Best LLM for Creative Writing: AI Writing Leaderboard
The writing board covers five writing-related categories of the LMArena text leaderboard, one per tab: creative writing (creative_writing, default), writing/literature/language tasks, longer prompts (longer_query; not a long-context test), multi-turn (multi_turn) and instruction following (instruction_following). Scores come from blind human pairwise votes, not automated benchmarks.
"Instruction following" is LMArena's instruction_following category: only prompts with explicit format, length or constraint requirements, reflecting how well a model follows them.
- Claude vs GeminiClaude Opus 5.5 (High)1538.8 vs 1527.6 · Δ11vs Gemini 4 Argon (High)
- Cheapest in top 20
GLM-5.3-Flash$0.238 / 1MScore 1479.1 · #20 - Best score per $ in top 20GLM-5.3-Flash6,228 / $Score 1479.1 · $0.238
Claude vs Gemini: which is better for writing?
| Model | Score | Rank | Creative writing | Input / output | Score per $ |
|---|---|---|---|---|---|
| Claude Opus 5.5 (High)Top Claude | 1538.8±10.7 | 1 | 1534.2 #1 | $4 / $20 | 192 |
| Claude Sonnet 5.5 (xHigh)Cheapest Claude in top 20 | 1490.5±11.2 | 13 | 1468.3 #18 | $2 / $10 | 373 |
 Gemini 4 Argon (High)Top Gemini | 1527.6±10.4 | 2 | 1523.1 #2 | $2 / $10 | 382 |
| Gemini 3.7 Flash (High)Cheapest Gemini in top 20 | 1486±6.8 | 15 | 1489.1 #9 | $0.75 / $3.75 | 991 |
When the gap is smaller than the combined confidence intervals, the rank difference may not be significant. Prices are OpenRouter quotes (USD / 1M tokens).
Full ranking · Instruction following
80 modelsSorted by LMArena score; ± is the 95% CI half-width. Prices: OpenRouter quote (official list price if none), USD per 1M tokens.
| # | Model | Score↓ | Rank | Votes | Creative writing | Input / output | Blended | Score per $ |
|---|---|---|---|---|---|---|---|---|
| 1 | Claude Opus 5.5 (High)Anthropic |
1538.8±10.7 | 1 | 3,593 | 1534.2 | $4 / $20 | $8 | 192 |
| 2 | Gemini 4 Argon (High)Google |
1527.6±10.4 | 2 | 3,595 | 1523.1 | $2 / $10 | $4 | 382 |
| 3 | Claude Opus 4.6 (High)Anthropic |
1521±4.9 | 3 | 26,917 | 1504.8 | $5 / $25 | $10 | 152 |
| 4 | Claude Fable 5.1 (Max)Anthropic |
1518.9±9.3 | 4 | 4,903 | 1509.7 | $10 / $50 | $20 | 76 |
| 5 | Claude Opus 5 (Max)Anthropic |
1518.4±6.6 | 5 | 11,981 | 1494.6 | $5 / $25 | $10 | 152 |
| 6 | Claude Opus 5 (High)Anthropic |
1514.2±5.5 | 6 | 25,022 | 1486.5 | $5 / $25 | $10 | 151 |
| 7 | Claude Opus 4.6Anthropic |
1509.9±4.7 | 7 | 29,546 | 1483.7 | $5 / $25 | $10 | 151 |
| 8 | Claude Fable 5 (High)Anthropic |
1501.6±5.9 | 8 | 15,587 | 1493.4 | $10 / $50 | $20 | 75 |
| 9 | Claude Opus 4.7 (High)Anthropic |
1497.7±5.4 | 9 | 22,749 | 1486.2 | $5 / $25 | $10 | 150 |
| 10 |  Muse Wonder (Max)Meta |
1492.6±13.3 | 10 | 2,104 | 1492.6 | $4 / $20 | $8 | 187 |
| 11 | Gemini 3.8 Flash (High)Google |
1491.6±6.2 | 11 | 15,791 | 1489.4 | $0.825 / $4.125 | $1.65 | 904 |
| 12 |  MiMo-V2.6-ProXiaomi |
1490.6±15.8 | 12 | 1,390 | 1466.4 | $0.435 / $0.87 | $0.544 | 2,741 |
| 13 | Claude Sonnet 5.5 (xHigh)Anthropic |
1490.5±11.2 | 13 | 3,031 | 1468.3 | $2 / $10 | $4 | 373 |
