59 | — | 106 / 152 | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1410.59168340436 \| rating \| reported \| Higher is better \| ### Configuration category french config text_style_control Reasoning effort high thinkingEnabled true ### Reported statistics lower 1380.54727744758 rank 159 upper 1440.6360893611404 variance 234.9800873650155 votes 414 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label GPT-5 mini (High) Observed 2026-10-22T06:45:03.380Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/2996/row` |  |  |  |  |  |  |
| [Arena text / non english](https://benchize.com/benchmarks/lmarena%3Atext%3Anon_english.md) | 1,362.58 | — | 117 / 173 | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1362.5792085768514 \| rating \| reported \| Higher is better \| ### Configuration category non_english config text Reasoning effort high thinkingEnabled true ### Reported statistics lower 1356.9430843239384 rank 177 upper 1368.2153328297645 variance 8.26922741515547 votes 15291 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) Source Arena Original model label GPT-5 mini (High) Observed 2026-10-22T06:45:03.380Z Evidence SHA-256 `8e027ef69b8de06c4b2a8b217bfe816b1f1536269bb257fd295b4ef1ba8246ac` Source locator `/rows/9907/row` |  |  |  |  |  |  |
| [Arena text style control / coding](https://benchize.com/benchmarks/lmarena%3Atext_style_control%3Acoding.md) | 1,431.69 | — | 119 / 173 | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1431.6904502175166 \| rating \| reported \| Higher is better \| ### Configuration category coding config text_style_control Reasoning effort high thinkingEnabled true ### Reported statistics lower 1423.253185184307 rank 186 upper 1440.127715250726 variance 18.531356071586313 votes 5516 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label GPT-5 mini (High) Observed 2026-10-22T06:45:03.380Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/995/row` |  |  |  |  |  |  |
| [Arena text style control / hard prompts english](https://benchize.com/benchmarks/lmarena%3Atext_style_control%3Ahard_prompts_english.md) | 1,409.56 | — | 121 / 173 | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1409.5623653307991 \| rating \| reported \| Higher is better \| ### Configuration category hard_prompts_english config text_style_control Reasoning effort high thinkingEnabled true ### Reported statistics lower 1401.1693683448543 rank 188 upper 1417.955362316744 variance 18.33740818113255 votes 5601 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label GPT-5 mini (High) Observed 2026-10-22T06:45:03.380Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/4055/row` |  |  |  |  |  |  |
| [Arena text / industry legal and government](https://benchize.com/benchmarks/lmarena%3Atext%3Aindustry_legal_and_government.md) | 1,375.04 | — | 123 / 173 | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1375.0446287630398 \| rating \| reported \| Higher is better \| ### Configuration category industry_legal_and_government config text Reasoning effort high thinkingEnabled true ### Reported statistics lower 1360.706361773747 rank 182 upper 1389.3828957523326 variance 53.517663432636965 votes 1692 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) Source Arena Original model label GPT-5 mini (High) Observed 2026-10-22T06:45:03.380Z Evidence SHA-256 `8e027ef69b8de06c4b2a8b217bfe816b1f1536269bb257fd295b4ef1ba8246ac` Source locator `/rows/5289/row` |  |  |  |  |  |  |
| [Arena text / industry business and management and financial operations](https://benchize.com/benchmarks/lmarena%3Atext%3Aindustry_business_and_management_and_financial_operations.md) | 1,357.92 | — | 124 / 173 | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1357.924217694425 \| rating \| reported \| Higher is better \| ### Configuration category industry_business_and_management_and_financial_operations config text Reasoning effort high thinkingEnabled true ### Reported statistics lower 1349.095772822699 rank 185 upper 1366.7526625661512 variance 20.28954167964328 votes 4829 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) Source Arena Original model label GPT-5 mini (High) Observed 2026-10-22T06:45:03.380Z Evidence SHA-256 `8e027ef69b8de06c4b2a8b217bfe816b1f1536269bb257fd295b4ef1ba8246ac` Source locator `/rows/4467/row` |  |  |  |  |  |  |
| [Arena text / hard prompts english](https://benchize.com/benchmarks/lmarena%3Atext%3Ahard_prompts_english.md) | 1,383.1 | — | 122 / 173 | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1383.098352245569 \| rating \| reported \| Higher is better \| ### Configuration category hard_prompts_english config text Reasoning effort high thinkingEnabled true ### Reported statistics lower 1374.866787713484 rank 184 upper 1391.329916777654 variance 17.63878198585862 votes 5601 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) Source Arena Original model label GPT-5 mini (High) Observed 2026-10-22T06:45:03.380Z Evidence SHA-256 `8e027ef69b8de06c4b2a8b217bfe816b1f1536269bb257fd295b4ef1ba8246ac` Source locator `/rows/4051/row` |  |  |  |  |  |  |
| [Arena text / spanish](https://benchize.com/benchmarks/lmarena%3Atext%3Aspanish.md) | 1,354.48 | — | 123 / 155 | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1354.4814763920315 \| rating \| reported \| Higher is better \| ### Configuration category spanish config text Reasoning effort high thinkingEnabled true ### Reported statistics lower 1333.6100584880583 rank 188 upper 1375.3528942960047 variance 113.39860861597897 votes 856 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) Source Arena Original model label GPT-5 mini (High) Observed 2026-10-22T06:45:03.380Z Evidence SHA-256 `8e027ef69b8de06c4b2a8b217bfe816b1f1536269bb257fd295b4ef1ba8246ac` Source locator `/rows/10952/row` |  |  |  |  |  |  |
| [ArXivMath Overall](https://benchize.com/benchmarks/matharena%3Aoverall--visual_math.md) | 78.16% | 95% CI 75.12–81.2% | 10 / 15 | 0.01usd per problem | [matharena · overall--visual_math](https://matharena.ai/competition_tables/overall--visual_math) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 78.16 \| percent \| competition \| Higher is better \| \| `cost_per_problem` \| 0.010 \| usd_per_problem \| competition \| Lower is better \| ### Configuration competition overall--visual_math predicted false Reasoning effort high sourceModelName GPT-5-mini (high) sourceModelVersion openai/gpt-5-mini thinkingEnabled true ### Reported statistics Uncertainty 95% confidence interval: 75.12–81.2% confidenceInterval95 3.04 problems Not reported ### Source [Original source](https://matharena.ai/competition_tables/overall--visual_math) Source matharena Original model label GPT-5-mini (high) Source version overall--visual_math Observed 2026-10-22T05:30:09.818Z Evidence SHA-256 `b38d1f465012aab8b7d0930aea897d4e5be10ec02c16643c24c9251c8febb173` Source locator `/table/rows/12` |  |  |  |  |  |  |
| [Arena text / industry life and physical and social science](https://benchize.com/benchmarks/lmarena%3Atext%3Aindustry_life_and_physical_and_social_science.md) | 1,370.79 | — | 128 / 173 | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1370.7906740233927 \| rating \| reported \| Higher is better \| ### Configuration category industry_life_and_physical_and_social_science config text Reasoning effort high thinkingEnabled true ### Reported statistics lower 1361.447855615422 rank 196 upper 1380.1334924313635 variance 22.722684240187796 votes 4211 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) Source Arena Original model label GPT-5 mini (High) Observed 2026-10-22T06:45:03.380Z Evidence SHA-256 `8e027ef69b8de06c4b2a8b217bfe816b1f1536269bb257fd295b4ef1ba8246ac` Source locator `/rows/5693/row` |  |  |  |  |  |  |
