Best LLM for Creative Writing: AI Writing Leaderboard
"Writing" uses two writing-related categories of the LMArena text leaderboard: creative writing and writing/literature/language tasks. Scores come from blind human pairwise votes, not automated benchmarks.
- Claude vs GeminiClaude Opus 5.5 (High)1534.2 vs 1523.1 · Δ11vs Gemini 4 Argon (High)
- Cheapest in top 20
MiMo-V2.6-Pro$0.544 / 1MScore 1466.4 · #20 - Best score per $ in top 20MiMo-V2.6-Pro2,697 / $Score 1466.4 · $0.544
Bottom line (Oct 22, 2026 data): the best LLM for writing is Claude Opus 5.5 (High) (1534.2). Claude Opus 5.5 (High) (1534.2) leads Gemini 4 Argon (High) (1523.1) by 11 points, but Gemini's output price is 50% of Claude's. Best value: MiMo-V2.6-Pro (highest score per dollar, $0.544/1M tokens blended).
Claude vs Gemini: which is better for writing?
| Model | Score | Rank | Writing & literature | Input / output | Score per $ |
|---|---|---|---|---|---|
| Claude Opus 5.5 (High)Top Claude | 1534.2±13.6 | 1 | 1532.1 #1 | $4 / $20 | 192 |
| Claude Sonnet 5.5 (xHigh)Cheapest Claude in top 20 | 1468.3±14.1 | 18 | 1475.7 #18 | $2 / $10 | 367 |
 Gemini 4 Argon (High)Top Gemini | 1523.1±13.4 | 2 | 1524.4 #2 | $2 / $10 | 381 |
| Gemini 3.7 Flash (High)Cheapest Gemini in top 20 | 1489.1±8.4 | 9 | 1491.5 #12 | $0.75 / $3.75 | 993 |
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 · Creative writing
416 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 | Writing & literature | Input / output | Blended | Score per $ |
|---|---|---|---|---|---|---|---|---|
| 1 | Claude Opus 5.5 (High)Anthropic |
1534.2±13.6 | 1 | 2,453 | 1532.1 | $4 / $20 | $8 | 192 |
| 2 | Gemini 4 Argon (High)Google |
1523.1±13.4 | 2 | 2,335 | 1524.4 | $2 / $10 | $4 | 381 |
| 3 | Claude Fable 5.1 (Max)Anthropic |
1509.7±10.9 | 3 | 3,729 | 1511.9 | $10 / $50 | $20 | 76 |
| 4 | Claude Opus 4.6 (High)Anthropic |
1504.8±6.1 | 4 | 15,413 | 1501.7 | $5 / $25 | $10 | 151 |
| 5 | Claude Opus 5 (Max)Anthropic |
1494.6±8 | 5 | 7,903 | 1499.3 | $5 / $25 | $10 | 150 |
| 6 | Claude Fable 5 (High)Anthropic |
1493.4±7.2 | 6 | 9,586 | 1501.1 | $10 / $50 | $20 | 75 |
| 7 |  Muse Wonder (Max)Meta |
1492.6±17 | 7 | 1,350 | 1497.2 | $4 / $20 | $8 | 187 |
| 8 | Gemini 3.8 Flash (High)Google |
1489.4±7.4 | 8 | 9,817 | 1494 | $0.825 / $4.125 | $1.65 | 903 |
| 9 | Gemini 3.7 Flash (High)Google |
1489.1±8.4 | 9 | 6,770 | 1491.5 | $0.75 / $3.75 | $1.5 | 993 |
| 10 | Claude Opus 5 (High)Anthropic |
1486.5±6.5 | 10 | 15,881 | 1492.6 | No price yet | ||
| 11 | Claude Opus 4.7 (High)Anthropic |
1486.2±6.9 | 11 | 11,804 | 1492.5 | $5 / $25 | $10 | 149 |
| 12 | Claude Opus 4.6Anthropic |
1483.7±6 | 12 | 15,623 | 1492.1 | No price yet | ||
| 13 | Gemini 3 ProGoogle |
1482.5±8.1 | 13 | 6,542 | 1478.1 | $2 / $12 | $4.5 | 329 |
| 14 | Gemini 3.1 Pro PreviewGoogle |
1481.8±5.2 | 14 | 24,371 | 1480.9 | $2 / $12 | $4.5 | 329 |
