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.
- Claude vs GeminiClaude Opus 5.5 (High)1532.1 vs 1524.4 · Δ8vs Gemini 4 Argon (High)
- Cheapest in top 20
Gemini 3.7 Flash (High)$1.5 / 1MScore 1491.5 · #12 - Best score per $ in top 20Gemini 3.7 Flash (High)994 / $Score 1491.5 · $1.5
Claude vs Gemini: which is better for writing?
| Model | Score | Rank | Creative writing | Input / output | Score per $ |
|---|---|---|---|---|---|
| Claude Opus 5.5 (High)Top Claude | 1532.1±11.9 | 1 | 1534.2 #1 | $4 / $20 | 192 |
| Claude Sonnet 5.5 (xHigh)Cheapest Claude in top 20 | 1475.7±12.5 | 18 | 1468.3 #18 | $2 / $10 | 369 |
| Gemini 4 Argon (High)Top Gemini | 1524.4±11.9 | 2 | 1523.1 #2 | $2 / $10 | 381 |
| Gemini 3.7 Flash (High)Cheapest Gemini in top 20 | 1491.5±7.5 | 12 | 1489.1 #9 | $0.75 / $3.75 | 994 |
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 · Writing & literature
67 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 |
1532.1±11.9 | 1 | 3,104 | 1534.2 | $4 / $20 | $8 | 192 |
| 2 | Gemini 4 Argon (High)Google |
1524.4±11.9 | 2 | 2,914 | 1523.1 | $2 / $10 | $4 | 381 |
| 3 | Claude Fable 5.1 (Max)Anthropic |
1511.9±9.6 | 3 | 4,724 | 1509.7 | $10 / $50 | $20 | 76 |
| 4 | Claude Opus 4.6 (High)Anthropic |
1501.7±5.3 | 4 | 21,687 | 1504.8 | $5 / $25 | $10 | 150 |
| 5 | Claude Fable 5 (High)Anthropic |
1501.1±6.4 | 5 | 12,474 | 1493.4 | $10 / $50 | $20 | 75 |
| 6 | Claude Opus 5 (Max)Anthropic |
1499.3±7.1 | 6 | 10,036 | 1494.6 | $5 / $25 | $10 | 150 |
| 7 |  Muse Wonder (Max)Meta |
1497.2±14.8 | 7 | 1,771 | 1492.6 | $4 / $20 | $8 | 187 |
| 8 | Gemini 3.8 Flash (High)Google |
1494±6.8 | 8 | 12,513 | 1489.4 | $0.825 / $4.125 | $1.65 | 906 |
| 9 | Claude Opus 4.7 (High)Anthropic |
1492.5±6 | 10 | 16,578 | 1486.2 | $5 / $25 | $10 | 149 |
| 10 | Gemini 3.7 Flash (High)Google |
1491.5±7.5 | 12 | 8,550 | 1489.1 | $0.75 / $3.75 | $1.5 | 994 |
| 11 | Gemini 3.1 Pro PreviewGoogle |
1480.9±4.6 | 13 | 33,586 | 1481.8 | $2 / $12 | $4.5 | 329 |
| 12 | Gemini 3 ProGoogle |
1478.1±6.9 | 15 | 9,574 | 1482.5 | $2 / $12 | $4.5 | 329 |
| 13 | Gemini 3.5 Flash (High)Google |
1477.4±6.3 | 16 | 12,677 | 1467.6 | $1.5 / $9 | $3.375 | 438 |
| 14 |  Qwen3.8-MaxAlibaba |
1476.8±7.5 | 17 | 8,031 | 1477.4 | $2 / $6 | $3 | 492 |
| 15 | Claude Sonnet 5.5 (xHigh)Anthropic |
1475.7±12.5 | 18 | 2,568 | 1468.3 | $2 / $10 | $4 | 369 |
| 16 | Muse Spark 1.3 (Max)Meta |
1470.3±8.6 | 20 | 5,839 | 1462.4 | $1.25 / $4.25 | $2 | 735 |
| 17 |  Kimi K3 (Max)Moonshot AI |
1469.9±7.1 | 21 | 9,511 | 1456.2 | $0.202 / $20 | $5.152 | 285 |
| 18 | Gemini 3.6 Flash (High)Google |
1469.9±7 | 22 | 9,856 | 1466.1 | $0.75 / $3.75 | $1.5 | 980 |
| 19 |  MiMo-V2.6-ProXiaomi |
1469.7±18.5 | 23 | 1,001 | 1466.4 | $0.435 / $0.87 | $0.544 | 2,703 |
| 20 |  GLM-5.3 (Max)Z.ai |
1469±7.9 | 24 | 7,239 | 1459.2 | $0.07 / $1.4 | $0.402 | 3,651 |
| 21 |  GPT-5.5 (High)OpenAI |
1466.3±5.8 | 26 | 18,172 | 1455.3 | $5 / $30 | $11.25 | 130 |
| 22 | GPT-5.6 Sol (xHigh)OpenAI |