| [Arena text / expert](https://benchize.com/benchmarks/lmarena%3Atext%3Aexpert.md) | 1,378.98 | — | 117 / 170 | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1378.976156631948 \| rating \| reported \| Higher is better \| ### Configuration category expert config text Reasoning effort high thinkingEnabled true ### Reported statistics lower 1361.7351742065262 rank 174 upper 1396.2171390573699 variance 77.37984158320168 votes 1228 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) Source Arena Original model label GPT-5 mini (High) Observed 2026-10-22T06:45:03.380Z Evidence SHA-256 `8e027ef69b8de06c4b2a8b217bfe816b1f1536269bb257fd295b4ef1ba8246ac` Source locator `/rows/2644/row` |  |  |  |  |  |  |
| [Arena text style control / hard prompts](https://benchize.com/benchmarks/lmarena%3Atext_style_control%3Ahard_prompts.md) | 1,404.31 | — | 120 / 173 | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1404.3065877030501 \| rating \| reported \| Higher is better \| ### Configuration category hard_prompts config text_style_control Reasoning effort high thinkingEnabled true ### Reported statistics lower 1398.2218582922737 rank 184 upper 1410.3913171138263 variance 9.637987475725556 votes 12861 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label GPT-5 mini (High) Observed 2026-10-22T06:45:03.380Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/3634/row` |  |  |  |  |  |  |
| [Arena vision / humor (config: vision)](https://benchize.com/benchmarks/benchmark%3Avision%3Ahumor--config-vision.md) | 1,205.49 | — | 60 / 70 | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/vision/latest) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1205.4902177218778 \| rating \| reported \| Higher is better \| ### Configuration category humor config vision Reasoning effort high thinkingEnabled true ### Reported statistics lower 1183.0445868517018 rank 74 upper 1227.9358485920538 variance 131.14974510364937 votes 1047 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/vision/latest) Source Arena Original model label GPT-5 mini (High) Observed 2026-10-22T06:45:03.380Z Evidence SHA-256 `06e61305486dce3fec5dc776ac2fd8321104e84c346cf9e08fa6f8e8a66ce0d7` Source locator `/rows/999/row` |  |  |  |  |  |  |
| [Arena text / math](https://benchize.com/benchmarks/lmarena%3Atext%3Amath.md) | 1,377.54 | — | 126 / 170 | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1377.537109417902 \| rating \| reported \| Higher is better \| ### Configuration category math config text Reasoning effort high thinkingEnabled true ### Reported statistics lower 1362.158603572033 rank 185 upper 1392.915615263771 variance 61.56474742808663 votes 1458 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) Source Arena Original model label GPT-5 mini (High) Observed 2026-10-22T06:45:03.380Z Evidence SHA-256 `8e027ef69b8de06c4b2a8b217bfe816b1f1536269bb257fd295b4ef1ba8246ac` Source locator `/rows/9097/row` |  |  |  |  |  |  |
| [Apex Shortlist](https://benchize.com/benchmarks/matharena%3Aapex--shortlist_2025.md) | 39.89% | 95% CI 32.89–46.89% | 24 / 25 | 0.07usd per problem | [matharena · apex--shortlist_2025](https://matharena.ai/competition_tables/apex--shortlist_2025) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 39.89 \| percent \| competition \| Higher is better \| \| `cost_per_problem` \| 0.068 \| usd_per_problem \| competition \| Lower is better \| ### Configuration competition apex--shortlist_2025 predicted false Reasoning effort high sourceModelName GPT-5-mini (high) sourceModelVersion openai/gpt-5-mini thinkingEnabled true ### Reported statistics Uncertainty 95% confidence interval: 32.89–46.89% confidenceInterval95 7.00 problems 47 ### Source [Original source](https://matharena.ai/competition_tables/apex--shortlist_2025) Source matharena Original model label GPT-5-mini (high) Source version apex--shortlist_2025 Observed 2026-10-22T05:30:14.141Z Evidence SHA-256 `74513abecacb4d230d741f4d6df425ce878fb450220e88a1a6823524476c2989` Source locator `/table/rows/33` |  |  |  |  |  |  |
| [Kangaroo 2025 3-4](https://benchize.com/benchmarks/matharena%3Akangaroo--kangaroo_2025_3-4.md) | 66.67% | 95% CI 57.24–76.1% | 8 / 16 | 0.02usd per problem | [matharena · kangaroo--kangaroo_2025_3-4](https://matharena.ai/competition_tables/kangaroo--kangaroo_2025_3-4) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 66.67 \| percent \| competition \| Higher is better \| \| `cost_per_problem` \| 0.015 \| usd_per_problem \| competition \| Lower is better \| ### Configuration competition kangaroo--kangaroo_2025_3-4 predicted false Reasoning effort high sourceModelName GPT-5-mini (high) sourceModelVersion openai/gpt-5-mini thinkingEnabled true ### Reported statistics Uncertainty 95% confidence interval: 57.24–76.1% confidenceInterval95 9.43 problems 24 ### Source [Original source](https://matharena.ai/competition_tables/kangaroo--kangaroo_2025_3-4) Source matharena Original model label GPT-5-mini (high) Source version kangaroo--kangaroo_2025_3-4 Observed 2026-10-22T05:30:10.341Z Evidence SHA-256 `38fec99c55752fef6703c9ed49d9e1e204b235f2bd78d5ee47725dac9e5da89c` Source locator `/table/rows/8` |  |  |  |  |  |  |
| [ARC-AGI-2](https://benchize.com/benchmarks/arc-prize%3Av2_Semi_Private.md) | 4.44% | — | 171 / 243 | 0.2usd per task | [arc prize · v2](https://arcprize.org/media/data/leaderboard/v2.json) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `score` \| 0.0444 \| score_fraction \| v2_Semi_Private \| Higher is better \| \| `cost_per_task` \| 0.1977 \| usd_per_task \| v2_Semi_Private \| Lower is better \| ### Configuration evaluationSplit v2_Semi_Private harness Not reported modelGroup gpt-5-mini-reasoning modelType CoT Reasoning effort high sourceModelVersion gpt-5-mini-2025-08-07-high thinkingEnabled true ### Source [Original source](https://arcprize.org/media/data/leaderboard/v2.json) Source arc prize Original model label GPT-5 Mini (High) Source version v2 Observed 2026-10-22T05:20:04.306Z Evidence SHA-256 `4351eb696e78113b0459e9bb5f0258318b905efef34f473dcea51ce641b0d94d` Source locator `/evaluations/65` |  |  |  |  |  |  |
| [Arena text style control / industry business and management and financial operations](https://benchize.com/benchmarks/lmarena%3Atext_style_control%3Aindustry_business_and_management_and_financial_operations.md) | 1,381.34 | — | 121 / 173 | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1381.3441514903197 \| rating \| reported \| Higher is better \| ### Configuration category industry_business_and_management_and_financial_operations config text_style_control Reasoning effort high thinkingEnabled true ### Reported statistics lower 1372.296823220984 rank 183 upper 1390.3914797596556 variance 21.308089617457814 votes 4829 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label GPT-5 mini (High) Observed 2026-10-22T06:45:03.380Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/4465/row` |  |  |  |  |  |  |
| [Arena text / korean](https://benchize.com/benchmarks/lmarena%3Atext%3Akorean.md) | 1,307.71 | — | 110 / 144 | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1307.7101319052254 \| rating \| reported \| Higher is better \| ### Configuration category korean config text Reasoning effort high thinkingEnabled true ### Reported statistics lower 1283.5215388572533 rank 166 upper 1331.8987249531976 variance 152.30881312289745 votes 662 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) Source Arena Original model label GPT-5 mini (High) Observed 2026-10-22T06:45:03.380Z Evidence SHA-256 `8e027ef69b8de06c4b2a8b217bfe816b1f1536269bb257fd295b4ef1ba8246ac` Source locator `/rows/8399/row` |  |  |  |  |  |  |
| [Arena text style control / industry mathematical](https://benchize.com/benchmarks/lmarena%3Atext_style_control%3Aindustry_mathematical.md) | 1,407.47 | — | 112 / 169 | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1407.4740849153636 \| rating \| reported \| Higher is better \| ### Configuration category industry_mathematical config text_style_control Reasoning effort high thinkingEnabled true ### Reported statistics lower 1391.009489674941 rank 168 upper 1423.9386801557862 variance 70.5676955250979 votes 1304 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label GPT-5 mini (High) Observed 2026-10-22T06:45:03.380Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/6080/row` |  |  |  |  |  |  |
