# Arena vision / creative writing (config: vision)

> Source: Benchize (https://benchize.com) — https://benchize.com/benchmarks/benchmark%3Avision%3Acreative_writing--config-vision. When citing or reusing this content, credit "Benchize" and link to https://benchize.com/benchmarks/benchmark%3Avision%3Acreative_writing--config-vision.

Human pairwise preferences on creative writing prompts in Arena’s vision evaluation. The original organizer publishes model ratings and uncertainty; these are preference ratings rather than task accuracy.

Canonical URL: https://benchize.com/benchmarks/benchmark%3Avision%3Acreative_writing--config-vision
Last updated: Wed, 21 Oct 2026 18:05:10 GMT

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

Human pairwise preferences on creative writing prompts in Arena’s vision evaluation. The original organizer publishes model ratings and uncertainty; these are preference ratings rather than task accuracy.

Multimodal · Models tested: 13 · Score publishers: [Arena](https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset)

## Model results

| # | Model | Score |  |
| --- | --- | --- | --- |
| 1 | [Gemini 3 Pro](https://benchize.com/models/gemini-3-pro.md) | 1,390.64 |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1390.639459948154 \| rating \| reported \| Higher is better \| ### Configuration category creative_writing config vision ### Reported statistics lower 1368.445487557508 rank 1 upper 1412.8334323388003 variance 128.22535226025525 votes 766 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/vision/latest) Source Arena Original model label gemini-3-pro Observed 2026-10-21T16:40:19.533Z Evidence SHA-256 `06e61305486dce3fec5dc776ac2fd8321104e84c346cf9e08fa6f8e8a66ce0d7` Source locator `/rows/329/row` |  |  |  |
| 2 | [Gemini 3 Flash](https://benchize.com/models/gemini-3-flash.md) | 1,306.36 |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1306.3639661103923 \| rating \| reported \| Higher is better \| ### Configuration category creative_writing config vision ### Reported statistics lower 1266.6090609624443 rank 3 upper 1346.1188712583407 variance 411.4198686208417 votes 217 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/vision/latest) Source Arena Original model label gemini-3-flash Observed 2026-10-21T16:40:19.533Z Evidence SHA-256 `06e61305486dce3fec5dc776ac2fd8321104e84c346cf9e08fa6f8e8a66ce0d7` Source locator `/rows/331/row` |  |  |  |
| 3 | [GPT-5.1](https://benchize.com/models/gpt-5-1.md) | 1,291.26 |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1291.2643112763622 \| rating \| reported \| Higher is better \| ### Configuration category creative_writing config vision ### Reported statistics lower 1261.6585429376505 rank 4 upper 1320.870079615073 variance 228.1689222343578 votes 411 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/vision/latest) Source Arena Original model label gpt-5.1 Observed 2026-10-21T16:40:19.533Z Evidence SHA-256 `06e61305486dce3fec5dc776ac2fd8321104e84c346cf9e08fa6f8e8a66ce0d7` Source locator `/rows/332/row` |  |  |  |
| 4 | [Gemini 2.5 Pro](https://benchize.com/models/gemini-2-5-pro.md) | 1,277.36 |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1277.3617983725967 \| rating \| reported \| Higher is better \| ### Configuration category creative_writing config vision ### Reported statistics lower 1263.5289926823252 rank 7 upper 1291.1946040628686 variance 49.81089794169208 votes 2418 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/vision/latest) Source Arena Original model label gemini-2.5-pro Observed 2026-10-21T16:40:19.533Z Evidence SHA-256 `06e61305486dce3fec5dc776ac2fd8321104e84c346cf9e08fa6f8e8a66ce0d7` Source locator `/rows/335/row` |  |  |  |
| 5 | [Gemini 2.5 Flash](https://benchize.com/models/gemini-2-5-flash.md) | 1,253.05 |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1253.054839283779 \| rating \| reported \| Higher is better \| ### Configuration category creative_writing config vision ### Reported statistics lower 1238.269469149889 rank 10 upper 1267.84020941767 variance 56.907331355082775 votes 1745 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/vision/latest) Source Arena Original model label gemini-2.5-flash Observed 2026-10-21T16:40:19.533Z Evidence SHA-256 `06e61305486dce3fec5dc776ac2fd8321104e84c346cf9e08fa6f8e8a66ce0d7` Source locator `/rows/338/row` |  |  |  |
| 6 | [GPT-5 Chat](https://benchize.com/models/gpt-5-chat.md) | 1,239.48 |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1239.480283453242 \| rating \| reported \| Higher is better \| ### Configuration category creative_writing config vision ### Reported statistics lower 1223.747852173376 rank 12 upper 1255.2127147331075 variance 64.43109389650418 votes 1518 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/vision/latest) Source Arena Original model label gpt-5-chat Observed 2026-10-21T16:40:19.533Z Evidence SHA-256 `06e61305486dce3fec5dc776ac2fd8321104e84c346cf9e08fa6f8e8a66ce0d7` Source locator `/rows/340/row` |  |  |  |