1462.8±6.7 | 28 | 11,702 | 1450.2 | $4 / $20 | $8 | 183 |
| 23 | GLM-5.2 (Max)Z.ai |
1462.6±6.1 | 29 | 14,034 | 1461.6 | $0.034 / $7 | $1.776 | 824 |
| 24 | Qwen3.7-Max-PreviewAlibaba |
1461.6±20 | 30 | 908 | 1447.7 | $1.475 / $4.425 | $2.213 | 661 |
| 25 | Claude Opus 4.8 (High)Anthropic |
1461.5±5.8 | 31 | 17,297 | 1454.4 | $5 / $25 | $10 | 146 |
| 26 | Gemini 3 FlashGoogle |
1459.1±7.8 | 32 | 7,061 | 1456.8 | $0.5 / $3 | $1.125 | 1,297 |
| 27 | GPT-5.4 (High)OpenAI |
1458.4±5.9 | 33 | 16,347 | 1439 | $2.5 / $15 | $5.625 | 259 |
| 28 | GLM-5.3-FlashZ.ai |
1455.1±6.9 | 34 | 10,617 | 1440.8 | $0.15 / $0.5 | $0.238 | 6,127 |
| 29 | GLM-5.1Z.ai |
1454.6±5.5 | 35 | 17,329 | 1452.6 | $1.4 / $4.4 | $2.15 | 677 |
| 30 | Gemini 2.5 ProGoogle |
1453.9±4.2 | 37 | 28,259 | 1453.7 | $1.25 / $10 | $3.438 | 423 |
| 31 | Muse Spark 1.2 (xHigh)Meta |
1453.8±11.7 | 38 | 2,949 | 1434.7 | $1.25 / $4.25 | $2 | 727 |
| 32 | Claude Opus 4.5 (20251101)Anthropic |
1451.6±5.4 | 40 | 16,904 | 1443 | $5 / $25 | $10 | 145 |
| 33 | MiMo-V2.5-ProXiaomi |
1451±5.4 | 41 | 20,206 | 1438 | $0.305 / $0.609 | $0.381 | 3,812 |
| 34 |  DeepSeek-V4.1-Flash-20260910 (Max)DeepSeek |
1450.9±10.4 | 42 | 3,655 | 1438.5 | $0.02 / $1 | $0.265 | 5,475 |
| 35 | Muse Spark 1.1Meta |
1447.2±6.4 | 45 | 12,793 | 1434.6 | $1.25 / $4.25 | $2 | 724 |
| 36 | DeepSeek-V4-ProDeepSeek |
1447.1±6.3 | 46 | 14,141 | 1446.2 | $0.435 / $0.87 | $0.544 | 2,661 |
| 37 |  Grok 4.5xAI |
1444.9±6.7 | 47 | 10,889 | 1441.8 | $2 / $6 | $3 | 482 |
| 38 | Claude Sonnet 4.6Anthropic |
1443.9±5.7 | 49 | 17,600 | 1435.4 | $3 / $15 | $6 | 241 |
| 39 | DeepSeek-V4-Pro (High, 20260813)DeepSeek |
1442.7±11.9 | 51 | 2,630 | 1438.6 | $0.955 / $1.911 | $1.194 | 1,208 |
| 40 | GPT-6.1 Sol (Max)OpenAI |
1442.4±13 | 52 | 2,390 | 1424.4 | $2 / $10 | $4 | 361 |
| 41 | GPT-6 Astra (Max)OpenAI |
1439.6±10.1 | 54 | 3,970 | 1420.5 | $10 / $50 | $20 | 72 |
| 42 | Kimi K2.6Moonshot AI |
1439±7 | 55 | 9,594 | 1433.6 | $0.65 / $3.41 | $1.34 | 1,074 |
| 43 | Qwen3.7-PlusAlibaba |
1437.6±6.6 | 57 | 10,845 | 1438 | $0.32 / $1.28 | $0.56 | 2,567 |
| 44 | GLM-5Z.ai |
1436.4±7.4 | 58 | 7,025 | 1437.9 | $1 / $3.2 | $1.55 | 927 |
| 45 | Claude Sonnet 5 (High)Anthropic |
1435.9±6.1 | 60 | 14,193 | 1416 | $2 / $10 | $4 | 359 |
| 46 | GPT-5.6 Terra (xHigh)OpenAI |
1431.8±6.4 | 62 | 12,984 | 1413 | $2 / $12 | $4.5 | 318 |
| 47 | Grok 4.6 (High)xAI |
1431.2±7.2 | 65 | 9,217 | 1427.9 | $2 / $6 | $3 | 477 |
| 48 |  Step 5 PreviewStepFun |
1429.4±12 | 67 | 2,685 | 1411.4 | $1 / $2.7 | $1.425 | 1,003 |
| 49 | GPT-5.1 (High)OpenAI |
1427.8±6.8 | 68 | 9,358 | 1427.1 | $1.25 / $10 | $3.438 | 415 |
| 50 | Kimi K2.5 (Thinking)Moonshot AI |
1425.2±5.3 | 71 | 17,928 | 1422.1 | $0.5 / $2.5 | $1 | 1,425 |
Show all 67 models (showing top 50)
Data: LMArena (lmarena-ai), CC-BY-4.0 · Writing & literature · 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).
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.