| [Arena text style control / industry life and physical and social science](https://benchize.com/benchmarks/lmarena%3Atext_style_control%3Aindustry_life_and_physical_and_social_science.md) | 1,397.99 | — | 120 / 173 | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1397.9929489089059 \| rating \| reported \| Higher is better \| ### Configuration category industry_life_and_physical_and_social_science config text_style_control Reasoning effort high thinkingEnabled true ### Reported statistics lower 1388.454913408153 rank 188 upper 1407.5309844096591 variance 23.682180510055964 votes 4211 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label GPT-5 mini (High) Observed 2026-10-22T06:45:03.380Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/5685/row` |  |  |  |  |  |  |
| [Arena text style control / industry software and it services](https://benchize.com/benchmarks/lmarena%3Atext_style_control%3Aindustry_software_and_it_services.md) | 1,415.99 | — | 121 / 173 | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1415.9923505931094 \| rating \| reported \| Higher is better \| ### Configuration category industry_software_and_it_services config text_style_control Reasoning effort high thinkingEnabled true ### Reported statistics lower 1409.04615789183 rank 188 upper 1422.9385432943889 variance 12.56022654294399 votes 8919 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label GPT-5 mini (High) Observed 2026-10-22T06:45:03.380Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/6888/row` |  |  |  |  |  |  |
| [Arena vision / homework (config: vision)](https://benchize.com/benchmarks/benchmark%3Avision%3Ahomework--config-vision.md) | 1,209.74 | — | 75 / 83 | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/vision/latest) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1209.7424578800046 \| rating \| reported \| Higher is better \| ### Configuration category homework config vision Reasoning effort high thinkingEnabled true ### Reported statistics lower 1190.3156277261237 rank 96 upper 1229.169288033885 variance 98.24437731693145 votes 976 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/vision/latest) Source Arena Original model label GPT-5 mini (High) Observed 2026-10-22T06:45:03.380Z Evidence SHA-256 `06e61305486dce3fec5dc776ac2fd8321104e84c346cf9e08fa6f8e8a66ce0d7` Source locator `/rows/903/row` |  |  |  |  |  |  |
| [Kangaroo 2025 7-8](https://benchize.com/benchmarks/matharena%3Akangaroo--kangaroo_2025_7-8.md) | 87.5% | 95% CI 81.58–93.42% | 10 / 15 | 0.009usd per problem | [matharena · kangaroo--kangaroo_2025_7-8](https://matharena.ai/competition_tables/kangaroo--kangaroo_2025_7-8) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 87.50 \| percent \| competition \| Higher is better \| \| `cost_per_problem` \| 0.009 \| usd_per_problem \| competition \| Lower is better \| ### Configuration competition kangaroo--kangaroo_2025_7-8 predicted false Reasoning effort high sourceModelName GPT-5-mini (high) sourceModelVersion openai/gpt-5-mini thinkingEnabled true ### Reported statistics Uncertainty 95% confidence interval: 81.58–93.42% confidenceInterval95 5.92 problems 30 ### Source [Original source](https://matharena.ai/competition_tables/kangaroo--kangaroo_2025_7-8) Source matharena Original model label GPT-5-mini (high) Source version kangaroo--kangaroo_2025_7-8 Observed 2026-10-22T05:30:10.837Z Evidence SHA-256 `197887eb5244aa6bce3570bd9eb25bbb0bb6ec95568339536d94e2859f0ee8c1` Source locator `/table/rows/12` |  |  |  |  |  |  |
| [Arena vision style control / english](https://benchize.com/benchmarks/lmarena%3Avision_style_control%3Aenglish.md) | 1,193.21 | — | 75 / 92 | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/vision_style_control/latest) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1193.214303799724 \| rating \| reported \| Higher is better \| ### Configuration category english config vision_style_control Reasoning effort high thinkingEnabled true ### Reported statistics lower 1182.2997002514678 rank 99 upper 1204.1289073479797 variance 31.011284039763645 votes 13428 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/vision_style_control/latest) Source Arena Original model label GPT-5 mini (High) Observed 2026-10-22T06:45:03.380Z Evidence SHA-256 `38568936995f36625aae49e9ea05557d55c1b1df9b2954f5c50cee523f26fe92` Source locator `/rows/688/row` |  |  |  |  |  |  |
| [Arena vision / creative writing vision (config: vision)](https://benchize.com/benchmarks/benchmark%3Avision%3Acreative_writing_vision--config-vision.md) | 1,180.99 | — | 72 / 79 | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/vision/latest) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1180.9876667372791 \| rating \| reported \| Higher is better \| ### Configuration category creative_writing_vision config vision Reasoning effort high thinkingEnabled true ### Reported statistics lower 1159.5023411645996 rank 92 upper 1202.472992309959 variance 120.16768537964676 votes 1017 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/vision/latest) Source Arena Original model label GPT-5 mini (High) Observed 2026-10-22T06:45:03.380Z Evidence SHA-256 `06e61305486dce3fec5dc776ac2fd8321104e84c346cf9e08fa6f8e8a66ce0d7` Source locator `/rows/454/row` |  |  |  |  |  |  |
| [Arena text style control / overall](https://benchize.com/benchmarks/lmarena%3Atext_style_control%3Aoverall.md) | 1,389.91 | — | 117 / 173 | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1389.913557222953 \| rating \| reported \| Higher is better \| ### Configuration category overall config text_style_control Reasoning effort high thinkingEnabled true ### Reported statistics lower 1385.2653916675063 rank 178 upper 1394.5617227783996 variance 5.624280784802595 votes 26805 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label GPT-5 mini (High) Observed 2026-10-22T06:45:03.380Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/177/row` |  |  |  |  |  |  |
| [Arena text style control / creative writing](https://benchize.com/benchmarks/lmarena%3Atext_style_control%3Acreative_writing.md) | 1,323.34 | — | 129 / 173 | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1323.3431841265551 \| rating \| reported \| Higher is better \| ### Configuration category creative_writing config text_style_control Reasoning effort high thinkingEnabled true ### Reported statistics lower 1312.9313699457155 rank 210 upper 1333.7549983073945 variance 28.219975690574447 votes 3522 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label GPT-5 mini (High) Observed 2026-10-22T06:45:03.380Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/1431/row` |  |  |  |  |  |  |
| [CMIMC 2025](https://benchize.com/benchmarks/matharena%3Acmimc--cmimc_2025.md) | 84.38% | 95% CI 78.75–90.01% | 10 / 22 | 0.04usd per problem | [matharena · cmimc--cmimc_2025](https://matharena.ai/competition_tables/cmimc--cmimc_2025) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 84.38 \| percent \| competition \| Higher is better \| \| `cost_per_problem` \| 0.039 \| usd_per_problem \| competition \| Lower is better \| ### Configuration competition cmimc--cmimc_2025 predicted false Reasoning effort high sourceModelName GPT-5-mini (high) sourceModelVersion openai/gpt-5-mini thinkingEnabled true ### Reported statistics Uncertainty 95% confidence interval: 78.75–90.01% confidenceInterval95 5.63 problems 40 ### Source [Original source](https://matharena.ai/competition_tables/cmimc--cmimc_2025) Source matharena Original model label GPT-5-mini (high) Source version cmimc--cmimc_2025 Observed 2026-10-22T05:30:12.870Z Evidence SHA-256 `d5d48c1f54a744d7ff2244bae3258963afdb1ab36fb20464ea9cf47138a1555e` Source locator `/table/rows/16` |  |  |  |  |  |  |