| 14 | Claude Opus 4.7Anthropic |
1488.7±5.3 | 14 | 23,299 | 1479.7 | $5 / $25 | $10 | 149 |
| 15 | Gemini 3.7 Flash (High)Google |
1486±6.8 | 15 | 10,965 | 1489.1 | $0.75 / $3.75 | $1.5 | 991 |
| 16 |  Kimi K3 (Max)Moonshot AI |
1484.6±6.4 | 16 | 11,772 | 1456.2 | $0.202 / $20 | $5.152 | 288 |
| 17 |  GPT-5.6 Sol (xHigh)OpenAI |
1482.7±6 | 17 | 14,874 | 1450.2 | $4 / $20 | $8 | 185 |
| 18 |  Qwen3.8-MaxAlibaba |
1480.7±6.7 | 18 | 10,824 | 1477.4 | $2 / $6 | $3 | 494 |
| 19 | GLM-5.3 (Max)Z.ai |
1480.3±7.3 | 19 | 8,368 | 1459.2 | $0.07 / $1.4 | $0.402 | 3,679 |
| 20 | GLM-5.3-FlashZ.ai |
1479.1±6.4 | 20 | 13,261 | 1440.8 | $0.15 / $0.5 | $0.238 | 6,228 |
| 21 | Muse Spark 1.3 (Max)Meta |
1479±7.7 | 21 | 7,300 | 1462.4 | $1.25 / $4.25 | $2 | 740 |
| 22 | GPT-5.5 (High)OpenAI |
1478.5±5.3 | 22 | 24,012 | 1455.3 | $5 / $30 | $11.25 | 131 |
| 23 | Claude Opus 4.5 (High, 32K, 20251101)Anthropic |
1477.8±6.6 | 23 | 9,874 | 1444.8 | $5 / $25 | $10 | 148 |
| 24 | Claude Opus 4.8 (High)Anthropic |
1476.5±5.3 | 24 | 22,661 | 1454.4 | $5 / $25 | $10 | 148 |
| 25 | Claude Sonnet 4.6Anthropic |
1476±5.1 | 25 | 23,703 | 1435.4 | $3 / $15 | $6 | 246 |
| 26 | MiMo-V2.5-ProXiaomi |
1475.2±5 | 26 | 26,041 | 1438 | $0.305 / $0.609 | $0.381 | 3,876 |
| 27 | GPT-5.5OpenAI |
1475.2±5.2 | 27 | 24,823 | 1452.3 | $5 / $30 | $11.25 | 131 |
| 28 |  DeepSeek-V4.1-Flash-20260910 (Max)DeepSeek |
1473.8±9 | 28 | 4,815 | 1438.5 | $0.02 / $1 | $0.265 | 5,562 |
| 29 | Claude Opus 4.5 (20251101)Anthropic |
1472.4±4.9 | 29 | 21,818 | 1443 | $5 / $25 | $10 | 147 |
| 30 | GPT-5.4 (High)OpenAI |
1469.4±5.4 | 30 | 21,857 | 1439 | $2.5 / $15 | $5.625 | 261 |
| 31 | Gemini 3.6 Flash (High)Google |
1466.9±6.3 | 31 | 13,097 | 1466.1 | $0.75 / $3.75 | $1.5 | 978 |
| 32 | GPT-6.1 Sol (Max)OpenAI |
1466.9±12.3 | 32 | 2,541 | 1424.4 | $2 / $10 | $4 | 367 |
| 33 | Gemini 3.5 Flash (High)Google |
1466.8±5.6 | 33 | 17,396 | 1467.6 | $1.5 / $9 | $3.375 | 435 |
| 34 | Gemini 3.1 Pro PreviewGoogle |
1466.1±4.2 | 35 | 44,777 | 1481.8 | $2 / $12 | $4.5 | 326 |
| 35 | GLM-5.2 (Max)Z.ai |
1465.9±5.6 | 36 | 18,036 | 1461.6 | $0.034 / $7 | $1.776 | 826 |
| 36 | Gemini 3.5 Flash (Medium)Google |
1464.5±5.7 | 37 | 17,060 | 1470.1 | $1.5 / $9 | $3.375 | 434 |
| 37 | Claude Opus 4.8Anthropic |
1462.9±5.3 | 38 | 23,277 | 1446.4 | $5 / $25 | $10 | 146 |
| 38 | Muse Spark 1.2 (xHigh)Meta |
1462.8±10.3 | 39 | 3,661 | 1434.7 | $1.25 / $4.25 | $2 | 731 |
| 39 | Qwen3.7-Max-PreviewAlibaba |
1460.3±16.3 | 40 | 1,380 | 1447.7 | $1.475 / $4.425 | $2.213 | 660 |
| 40 | Gemini 3 ProGoogle |
1458±6.2 | 43 | 11,694 | 1482.5 | $2 / $12 | $4.5 | 324 |
| 41 | Muse Spark 1.1Meta |
1456.3±5.7 | 45 | 16,535 | 1434.6 | $1.25 / $4.25 | $2 | 728 |
| 42 | GPT-5.6 Terra (xHigh)OpenAI |
1455.4±5.8 | 46 | 16,552 | 1413 | $2 / $12 | $4.5 | 323 |
| 43 | GPT-6 Astra (Max)OpenAI |
1455.3±9.3 | 47 | 4,439 | 1420.5 | $10 / $50 | $20 | 73 |
| 44 | GPT-5.4OpenAI |
1454.9±5.3 | 48 | 23,384 | 1427.7 | $2.5 / $15 | $5.625 | 259 |
| 45 | GLM-5.1Z.ai |
1452.4±4.9 | 49 | 22,863 | 1452.6 | $1.4 / $4.4 | $2.15 | 676 |
