---
title: "Creative writing leaderboard"
description: "Rankings on stories, copy and poetry."
canonical: https://pirouter.ai/rankings/creative
last-updated: 2026-10-15
---

# Creative writing leaderboard

> Rankings on stories, copy and poetry.

- Updated: 2026-09-30
- 1,763,417 votes · 383 models
- Score · higher is better

## Full ranking

| Rank | Rank spread | Model | Vendor | Score | Votes |
|---|---|---|---|---|---|
| 1 | 1–5 | Gemini 4 Argon (high) | Google | 1522 ±19 | 1104 |
| 2 | 1–7 | [Claude Opus 5.5 \(high\)](https://pirouter.ai/models/anthropic/claude-opus-5.5) | Anthropic | 1515 ±21 | 908 |
| 3 | 1–6 | Claude Fable 5 (high) | Anthropic | 1503 ±8 | 8072 |
| 4 | 1–6 | Claude Opus 4.6 (high) | Anthropic | 1501 ±6 | 13974 |
| 5 | 1–9 | [Gemini 3.7 Flash \(high\)](https://pirouter.ai/models/google/gemini-3.7-flash) | Google | 1496 ±10 | 4600 |
| 6 | 2–10 | Claude Opus 4.7 (high) | Anthropic | 1489 ±7 | 11712 |
| 7 | 5–17 | Gemini 3 Pro | Google | 1484 ±8 | 6509 |
| 8 | 5–18 | [Gemini 3.8 Flash \(high\)](https://pirouter.ai/models/google/gemini-3.8-flash) | Google | 1484 ±9 | 5335 |
| 9 | 4–21 | [Claude Fable 5.1 \(max\)](https://pirouter.ai/models/anthropic/claude-fable-5.1) | Anthropic | 1482 ±13 | 2506 |
| 10 | 6–19 | Gemini 3.1 Pro Preview | Google | 1480 ±5 | 22144 |
| 11 | 7–28 | Claude Opus 5 (high) | Anthropic | 1472 ±7 | 12964 |
| 12 | 7–28 | [Gemini 3.6 Flash \(high\)](https://pirouter.ai/models/google/gemini-3.6-flash) | Google | 1472 ±8 | 7475 |
| 13 | 8–29 | Claude Opus 4.8 (high) | Anthropic | 1469 ±7 | 12699 |
| 14 | 7–30 | [Gemini 3.5 Flash \(medium\)](https://pirouter.ai/models/google/gemini-3.5-flash) | Google | 1469 ±7 | 9356 |
| 15 | 7–30 | Claude Opus 4.5 20251101 High 32k | Anthropic | 1469 ±8 | 5677 |
| 16 | 7–30 | [GPT-5.6 Sol \(xhigh\)](https://pirouter.ai/models/openai/gpt-5.6-sol) | OpenAI | 1469 ±8 | 7388 |
| 17 | 7–34 | Qwen3.8 (max) | Alibaba | 1468 ±10 | 4437 |
| 18 | 7–48 | Muse Spark | Meta | 1465 ±14 | 2046 |
| 19 | 10–46 | Grok 4.20 Beta1 | xAI | 1463 ±10 | 4172 |
| 20 | 11–39 | Claude Opus 4.5 | Anthropic | 1462 ±6 | 11402 |
| 21 | 11–48 | Kimi K3 (max) | Moonshot | 1460 ±9 | 5548 |
| 22 | 10–52 | Muse Spark 1.3 (max) | Meta | 1459 ±13 | 2482 |
| 23 | 11–52 | Gemini 3 Flash | Google | 1457 ±9 | 4816 |
| 24 | 11–52 | GPT-5.5 Instant | OpenAI | 1456 ±10 | 4351 |
| 25 | 14–52 | [GLM 5.2 \(max\)](https://pirouter.ai/models/z-ai/glm-5.2) | Z.ai | 1455 ±7 | 8871 |
| 26 | 11–52 | GLM 5.3 (max) | Z.ai | 1455 ±10 | 3895 |
| 27 | 17–52 | Claude Sonnet 4.5 | Anthropic | 1454 ±6 | 12376 |
| 28 | 9–69 | Muse Spark 1.2 (xhigh) | Meta | 1453 ±22 | 734 |
| 29 | 17–52 | [GPT-5.5 \(high\)](https://pirouter.ai/models/openai/gpt-5.5) | OpenAI | 1451 ±7 | 13155 |
| 30 | 17–54 | Grok 4.5 | xAI | 1451 ±8 | 8173 |
| 31 | 18–53 | Claude Sonnet 4.5 20250929 High 32k | Anthropic | 1450 ±6 | 12649 |