| [Arena text / russian](https://benchize.com/benchmarks/lmarena%3Atext%3Arussian.md) | 1,361.92 | — | 118 / 172 | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1361.9177275280715 \| rating \| reported \| Higher is better \| ### Configuration category russian config text Reasoning effort high thinkingEnabled true ### Reported statistics lower 1348.8334840723944 rank 181 upper 1375.0019709837486 variance 44.56573265478713 votes 1871 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) Source Arena Original model label GPT-5 mini (High) Observed 2026-10-22T06:45:03.380Z Evidence SHA-256 `8e027ef69b8de06c4b2a8b217bfe816b1f1536269bb257fd295b4ef1ba8246ac` Source locator `/rows/10564/row` |  |  |  |  |  |  |
| [Arena text / exclude ties](https://benchize.com/benchmarks/lmarena%3Atext%3Aexclude_ties.md) | 1,342.41 | — | 122 / 173 | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1342.412476644644 \| rating \| reported \| Higher is better \| ### Configuration category exclude_ties config text Reasoning effort high thinkingEnabled true ### Reported statistics lower 1336.3317630042754 rank 183 upper 1348.4931902850124 variance 9.625270008616585 votes 19512 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) Source Arena Original model label GPT-5 mini (High) Observed 2026-10-22T06:45:03.380Z Evidence SHA-256 `8e027ef69b8de06c4b2a8b217bfe816b1f1536269bb257fd295b4ef1ba8246ac` Source locator `/rows/2236/row` |  |  |  |  |  |  |
| [Arena text style control / spanish](https://benchize.com/benchmarks/lmarena%3Atext_style_control%3Aspanish.md) | 1,371.49 | — | 120 / 155 | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1371.4862577119566 \| rating \| reported \| Higher is better \| ### Configuration category spanish config text_style_control Reasoning effort high thinkingEnabled true ### Reported statistics lower 1349.9813278106612 rank 184 upper 1392.9911876132524 variance 120.38707992087038 votes 856 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label GPT-5 mini (High) Observed 2026-10-22T06:45:03.380Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/10948/row` |  |  |  |  |  |  |
| [HMMT Nov 2025](https://benchize.com/benchmarks/matharena%3Ahmmt--hmmt_nov_2025.md) | 84.17% | 95% CI 77.64–90.7% | 11 / 13 | 0.03usd per problem | [matharena · hmmt--hmmt_nov_2025](https://matharena.ai/competition_tables/hmmt--hmmt_nov_2025) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 84.17 \| percent \| competition \| Higher is better \| \| `cost_per_problem` \| 0.030 \| usd_per_problem \| competition \| Lower is better \| ### Configuration competition hmmt--hmmt_nov_2025 predicted false Reasoning effort high sourceModelName GPT-5-mini (high) sourceModelVersion openai/gpt-5-mini thinkingEnabled true ### Reported statistics Uncertainty 95% confidence interval: 77.64–90.7% confidenceInterval95 6.53 problems 30 ### Source [Original source](https://matharena.ai/competition_tables/hmmt--hmmt_nov_2025) Source matharena Original model label GPT-5-mini (high) Source version hmmt--hmmt_nov_2025 Observed 2026-10-22T05:30:13.113Z Evidence SHA-256 `aa9287d733e27dde3646179a18070c07f558fb51926a8fe90cdf38985d6fce6d` Source locator `/table/rows/18` |  |  |  |  |  |  |
| [Arena text style control / industry legal and government](https://benchize.com/benchmarks/lmarena%3Atext_style_control%3Aindustry_legal_and_government.md) | 1,396.49 | — | 116 / 173 | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1396.48621964743 \| rating \| reported \| Higher is better \| ### Configuration category industry_legal_and_government config text_style_control Reasoning effort high thinkingEnabled true ### Reported statistics lower 1381.7552381931653 rank 179 upper 1411.2172011016946 variance 56.489428817221444 votes 1692 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label GPT-5 mini (High) Observed 2026-10-22T06:45:03.380Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/5286/row` |  |  |  |  |  |  |
| [Arena text / japanese](https://benchize.com/benchmarks/lmarena%3Atext%3Ajapanese.md) | 1,341.11 | — | 91 / 138 | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1341.1060218799173 \| rating \| reported \| Higher is better \| ### Configuration category japanese config text Reasoning effort high thinkingEnabled true ### Reported statistics lower 1312.6625978184436 rank 135 upper 1369.549445941391 variance 210.60446307078624 votes 460 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) Source Arena Original model label GPT-5 mini (High) Observed 2026-10-22T06:45:03.380Z Evidence SHA-256 `8e027ef69b8de06c4b2a8b217bfe816b1f1536269bb257fd295b4ef1ba8246ac` Source locator `/rows/8085/row` |  |  |  |  |  |  |
| [Arena text / german](https://benchize.com/benchmarks/lmarena%3Atext%3Agerman.md) | 1,365.67 | — | 104 / 149 | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1365.6668914363872 \| rating \| reported \| Higher is better \| ### Configuration category german config text Reasoning effort high thinkingEnabled true ### Reported statistics lower 1341.5599381121792 rank 157 upper 1389.7738447605952 variance 151.28242308491875 votes 592 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) Source Arena Original model label GPT-5 mini (High) Observed 2026-10-22T06:45:03.380Z Evidence SHA-256 `8e027ef69b8de06c4b2a8b217bfe816b1f1536269bb257fd295b4ef1ba8246ac` Source locator `/rows/3293/row` |  |  |  |  |  |  |
| [Arena text / industry writing and literature and language](https://benchize.com/benchmarks/lmarena%3Atext%3Aindustry_writing_and_literature_and_language.md) | 1,344.28 | — | 122 / 173 | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1344.2790337751496 \| rating \| reported \| Higher is better \| ### Configuration category industry_writing_and_literature_and_language config text Reasoning effort high thinkingEnabled true ### Reported statistics lower 1336.4064117891132 rank 191 upper 1352.151655761186 variance 16.134020909229463 votes 6144 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) Source Arena Original model label GPT-5 mini (High) Observed 2026-10-22T06:45:03.380Z Evidence SHA-256 `8e027ef69b8de06c4b2a8b217bfe816b1f1536269bb257fd295b4ef1ba8246ac` Source locator `/rows/7308/row` |  |  |  |  |  |  |
| [ARC-AGI-1](https://benchize.com/benchmarks/arc-prize%3Av1_Semi_Private.md) | 54.33% | — | 161 / 245 | 0.12usd per task | [arc prize · v1](https://arcprize.org/media/data/leaderboard/v1.json) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `score` \| 0.5433 \| score_fraction \| v1_Semi_Private \| Higher is better \| \| `cost_per_task` \| 0.116 \| usd_per_task \| v1_Semi_Private \| Lower is better \| ### Configuration evaluationSplit v1_Semi_Private harness Not reported modelGroup gpt-5-mini-reasoning modelType CoT Reasoning effort high sourceModelVersion gpt-5-mini-2025-08-07-high thinkingEnabled true ### Source [Original source](https://arcprize.org/media/data/leaderboard/v1.json) Source arc prize Original model label GPT-5 Mini (High) Source version v1 Observed 2026-10-22T05:20:04.066Z Evidence SHA-256 `2bf68d22dafba37047d07ad833ebc0e8199c9aa2f9eeaed50c75c1b704462836` Source locator `/evaluations/63` |  |  |  |  |  |  |
| [HMMT Feb 2025](https://benchize.com/benchmarks/matharena%3Ahmmt--hmmt_feb_2025.md) | 89.17% | 95% CI 83.61–94.73% | 10 / 35 | 0.03usd per problem | [matharena · hmmt--hmmt_feb_2025](https://matharena.ai/competition_tables/hmmt--hmmt_feb_2025) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 89.17 \| percent \| competition \| Higher is better \| \| `cost_per_problem` \| 0.034 \| usd_per_problem \| competition \| Lower is better \| ### Configuration competition hmmt--hmmt_feb_2025 predicted false Reasoning effort high sourceModelName GPT-5-mini (high) sourceModelVersion openai/gpt-5-mini thinkingEnabled true ### Reported statistics Uncertainty 95% confidence interval: 83.61–94.73% confidenceInterval95 5.56 problems 30 ### Source [Original source](https://matharena.ai/competition_tables/hmmt--hmmt_feb_2025) Source matharena Original model label GPT-5-mini (high) Source version hmmt--hmmt_feb_2025 Observed 2026-10-22T05:30:12.126Z Evidence SHA-256 `8554225c26eb7a3c2649943ee7cf6b404ec1f7441b20fbdcfccbf35b9a864864` Source locator `/table/rows/17` |  |  |  |  |  |  |