| 46 | Claude Sonnet 5 (High)Anthropic |
1452.3±5.6 | 50 | 18,217 | 1416 | $2 / $10 | $4 | 363 |
| 47 | Kimi K2.6Moonshot AI |
1450.7±6.3 | 51 | 13,202 | 1433.6 | $0.65 / $3.41 | $1.34 | 1,083 |
| 48 | MiMo-V2.6-FlashXiaomi |
1448.9±9.3 | 52 | 4,551 | 1404.3 | $0.14 / $0.28 | $0.175 | 8,279 |
| 49 | DeepSeek-V4-Pro (High, 20260813)DeepSeek |
1448±10.3 | 53 | 3,480 | 1438.6 | $0.955 / $1.911 | $1.194 | 1,213 |
| 50 |  Grok 4.5xAI |
1445.4±6.1 | 54 | 14,513 | 1441.8 | $2 / $6 | $3 | 482 |
Show all 80 models (showing top 50)
Data: LMArena (lmarena-ai), CC-BY-4.0 · Instruction following · published Oct 22, 2026
Sources & method
- LMLMArena leaderboard dataset (Hugging Face, CC-BY-4.0)
config text · creative_writing · published Oct 22, 2026 · 416 models
- LMLMArena leaderboard dataset (Hugging Face, CC-BY-4.0)
config text · industry_writing_and_literature_and_language · published Oct 22, 2026 · 417 models
- LMLMArena leaderboard dataset (Hugging Face, CC-BY-4.0)
config text · longer_query · published Oct 22, 2026 · 396 models
- LMLMArena leaderboard dataset (Hugging Face, CC-BY-4.0)
config text · multi_turn · published Oct 22, 2026 · 416 models
- LMLMArena leaderboard dataset (Hugging Face, CC-BY-4.0)
config text · instruction_following · published Oct 22, 2026 · 418 models
- $
- Only the latest LMArena publish date is used; score, CI, votes and rank are copied from the dataset.
- Reasoning tiers of one model (e.g. High / Max) are separate LMArena entries and are listed separately.
- Prices are shown only when the entry maps to our LLM leaderboard; otherwise –, never estimated.
- Score ÷ blended price (3:1 input:output). A rough value indicator only.
- Synced daily at 06:35 UTC; if the source fails, the last good snapshot is kept.
FAQ
What is the best AI for writing?
In LMArena's creative writing category published Oct 22, 2026, #1 is Anthropic's Claude Opus 5.5 (High) (1534.2, 2,453 votes).
Claude or Gemini: which is better for writing?
Top creative-writing scores: Claude Claude Opus 5.5 (High) (1534.2, output $20/1M tokens); Gemini Gemini 4 Argon (High) (1523.1, output $10/1M tokens).
What is the cheapest good LLM for writing?
Among the top 20 for creative writing, the best score per dollar is MiMo-V2.6-Pro (1466.4, #20) at about $0.544/1M tokens blended; the cheapest is MiMo-V2.6-Pro ($0.544/1M, 1466.4).
Which vendors rank highest for writing?
By the creative writing category, each vendor's best model ranks: Anthropic Claude Opus 5.5 (High) (1534.2, #1), Google Gemini 4 Argon (High) (1523.1, #2), Meta Muse Wonder (Max) (1492.6, #7), Alibaba Qwen3.8-Max (1477.4, #16), Xiaomi MiMo-V2.6-Pro (1466.4, #20).
Which LLM follows instructions best?
On LMArena's Instruction following category (published Oct 22, 2026, 418 models), the top three are Claude Opus 5.5 (High) (1538.8), Gemini 4 Argon (High) (1527.6), Claude Opus 4.6 (High) (1521).
Where do the scores come from?
From LMArena: users submit writing prompts, two anonymous models answer, users vote for the better one, and scores are fitted with a Bradley-Terry model.