| 32 | 18–55 | Claude Sonnet 4.6 | Anthropic | 1449 ±7 | 12357 |
| 33 | 18–59 | GLM 5 | Z.ai | 1449 ±9 | 4851 |
| 34 | 13–67 | [GPT-6 Astra \(max\)](https://pirouter.ai/models/openai/gpt-6-astra) | OpenAI | 1448 ±15 | 1875 |
| 35 | 18–59 | Muse Spark 1.1 | Meta | 1448 ±8 | 7540 |
| 36 | 19–59 | Grok 4.20 Multi Agent Beta 0309 | xAI | 1447 ±7 | 11288 |
| 37 | 19–59 | GLM 5.1 | Z.ai | 1447 ±7 | 11139 |
| 38 | 20–59 | Gemini 3 Flash | Google | 1447 ±6 | 15204 |
| 39 | 19–60 | [DeepSeek V4 Pro 0813](https://pirouter.ai/models/deepseek/deepseek-v4-pro) | DeepSeek | 1446 ±7 | 9736 |
| 40 | 20–60 | Grok 4.20 Beta 0309 Reasoning | xAI | 1446 ±7 | 11441 |
| 41 | 18–66 | Qwen3.5 Preview (max) | Alibaba | 1446 ±11 | 3318 |
| 42 | 19–62 | Claude Opus 4.1 (thinking) | Anthropic | 1445 ±8 | 6816 |
| 43 | 19–65 | Grok 4.6 (high) | xAI | 1445 ±9 | 5033 |
| 44 | 11–76 | MiMo V2.6 Pro | Xiaomi | 1445 ±21 | 798 |
| 45 | 22–62 | Gemini 2.5 Pro | Google | 1443 ±5 | 17584 |
| 46 | 22–65 | [GPT-5.4 \(high\)](https://pirouter.ai/models/openai/gpt-5.4) | OpenAI | 1442 ±7 | 11118 |
| 47 | 11–89 | Qwen3.7 Preview (max) | Alibaba | 1439 ±27 | 506 |
| 48 | 19–76 | [GPT-6 Sol \(max\)](https://pirouter.ai/models/openai/gpt-6-sol) | OpenAI | 1438 ±16 | 1532 |
| 49 | 19–76 | [DeepSeek V4.1 Flash \(max\)](https://pirouter.ai/models/deepseek/deepseek-v4.1-flash) | DeepSeek | 1438 ±15 | 1626 |
| 50 | 17–87 | Qwen3.6 Preview (max) | Alibaba | 1437 ±22 | 759 |
| 51 | 22–74 | GPT-4.5 Preview 2025 02 27 | OpenAI | 1436 ±12 | 2618 |
| 52 | 31–73 | [Claude Sonnet 5 \(high\)](https://pirouter.ai/models/anthropic/claude-sonnet-5) | Anthropic | 1436 ±7 | 9284 |
| 53 | 30–74 | [Gemini 3.5 Flash Lite](https://pirouter.ai/models/google/gemini-3.5-flash-lite) | Google | 1435 ±8 | 7360 |
| 54 | 32–73 | MiMo V2.5 Pro | Xiaomi | 1435 ±6 | 12991 |
| 55 | 29–74 | [GLM 5.3 Flash](https://pirouter.ai/models/z-ai/glm-5.3-flash) | Z.ai | 1435 ±10 | 4577 |
| 56 | 32–74 | Kimi K2.6 | Moonshot | 1434 ±8 | 6327 |
| 57 | 32–74 | GPT-5.2 Chat Latest | OpenAI | 1433 ±8 | 5643 |
| 58 | 22–85 | Grok 4.7 (xhigh) | xAI | 1433 ±17 | 1293 |
| 59 | 32–76 | Claude Opus 4 (thinking) | Anthropic | 1432 ±9 | 4416 |
| 60 | 37–74 | Qwen3.7 Plus | Alibaba | 1432 ±8 | 7818 |
| 61 | 39–74 | Grok 4.1 | xAI | 1431 ±7 | 10065 |
| 62 | 41–79 | GPT-5.1 (high) | OpenAI | 1428 ±8 | 6213 |
| 63 | 41–79 | Ernie 5.1 | Baidu | 1428 ±8 | 6456 |
| 64 | 44–80 | [GPT-5.6 Terra \(xhigh\)](https://pirouter.ai/models/openai/gpt-5.6-terra) | OpenAI | 1426 ±8 | 7834 |
| 65 | 46–82 | Kimi K2.5 (thinking) | Moonshot | 1423 ±6 | 12258 |
| 66 | 45–89 | MiMo V2 Pro | Xiaomi | 1423 ±10 | 3734 |
| 67 | 41–94 | Hy3 | Tencent | 1423 ±14 | 1998 |
| 68 | 46–85 | Grok 4.3 | xAI | 1422 ±7 | 13208 |
| 69 | 48–85 | Chatgpt 4o Latest | OpenAI | 1422 ±6 | 11469 |
| 70 | 46–88 | Ernie 5.0 0110 | Baidu | 1422 ±8 | 5760 |