| [Arena vision / english (config: vision)](https://benchize.com/benchmarks/benchmark%3Avision%3Aenglish--config-vision.md) | 1,215.94 | — | 73 / 92 | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/vision/latest) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1215.939043817838 \| rating \| reported \| Higher is better \| ### Configuration category english config vision Reasoning effort high thinkingEnabled true ### Reported statistics lower 1205.455609545007 rank 91 upper 1226.4224780906684 variance 28.60954634231917 votes 13428 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/vision/latest) Source Arena Original model label GPT-5 mini (High) Observed 2026-10-22T06:45:03.380Z Evidence SHA-256 `06e61305486dce3fec5dc776ac2fd8321104e84c346cf9e08fa6f8e8a66ce0d7` Source locator `/rows/680/row` |  |  |  |  |  |  |
| [Arena text / longer query](https://benchize.com/benchmarks/lmarena%3Atext%3Alonger_query.md) | 1,354.97 | — | 122 / 172 | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1354.9715789630102 \| rating \| reported \| Higher is better \| ### Configuration category longer_query config text Reasoning effort high thinkingEnabled true ### Reported statistics lower 1346.9252300446624 rank 193 upper 1363.017927881358 variance 16.85394375881897 votes 5902 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) Source Arena Original model label GPT-5 mini (High) Observed 2026-10-22T06:45:03.380Z Evidence SHA-256 `8e027ef69b8de06c4b2a8b217bfe816b1f1536269bb257fd295b4ef1ba8246ac` Source locator `/rows/8710/row` |  |  |  |  |  |  |
| [Arena vision style control / humor](https://benchize.com/benchmarks/lmarena%3Avision_style_control%3Ahumor.md) | 1,182.46 | — | 61 / 70 | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/vision_style_control/latest) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1182.4640703246303 \| rating \| reported \| Higher is better \| ### Configuration category humor config vision_style_control Reasoning effort high thinkingEnabled true ### Reported statistics lower 1158.5042000417823 rank 77 upper 1206.423940607478 variance 149.4420247012228 votes 1047 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/vision_style_control/latest) Source Arena Original model label GPT-5 mini (High) Observed 2026-10-22T06:45:03.380Z Evidence SHA-256 `38568936995f36625aae49e9ea05557d55c1b1df9b2954f5c50cee523f26fe92` Source locator `/rows/1002/row` |  |  |  |  |  |  |
| [Arena text / hard prompts](https://benchize.com/benchmarks/lmarena%3Atext%3Ahard_prompts.md) | 1,380.12 | — | 118 / 173 | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1380.1213934664777 \| rating \| reported \| Higher is better \| ### Configuration category hard_prompts config text Reasoning effort high thinkingEnabled true ### Reported statistics lower 1374.1479087266944 rank 177 upper 1386.094878206261 variance 9.288794075885997 votes 12861 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) Source Arena Original model label GPT-5 mini (High) Observed 2026-10-22T06:45:03.380Z Evidence SHA-256 `8e027ef69b8de06c4b2a8b217bfe816b1f1536269bb257fd295b4ef1ba8246ac` Source locator `/rows/3627/row` |  |  |  |  |  |  |
| [Arena text / industry software and it services](https://benchize.com/benchmarks/lmarena%3Atext%3Aindustry_software_and_it_services.md) | 1,393.8 | — | 119 / 173 | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1393.8041887802392 \| rating \| reported \| Higher is better \| ### Configuration category industry_software_and_it_services config text Reasoning effort high thinkingEnabled true ### Reported statistics lower 1387.0037343059562 rank 180 upper 1400.6046432545227 variance 12.038702798964955 votes 8919 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) Source Arena Original model label GPT-5 mini (High) Observed 2026-10-22T06:45:03.380Z Evidence SHA-256 `8e027ef69b8de06c4b2a8b217bfe816b1f1536269bb257fd295b4ef1ba8246ac` Source locator `/rows/6880/row` |  |  |  |  |  |  |
| [Arena vision / chinese (config: vision)](https://benchize.com/benchmarks/benchmark%3Avision%3Achinese--config-vision.md) | 1,213.76 | — | 69 / 83 | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/vision/latest) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1213.7626993667068 \| rating \| reported \| Higher is better \| ### Configuration category chinese config vision Reasoning effort high thinkingEnabled true ### Reported statistics lower 1195.307062373991 rank 88 upper 1232.2183363594227 variance 88.66697593425089 votes 1600 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/vision/latest) Source Arena Original model label GPT-5 mini (High) Observed 2026-10-22T06:45:03.380Z Evidence SHA-256 `06e61305486dce3fec5dc776ac2fd8321104e84c346cf9e08fa6f8e8a66ce0d7` Source locator `/rows/288/row` |  |  |  |  |  |  |
| [Arena text style control / polish](https://benchize.com/benchmarks/lmarena%3Atext_style_control%3Apolish.md) | 1,399.04 | — | 91 / 137 | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1399.0391756268627 \| rating \| reported \| Higher is better \| ### Configuration category polish config text_style_control Reasoning effort high thinkingEnabled true ### Reported statistics lower 1382.846594262235 rank 134 upper 1415.2317569914906 variance 68.25523934751291 votes 1562 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label GPT-5 mini (High) Observed 2026-10-22T06:45:03.380Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/10281/row` |  |  |  |  |  |  |
| [Arena text / industry entertainment and sports and media](https://benchize.com/benchmarks/lmarena%3Atext%3Aindustry_entertainment_and_sports_and_media.md) | 1,339.97 | — | 117 / 173 | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1339.9680145282691 \| rating \| reported \| Higher is better \| ### Configuration category industry_entertainment_and_sports_and_media config text Reasoning effort high thinkingEnabled true ### Reported statistics lower 1331.1631362776016 rank 180 upper 1348.7728927789367 variance 20.181364587703584 votes 4845 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) Source Arena Original model label GPT-5 mini (High) Observed 2026-10-22T06:45:03.380Z Evidence SHA-256 `8e027ef69b8de06c4b2a8b217bfe816b1f1536269bb257fd295b4ef1ba8246ac` Source locator `/rows/4872/row` |  |  |  |  |  |  |
| [Arena text style control / exclude ties](https://benchize.com/benchmarks/lmarena%3Atext_style_control%3Aexclude_ties.md) | 1,366.3 | — | 117 / 173 | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1366.2980175408527 \| rating \| reported \| Higher is better \| ### Configuration category exclude_ties config text_style_control Reasoning effort high thinkingEnabled true ### Reported statistics lower 1360.0245028471368 rank 179 upper 1372.5715322345684 variance 10.245323052859732 votes 19512 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label GPT-5 mini (High) Observed 2026-10-22T06:45:03.380Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/2232/row` |  |  |  |  |  |  |
| [Arena text / industry medicine and healthcare](https://benchize.com/benchmarks/lmarena%3Atext%3Aindustry_medicine_and_healthcare.md) | 1,379.6 | — | 120 / 173 | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1379.5989922900392 \| rating \| reported \| Higher is better \| ### Configuration category industry_medicine_and_healthcare config text Reasoning effort high thinkingEnabled true ### Reported statistics lower 1363.8223977397583 rank 183 upper 1395.3755868403205 variance 64.79333691229898 votes 1436 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) Source Arena Original model label GPT-5 mini (High) Observed 2026-10-22T06:45:03.380Z Evidence SHA-256 `8e027ef69b8de06c4b2a8b217bfe816b1f1536269bb257fd295b4ef1ba8246ac` Source locator `/rows/6495/row` |  |  |  |  |  |  |