| 7 | [Qwen3 VL 235B A22B Thinking](https://benchize.com/models/qwen3-vl-235b-a22b-thinking.md) | 1,229.91 |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1229.9050466211634 \| rating \| reported \| Higher is better \| ### Configuration category creative_writing config vision ### Reported statistics lower 1191.714962786859 rank 13 upper 1268.0951304554678 variance 379.6689152085402 votes 219 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/vision/latest) Source Arena Original model label qwen3-vl-235b-a22b-thinking Observed 2026-10-21T16:40:19.533Z Evidence SHA-256 `06e61305486dce3fec5dc776ac2fd8321104e84c346cf9e08fa6f8e8a66ce0d7` Source locator `/rows/341/row` |  |  |  |
| 8 | [Qwen3 VL 235B A22B Instruct](https://benchize.com/models/qwen3-vl-235b-a22b-instruct.md) | 1,224.79 |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1224.7879890801023 \| rating \| reported \| Higher is better \| ### Configuration category creative_writing config vision ### Reported statistics lower 1202.8479450536606 rank 14 upper 1246.728033106544 variance 125.30800259762144 votes 690 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/vision/latest) Source Arena Original model label qwen3-vl-235b-a22b-instruct Observed 2026-10-21T16:40:19.533Z Evidence SHA-256 `06e61305486dce3fec5dc776ac2fd8321104e84c346cf9e08fa6f8e8a66ce0d7` Source locator `/rows/342/row` |  |  |  |
| 9 | [Gemini 2.0 Flash 001](https://benchize.com/models/gemini-2-0-flash-001.md) | 1,205.26 |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1205.259202004486 \| rating \| reported \| Higher is better \| ### Configuration category creative_writing config vision ### Reported statistics lower 1172.0096779046896 rank 18 upper 1238.5087261042827 variance 287.78932808218514 votes 292 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/vision/latest) Source Arena Original model label gemini-2.0-flash-001 Observed 2026-10-21T16:40:19.533Z Evidence SHA-256 `06e61305486dce3fec5dc776ac2fd8321104e84c346cf9e08fa6f8e8a66ce0d7` Source locator `/rows/346/row` |  |  |  |
| 10 | [Gemma 3 27B](https://benchize.com/models/gemma-3-27b-it.md) | 1,182.13 |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1182.1307034271204 \| rating \| reported \| Higher is better \| ### Configuration category creative_writing config vision ### Reported statistics lower 1160.6506866246389 rank 25 upper 1203.6107202296018 variance 120.10830868454175 votes 732 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/vision/latest) Source Arena Original model label gemma-3-27b-it Observed 2026-10-21T16:40:19.533Z Evidence SHA-256 `06e61305486dce3fec5dc776ac2fd8321104e84c346cf9e08fa6f8e8a66ce0d7` Source locator `/rows/353/row` |  |  |  |
| 11 | [Mistral Small 3.1 24B](https://benchize.com/models/mistral-small-3-1-24b-instruct.md) | 1,143.49 |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1143.4937663035084 \| rating \| reported \| Higher is better \| ### Configuration category creative_writing config vision ### Reported statistics lower 1121.9006359102457 rank 31 upper 1165.0868966967714 variance 121.376618088073 votes 777 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/vision/latest) Source Arena Original model label mistral-small-3.1-24b-instruct-2503 Observed 2026-10-21T16:40:19.533Z Evidence SHA-256 `06e61305486dce3fec5dc776ac2fd8321104e84c346cf9e08fa6f8e8a66ce0d7` Source locator `/rows/359/row` |  |  |  |
| 12 | [Llama 4 Scout](https://benchize.com/models/llama-4-scout.md) | 1,126.76 |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1126.759681598881 \| rating \| reported \| Higher is better \| ### Configuration category creative_writing config vision ### Reported statistics lower 1090.1427705507765 rank 32 upper 1163.3765926469855 variance 349.0335930407099 votes 265 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/vision/latest) Source Arena Original model label llama-4-scout-17b-16e-instruct Observed 2026-10-21T16:40:19.533Z Evidence SHA-256 `06e61305486dce3fec5dc776ac2fd8321104e84c346cf9e08fa6f8e8a66ce0d7` Source locator `/rows/360/row` |  |  |  |
| 13 | [Llama 4 Maverick](https://benchize.com/models/llama-4-maverick.md) | 1,112.91 |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1112.9129032575138 \| rating \| reported \| Higher is better \| ### Configuration category creative_writing config vision ### Reported statistics lower 1074.9475947680562 rank 34 upper 1150.8782117469716 variance 375.2128334514461 votes 250 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/vision/latest) Source Arena Original model label llama-4-maverick-17b-128e-instruct Observed 2026-10-21T16:40:19.533Z Evidence SHA-256 `06e61305486dce3fec5dc776ac2fd8321104e84c346cf9e08fa6f8e8a66ce0d7` Source locator `/rows/362/row` |  |  |  |

---
Cite as: Arena vision / creative writing (config: vision) — Benchize, https://benchize.com/benchmarks/benchmark%3Avision%3Acreative_writing--config-vision (retrieved 2026-10-21)