| 71 | 43–101 | Ernie 5.0 Preview 1203 | Baidu | 1420 ±15 | 1574 |
| 72 | 39–107 | Gemma 4 31b | Google | 1419 ±19 | 972 |
| 73 | 59–97 | Grok 4.1 Fast Reasoning | xAI | 1414 ±7 | 8964 |
| 74 | 59–99 | Gemini 3.1 Flash Lite Preview | Google | 1413 ±7 | 10597 |
| 75 | 61–104 | [DeepSeek V4 Flash 0731 \(high\)](https://pirouter.ai/models/deepseek/deepseek-v4-flash) | DeepSeek | 1411 ±8 | 8650 |
| 76 | 55–117 | DeepSeek V3.2 Exp | DeepSeek | 1409 ±15 | 1645 |
| 77 | 55–117 | [GPT-6 Luna \(max\)](https://pirouter.ai/models/openai/gpt-6-luna) | OpenAI | 1409 ±16 | 1588 |
| 78 | 63–107 | [GPT-5.6 Luna \(xhigh\)](https://pirouter.ai/models/openai/gpt-5.6-luna) | OpenAI | 1409 ±8 | 7794 |
| 79 | 66–108 | Qwen3.6 Plus | Alibaba | 1407 ±8 | 7213 |
| 80 | 63–110 | GPT-5.3 Chat Latest | OpenAI | 1407 ±9 | 5354 |
| 81 | 46–124 | Ernie 5.0 Preview 1022 | Baidu | 1407 ±22 | 733 |
| 82 | 59–118 | GLM 5v Turbo | Z.ai | 1406 ±14 | 1957 |
| 83 | 68–108 | Minimax M3 | MiniMax | 1406 ±7 | 10514 |
| 84 | 62–118 | GLM 4.7 | Z.ai | 1405 ±13 | 1956 |
| 85 | 70–109 | Qwen3.5 397b A17b | Alibaba | 1405 ±6 | 15391 |
| 86 | 45–134 | DeepSeek V3.1 Terminus | DeepSeek | 1404 ±27 | 447 |
| 87 | 70–113 | Dola Seed 2.0 Pro | ByteDance | 1404 ±6 | 13179 |
| 88 | 70–117 | GPT-4.1 2025 04 14 | OpenAI | 1402 ±8 | 6595 |
| 89 | 63–124 | DeepSeek V3.1 (thinking) | DeepSeek | 1402 ±15 | 1608 |
| 90 | 71–117 | [GPT-5.4 Mini \(high\)](https://pirouter.ai/models/openai/gpt-5.4-mini) | OpenAI | 1402 ±7 | 10803 |
| 91 | 71–117 | DeepSeek V3.2 | DeepSeek | 1401 ±8 | 6857 |
| 92 | 70–118 | GLM 4.6 | Z.ai | 1401 ±9 | 5109 |
| 93 | 66–124 | Mistral Medium 3.5 | Mistral | 1400 ±14 | 2067 |
| 94 | 62–131 | Gemma 4 26b A4b | Google | 1399 ±18 | 996 |
| 95 | 72–122 | Grok 3 Preview 02 24 | xAI | 1398 ±9 | 4690 |
| 96 | 73–124 | Claude Sonnet 4 (thinking) | Anthropic | 1396 ±9 | 4213 |
| 97 | 74–124 | Grok 4 0709 | xAI | 1395 ±9 | 5278 |
| 98 | 73–125 | MiMo V2 Omni | Xiaomi | 1395 ±11 | 3455 |
| 99 | 75–124 | MiMo V2.5 | Xiaomi | 1395 ±8 | 7909 |
| 100 | 79–121 | Gemini 2.5 Flash | Google | 1394 ±5 | 17563 |

## FAQ

### What is the best AI model for creative writing?

As of 2026-09-30, Google Gemini 4 Argon (high) is #1 on the creative writing board with a score of 1522, rank spread 1–5.

### What is the best open-weights model for creative writing?

Kimi K3 (Moonshot), #21 on this board.

### What does this board rank?

Rankings on stories, copy and poetry.

### How often is it updated?

Whenever new models ship or the rankings change; this board was last updated on 2026-09-30.

Data: [LMArena leaderboard dataset](https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset), used under [CC BY 4.0](https://creativecommons.org/licenses/by/4.0/); filtered and reasoning tiers merged, scores unchanged.
View the original board: https://arena.ai/leaderboard/text/creative-writing