| [Kangaroo 2025 9-10](https://benchize.com/benchmarks/matharena%3Akangaroo--kangaroo_2025_9-10.md) | 97.5% | 95% CI 94.71–100.29% | 8 / 15 | 0.007usd per problem | [matharena · kangaroo--kangaroo_2025_9-10](https://matharena.ai/competition_tables/kangaroo--kangaroo_2025_9-10) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 97.50 \| percent \| competition \| Higher is better \| \| `cost_per_problem` \| 0.007 \| usd_per_problem \| competition \| Lower is better \| ### Configuration competition kangaroo--kangaroo_2025_9-10 predicted false Reasoning effort high sourceModelName GPT-5-mini (high) sourceModelVersion openai/gpt-5-mini thinkingEnabled true ### Reported statistics Uncertainty 95% confidence interval: 94.71–100.29% confidenceInterval95 2.79 problems 30 ### Source [Original source](https://matharena.ai/competition_tables/kangaroo--kangaroo_2025_9-10) Source matharena Original model label GPT-5-mini (high) Source version kangaroo--kangaroo_2025_9-10 Observed 2026-10-22T05:30:11.076Z Evidence SHA-256 `52964b89ab1a06cf2e79ec946b33004aa40ca31f1ec26888e6dd0f0a7994223a` Source locator `/table/rows/8` |  |  |  |  |  |  |
| [Arena text / french](https://benchize.com/benchmarks/lmarena%3Atext%3Afrench.md) | 1,386.47 | — | 113 / 152 | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1386.4670707135683 \| rating \| reported \| Higher is better \| ### Configuration category french config text Reasoning effort high thinkingEnabled true ### Reported statistics lower 1356.7026131250138 rank 164 upper 1416.2315283021228 variance 230.62148441325158 votes 414 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) Source Arena Original model label GPT-5 mini (High) Observed 2026-10-22T06:45:03.380Z Evidence SHA-256 `8e027ef69b8de06c4b2a8b217bfe816b1f1536269bb257fd295b4ef1ba8246ac` Source locator `/rows/3001/row` |  |  |  |  |  |  |
| [Arena vision / diagram (config: vision)](https://benchize.com/benchmarks/benchmark%3Avision%3Adiagram--config-vision.md) | 1,202.23 | — | 76 / 84 | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/vision/latest) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1202.2277607917924 \| rating \| reported \| Higher is better \| ### Configuration category diagram config vision Reasoning effort high thinkingEnabled true ### Reported statistics lower 1187.3995454541223 rank 95 upper 1217.0559761294626 variance 57.2376225708415 votes 1936 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/vision/latest) Source Arena Original model label GPT-5 mini (High) Observed 2026-10-22T06:45:03.380Z Evidence SHA-256 `06e61305486dce3fec5dc776ac2fd8321104e84c346cf9e08fa6f8e8a66ce0d7` Source locator `/rows/561/row` |  |  |  |  |  |  |
| [Arena text style control / english](https://benchize.com/benchmarks/lmarena%3Atext_style_control%3Aenglish.md) | 1,397.68 | — | 120 / 173 | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1397.6775977363022 \| rating \| reported \| Higher is better \| ### Configuration category english config text_style_control Reasoning effort high thinkingEnabled true ### Reported statistics lower 1391.3926808457138 rank 185 upper 1403.9625146268904 variance 10.282598920184606 votes 11473 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label GPT-5 mini (High) Observed 2026-10-22T06:45:03.380Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/1821/row` |  |  |  |  |  |  |
| [Arena text / instruction following](https://benchize.com/benchmarks/lmarena%3Atext%3Ainstruction_following.md) | 1,356.86 | — | 118 / 173 | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1356.8562758152852 \| rating \| reported \| Higher is better \| ### Configuration category instruction_following config text Reasoning effort high thinkingEnabled true ### Reported statistics lower 1349.398991910941 rank 180 upper 1364.3135597196297 variance 14.476553264195315 votes 7013 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) Source Arena Original model label GPT-5 mini (High) Observed 2026-10-22T06:45:03.380Z Evidence SHA-256 `8e027ef69b8de06c4b2a8b217bfe816b1f1536269bb257fd295b4ef1ba8246ac` Source locator `/rows/7713/row` |  |  |  |  |  |  |
| [AIME 2025](https://benchize.com/benchmarks/aime-2025.md) | 87.5% | 95% CI 81.58–93.42% | 16 / 36 | 0.03usd per problem | [matharena · aime--aime_2025](https://matharena.ai/competition_tables/aime--aime_2025) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 87.50 \| percent \| competition \| Higher is better \| \| `cost_per_problem` \| 0.033 \| usd_per_problem \| competition \| Lower is better \| ### Configuration competition aime--aime_2025 predicted false Reasoning effort high sourceModelName GPT-5-mini (high) sourceModelVersion openai/gpt-5-mini thinkingEnabled true ### Reported statistics Uncertainty 95% confidence interval: 81.58–93.42% confidenceInterval95 5.92 problems 30 ### Source [Original source](https://matharena.ai/competition_tables/aime--aime_2025) Source matharena Original model label GPT-5-mini (high) Source version aime--aime_2025 Observed 2026-10-22T05:30:11.892Z Evidence SHA-256 `fab0abcecc4032852ef2cbd2a84d34ffc42202be358b2994bfaba44ae7a0cd9a` Source locator `/table/rows/25` |  |  |  |  |  |  |
| [Arena text style control / non english](https://benchize.com/benchmarks/lmarena%3Atext_style_control%3Anon_english.md) | 1,377.99 | — | 112 / 173 | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1377.991816865774 \| rating \| reported \| Higher is better \| ### Configuration category non_english config text_style_control Reasoning effort high thinkingEnabled true ### Reported statistics lower 1372.2499661702284 rank 171 upper 1383.7336675613194 variance 8.5823774115012 votes 15291 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label GPT-5 mini (High) Observed 2026-10-22T06:45:03.380Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/9901/row` |  |  |  |  |  |  |
| [Arena text style control / math](https://benchize.com/benchmarks/lmarena%3Atext_style_control%3Amath.md) | 1,406.16 | — | 106 / 170 | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1406.1615238808308 \| rating \| reported \| Higher is better \| ### Configuration category math config text_style_control Reasoning effort high thinkingEnabled true ### Reported statistics lower 1390.70475415599 rank 154 upper 1421.6182936056714 variance 62.192969254212144 votes 1458 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label GPT-5 mini (High) Observed 2026-10-22T06:45:03.380Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/9066/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) | 1,348.35 | — | 116 / 173 | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1348.35060641888 \| rating \| reported \| Higher is better \| ### Configuration category industry_entertainment_and_sports_and_media config text_style_control Reasoning effort high thinkingEnabled true ### Reported statistics lower 1339.336702688754 rank 183 upper 1357.364510149006 variance 21.15093880956878 votes 4845 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label GPT-5 mini (High) Observed 2026-10-22T06:45:03.380Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/4875/row` |  |  |  |  |  |  |
| [Arena vision style control / chinese](https://benchize.com/benchmarks/lmarena%3Avision_style_control%3Achinese.md) | 1,179.78 | — | 70 / 83 | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/vision_style_control/latest) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1179.7826762976886 \| rating \| reported \| Higher is better \| ### Configuration category chinese config vision_style_control Reasoning effort high thinkingEnabled true ### Reported statistics lower 1159.9601692345784 rank 93 upper 1199.605183360799 variance 102.28712700245903 votes 1600 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/vision_style_control/latest) Source Arena Original model label GPT-5 mini (High) Observed 2026-10-22T06:45:03.380Z Evidence SHA-256 `38568936995f36625aae49e9ea05557d55c1b1df9b2954f5c50cee523f26fe92` Source locator `/rows/293/row` |  |  |  |  |  |  |
| [Arena text style control / industry writing and literature and language](https://benchize.com/benchmarks/lmarena%3Atext_style_control%3Aindustry_writing_and_literature_and_language.md) | 1,351.11 | — | 121 / 173 | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1351.1140793628808 \| rating \| reported \| Higher is better \| ### Configuration category industry_writing_and_literature_and_language config text_style_control Reasoning effort high thinkingEnabled true ### Reported statistics lower 1343.093739548332 rank 196 upper 1359.1344191774294 variance 16.745162122865693 votes 6144 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label GPT-5 mini (High) Observed 2026-10-22T06:45:03.380Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/7313/row` |  |  |  |  |  |  |
| [Arena text / industry mathematical](https://benchize.com/benchmarks/lmarena%3Atext%3Aindustry_mathematical.md) | 1,380.15 | — | 124 / 169 | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1380.147001444969 \| rating \| reported \| Higher is better \| ### Configuration category industry_mathematical config text Reasoning effort high thinkingEnabled true ### Reported statistics lower 1363.7611666750952 rank 181 upper 1396.532836214843 variance 69.89417136510939 votes 1304 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) Source Arena Original model label GPT-5 mini (High) Observed 2026-10-22T06:45:03.380Z Evidence SHA-256 `8e027ef69b8de06c4b2a8b217bfe816b1f1536269bb257fd295b4ef1ba8246ac` Source locator `/rows/6093/row` |  |  |  |  |  |  |
| [Arena text style control / longer query](https://benchize.com/benchmarks/lmarena%3Atext_style_control%3Alonger_query.md) | 1,370.53 | — | 125 / 172 | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1370.526527988885 \| rating \| reported \| Higher is better \| ### Configuration category longer_query config text_style_control Reasoning effort high thinkingEnabled true ### Reported statistics lower 1362.334895770251 rank 201 upper 1378.7181602075188 variance 17.468061363530666 votes 5902 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label GPT-5 mini (High) Observed 2026-10-22T06:45:03.380Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/8718/row` |  |  |  |  |  |  |
| [Arena text style control / german](https://benchize.com/benchmarks/lmarena%3Atext_style_control%3Agerman.md) | 1,386.18 | — | 98 / 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` \| 1386.1805730467179 \| rating \| reported \| Higher is better \| ### Configuration category german config text_style_control Reasoning effort high thinkingEnabled true ### Reported statistics lower 1361.6510775445777 rank 146 upper 1410.7100685488579 variance 156.63220085769075 votes 592 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label GPT-5 mini (High) Observed 2026-10-22T06:45:03.380Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/3282/row` |  |  |  |  |  |  |
| [Kangaroo 2025 11-12](https://benchize.com/benchmarks/matharena%3Akangaroo--kangaroo_2025_11-12.md) | 85% | 95% CI 78.61–91.39% | 15 / 16 | 0.01usd per problem | [matharena · kangaroo--kangaroo_2025_11-12](https://matharena.ai/competition_tables/kangaroo--kangaroo_2025_11-12) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 85.00 \| percent \| competition \| Higher is better \| \| `cost_per_problem` \| 0.011 \| usd_per_problem \| competition \| Lower is better \| ### Configuration competition kangaroo--kangaroo_2025_11-12 predicted false Reasoning effort high sourceModelName GPT-5-mini (high) sourceModelVersion openai/gpt-5-mini thinkingEnabled true ### Reported statistics Uncertainty 95% confidence interval: 78.61–91.39% confidenceInterval95 6.39 problems 30 ### Source [Original source](https://matharena.ai/competition_tables/kangaroo--kangaroo_2025_11-12) Source matharena Original model label GPT-5-mini (high) Source version kangaroo--kangaroo_2025_11-12 Observed 2026-10-22T05:30:11.337Z Evidence SHA-256 `1e53cfaa398a3ab9a1de8f0f33a4b2499b23b5df61a94735b6b646efc684444c` Source locator `/table/rows/18` |  |  |  |  |  |  |
| [Arena text style control / russian](https://benchize.com/benchmarks/lmarena%3Atext_style_control%3Arussian.md) | 1,378.51 | — | 114 / 172 | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1378.5056276076652 \| rating \| reported \| Higher is better \| ### Configuration category russian config text_style_control Reasoning effort high thinkingEnabled true ### Reported statistics lower 1365.2027362000208 rank 174 upper 1391.8085190153097 variance 46.06763421496318 votes 1871 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label GPT-5 mini (High) Observed 2026-10-22T06:45:03.380Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/10557/row` |  |  |  |  |  |  |
| [Arena vision / entity recognition (config: vision)](https://benchize.com/benchmarks/benchmark%3Avision%3Aentity_recognition--config-vision.md) | 1,226.03 | — | 22 / 37 | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/vision/latest) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1226.0321800913969 \| rating \| reported \| Higher is better \| ### Configuration category entity_recognition config vision Reasoning effort high thinkingEnabled true ### Reported statistics lower 1190.4628041175185 rank 29 upper 1261.6015560652752 variance 329.3489703327089 votes 282 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/vision/latest) Source Arena Original model label GPT-5 mini (High) Observed 2026-10-22T06:45:03.380Z Evidence SHA-256 `06e61305486dce3fec5dc776ac2fd8321104e84c346cf9e08fa6f8e8a66ce0d7` Source locator `/rows/785/row` |  |  |  |  |  |  |
| [Kangaroo 2025 1-2](https://benchize.com/benchmarks/matharena%3Akangaroo--kangaroo_2025_1-2.md) | 61.46% | 95% CI 51.72–71.2% | 14 / 16 | 0.009usd 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` \| 61.46 \| percent \| competition \| Higher is better \| \| `cost_per_problem` \| 0.009 \| usd_per_problem \| competition \| Lower is better \| ### Configuration competition kangaroo--kangaroo_2025_1-2 predicted false Reasoning effort high sourceModelName GPT-5-mini (high) sourceModelVersion openai/gpt-5-mini thinkingEnabled true ### Reported statistics Uncertainty 95% confidence interval: 51.72–71.2% confidenceInterval95 9.74 problems 24 ### Source [Original source](https://matharena.ai/competition_tables/kangaroo--kangaroo_2025_1-2) Source matharena Original model label GPT-5-mini (high) Source version kangaroo--kangaroo_2025_1-2 Observed 2026-10-22T05:30:10.078Z Evidence SHA-256 `a59a4c362e2d87350330706a01dd330e9a1ac7cc64a4de0bacbf1a439d8fcf90` Source locator `/table/rows/16` |  |  |  |  |  |  |
| [Arena vision / captioning (config: vision)](https://benchize.com/benchmarks/benchmark%3Avision%3Acaptioning--config-vision.md) | 1,216.96 | — | 16 / 24 | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/vision/latest) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1216.962021342088 \| rating \| reported \| Higher is better \| ### Configuration category captioning config vision Reasoning effort high thinkingEnabled true ### Reported statistics lower 1180.4576750953474 rank 18 upper 1253.4663675888287 variance 346.89094875189556 votes 283 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/vision/latest) Source Arena Original model label GPT-5 mini (High) Observed 2026-10-22T06:45:03.380Z Evidence SHA-256 `06e61305486dce3fec5dc776ac2fd8321104e84c346cf9e08fa6f8e8a66ce0d7` Source locator `/rows/184/row` |  |  |  |  |  |  |
| [BRUMO 2025](https://benchize.com/benchmarks/matharena%3Abrumo--brumo_2025.md) | 90% | 95% CI 84.63–95.37% | 13 / 26 | 0.03usd per problem | [matharena · brumo--brumo_2025](https://matharena.ai/competition_tables/brumo--brumo_2025) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 90.00 \| percent \| competition \| Higher is better \| \| `cost_per_problem` \| 0.027 \| usd_per_problem \| competition \| Lower is better \| ### Configuration competition brumo--brumo_2025 predicted false Reasoning effort high sourceModelName GPT-5-mini (high) sourceModelVersion openai/gpt-5-mini thinkingEnabled true ### Reported statistics Uncertainty 95% confidence interval: 84.63–95.37% confidenceInterval95 5.37 problems 30 ### Source [Original source](https://matharena.ai/competition_tables/brumo--brumo_2025) Source matharena Original model label GPT-5-mini (high) Source version brumo--brumo_2025 Observed 2026-10-22T05:30:12.351Z Evidence SHA-256 `d1d1c126b1feff70b2bcc20a7adbf380d94c2aaab0704704cb01593d4e1958ff` Source locator `/table/rows/22` |  |  |  |  |  |  |
| [Arena text style control / japanese](https://benchize.com/benchmarks/lmarena%3Atext_style_control%3Ajapanese.md) | 1,364.1 | — | 86 / 138 | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1364.0995937631283 \| rating \| reported \| Higher is better \| ### Configuration category japanese config text_style_control Reasoning effort high thinkingEnabled true ### Reported statistics lower 1335.3791285480684 rank 124 upper 1392.820058978188 variance 214.72705049599153 votes 460 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label GPT-5 mini (High) Observed 2026-10-22T06:45:03.380Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/8074/row` |  |  |  |  |  |  |
| [Kangaroo 2025 5-6](https://benchize.com/benchmarks/matharena%3Akangaroo--kangaroo_2025_5-6.md) | 70.83% | 95% CI 62.7–78.96% | 9 / 16 | 0.01usd per problem | [matharena · kangaroo--kangaroo_2025_5-6](https://matharena.ai/competition_tables/kangaroo--kangaroo_2025_5-6) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 70.83 \| percent \| competition \| Higher is better \| \| `cost_per_problem` \| 0.011 \| usd_per_problem \| competition \| Lower is better \| ### Configuration competition kangaroo--kangaroo_2025_5-6 predicted false Reasoning effort high sourceModelName GPT-5-mini (high) sourceModelVersion openai/gpt-5-mini thinkingEnabled true ### Reported statistics Uncertainty 95% confidence interval: 62.7–78.96% confidenceInterval95 8.13 problems 30 ### Source [Original source](https://matharena.ai/competition_tables/kangaroo--kangaroo_2025_5-6) Source matharena Original model label GPT-5-mini (high) Source version kangaroo--kangaroo_2025_5-6 Observed 2026-10-22T05:30:10.589Z Evidence SHA-256 `9460cafccce0b6f3ba1f90e1090be31d6cf94dd10b9157819abc97efe624b126` Source locator `/table/rows/10` |  |  |  |  |  |  |
| [Arena text style control / instruction following](https://benchize.com/benchmarks/lmarena%3Atext_style_control%3Ainstruction_following.md) | 1,372.94 | — | 119 / 173 | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1372.939471274597 \| rating \| reported \| Higher is better \| ### Configuration category instruction_following config text_style_control Reasoning effort high thinkingEnabled true ### Reported statistics lower 1365.380674049794 rank 187 upper 1380.4982684994 variance 14.873364040217602 votes 7013 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label GPT-5 mini (High) Observed 2026-10-22T06:45:03.380Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/7720/row` |  |  |  |  |  |  |
| [Arena vision style control / entity recognition](https://benchize.com/benchmarks/lmarena%3Avision_style_control%3Aentity_recognition.md) | 1,211.19 | — | 18 / 37 | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/vision_style_control/latest) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1211.1918062129212 \| rating \| reported \| Higher is better \| ### Configuration category entity_recognition config vision_style_control Reasoning effort high thinkingEnabled true ### Reported statistics lower 1171.0380927933693 rank 26 upper 1251.3455196324733 variance 419.71573213120683 votes 282 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/vision_style_control/latest) Source Arena Original model label GPT-5 mini (High) Observed 2026-10-22T06:45:03.380Z Evidence SHA-256 `38568936995f36625aae49e9ea05557d55c1b1df9b2954f5c50cee523f26fe92` Source locator `/rows/782/row` |  |  |  |  |  |  |
| [Arena text style control / korean](https://benchize.com/benchmarks/lmarena%3Atext_style_control%3Akorean.md) | 1,323.15 | — | 107 / 144 | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1323.1498905398707 \| rating \| reported \| Higher is better \| ### Configuration category korean config text_style_control Reasoning effort high thinkingEnabled true ### Reported statistics lower 1298.4401165025765 rank 169 upper 1347.859664577165 variance 158.9429853275936 votes 662 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label GPT-5 mini (High) Observed 2026-10-22T06:45:03.380Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/8402/row` |  |  |  |  |  |  |
| [Arena vision style control / creative writing vision](https://benchize.com/benchmarks/lmarena%3Avision_style_control%3Acreative_writing_vision.md) | 1,148.88 | — | 75 / 79 | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/vision_style_control/latest) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1148.8799597728619 \| rating \| reported \| Higher is better \| ### Configuration category creative_writing_vision config vision_style_control Reasoning effort high thinkingEnabled true ### Reported statistics lower 1126.4922868500566 rank 98 upper 1171.2676326956669 variance 130.47332336311152 votes 1017 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/vision_style_control/latest) Source Arena Original model label GPT-5 mini (High) Observed 2026-10-22T06:45:03.380Z Evidence SHA-256 `38568936995f36625aae49e9ea05557d55c1b1df9b2954f5c50cee523f26fe92` Source locator `/rows/460/row` |  |  |  |  |  |  |
| [Arena text / multi turn](https://benchize.com/benchmarks/lmarena%3Atext%3Amulti_turn.md) | 1,362.8 | — | 122 / 173 | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1362.8010125552264 \| rating \| reported \| Higher is better \| ### Configuration category multi_turn config text Reasoning effort high thinkingEnabled true ### Reported statistics lower 1353.6085692949741 rank 191 upper 1371.9934558154785 variance 21.997115428582813 votes 4394 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) Source Arena Original model label GPT-5 mini (High) Observed 2026-10-22T06:45:03.380Z Evidence SHA-256 `8e027ef69b8de06c4b2a8b217bfe816b1f1536269bb257fd295b4ef1ba8246ac` Source locator `/rows/9506/row` |  |  |  |  |  |  |
| [Arena text style control / expert](https://benchize.com/benchmarks/lmarena%3Atext_style_control%3Aexpert.md) | 1,403.05 | — | 114 / 170 | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1403.0517383766348 \| rating \| reported \| Higher is better \| ### Configuration category expert config text_style_control Reasoning effort high thinkingEnabled true ### Reported statistics lower 1385.593273500415 rank 176 upper 1420.5102032528546 variance 79.34433507193626 votes 1228 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label GPT-5 mini (High) Observed 2026-10-22T06:45:03.380Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/2646/row` |  |  |  |  |  |  |
| [Arena text / overall](https://benchize.com/benchmarks/lmarena%3Atext.md) | 1,373.27 | — | 120 / 173 | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1373.2698448489189 \| rating \| reported \| Higher is better \| ### Configuration category overall config text Reasoning effort high thinkingEnabled true ### Reported statistics lower 1368.7134667846703 rank 181 upper 1377.8262229131676 variance 5.404348200357596 votes 26805 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) Source Arena Original model label GPT-5 mini (High) Observed 2026-10-22T06:45:03.380Z Evidence SHA-256 `8e027ef69b8de06c4b2a8b217bfe816b1f1536269bb257fd295b4ef1ba8246ac` Source locator `/rows/180/row` |  |  |  |  |  |  |

---
Cite as: GPT-5 MiniHigh — Benchize, https://benchize.com/models/gpt-5-mini-high (retrieved 2026-10-22)