| 15 | Claude Opus 4.7Anthropic |
1479.7±6.8 | 15 | 12,036 | 1479.1 | No price yet | ||
| 16 |  Qwen3.8-MaxAlibaba |
1477.4±8.5 | 16 | 6,134 | 1476.8 | $2 / $6 | $3 | 493 |
| 17 | Gemini 3.5 Flash (Medium)Google |
1470.1±7.3 | 17 | 9,480 | 1472.6 | No price yet | ||
| 18 | Claude Sonnet 5.5 (xHigh)Anthropic |
1468.3±14.1 | 18 | 2,058 | 1475.7 | $2 / $10 | $4 | 367 |
| 19 | Gemini 3.5 Flash (High)Google |
1467.6±7.2 | 19 | 9,477 | 1477.4 | $1.5 / $9 | $3.375 | 435 |
| 20 | MiMo-V2.6-ProXiaomi |
1466.4±21.1 | 20 | 792 | 1469.7 | $0.435 / $0.87 | $0.544 | 2,697 |
| 21 | Gemini 3.6 Flash (High)Google |
1466.1±7.9 | 21 | 7,584 | 1469.9 | $0.75 / $3.75 | $1.5 | 977 |
| 22 | Qwen3.5-Max-PreviewAlibaba |
1464.2±10.7 | 22 | 3,323 | 1466.4 | No price yet | ||
| 23 | Muse Spark 1.3 (Max)Meta |
1462.4±9.8 | 23 | 4,562 | 1470.3 | $1.25 / $4.25 | $2 | 731 |
| 24 |  GLM-5.2 (Max)Z.ai |
1461.6±6.9 | 24 | 10,456 | 1462.6 | $0.034 / $7 | $1.776 | 823 |
| 25 | GLM-5.3 (Max)Z.ai |
1459.2±8.8 | 25 | 5,741 | 1469 | $0.07 / $1.4 | $0.402 | 3,626 |
| 26 | Muse SparkMeta |
1458.7±13.6 | 26 | 2,047 | 1454.1 | No price yet | ||
| 27 | Gemini 3 FlashGoogle |
1456.8±9.2 | 27 | 4,833 | 1459.1 | $0.5 / $3 | $1.125 | 1,295 |
| 28 |  Kimi K3 (Max)Moonshot AI |
1456.2±7.9 | 28 | 7,248 | 1469.9 | $0.202 / $20 | $5.152 | 283 |
| 29 |  GPT-5.5 (High)OpenAI |
1455.3±6.5 | 29 | 13,161 | 1466.3 | $5 / $30 | $11.25 | 129 |
| 30 | Claude Opus 4.8 (High)Anthropic |
1454.4±6.5 | 30 | 12,810 | 1461.5 | $5 / $25 | $10 | 145 |
| 31 | Gemini 2.5 ProGoogle |
1453.7±5.1 | 31 | 17,700 | 1453.9 | $1.25 / $10 | $3.438 | 423 |
| 32 | GLM-5.1Z.ai |
1452.6±6.3 | 32 | 12,807 | 1454.6 | $1.4 / $4.4 | $2.15 | 676 |
| 33 | GPT-5.5OpenAI |
1452.3±6.5 | 33 | 13,417 | 1463.9 | No price yet | ||
| 34 | GPT-5.6 Sol (xHigh)OpenAI |
1450.2±7.4 | 34 | 8,988 | 1462.8 | $4 / $20 | $8 | 181 |
| 35 | Qwen3.7-Max-PreviewAlibaba |
1447.7±26.6 | 35 | 511 | 1461.6 | $1.475 / $4.425 | $2.213 | 654 |
| 36 | Claude Opus 4.8Anthropic |
1446.4±6.5 | 36 | 12,844 | 1452.7 | No price yet | ||
| 37 |  DeepSeek-V4-ProDeepSeek |
1446.2±7.2 | 37 | 9,731 | 1447.1 | $0.435 / $0.87 | $0.544 | 2,659 |
| 38 | Claude Opus 4.5 (High, 32K, 20251101)Anthropic |
1444.8±8.2 | 38 | 5,692 | 1444.8 | No price yet | ||
| 39 | Claude Opus 4.5 (20251101)Anthropic |
1443±6.3 | 39 | 11,407 | 1451.6 | $5 / $25 | $10 | 144 |
| 40 |  Grok 4.5xAI |
1441.8±7.6 | 40 | 8,288 | 1444.9 | $2 / $6 | $3 | 481 |
| 41 | Claude Sonnet 4.5 (20250929)Anthropic |
1441.6±6 | 41 | 12,417 | 1441.8 | No price yet | ||
| 42 |  ERNIE 5.1Baidu |
1440.9±8.3 | 42 | 6,457 | 1449.2 | No price yet | ||
| 43 | DeepSeek-V4-Pro Preview (High)DeepSeek |
1440.8±7.3 | 43 | 9,401 | 1437.6 | No price yet | ||
| 44 | GLM-5.3-FlashZ.ai |
1440.8±7.7 | 44 | 8,207 | 1455.1 | $0.15 / $0.5 | $0.238 | 6,067 |
| 45 | GPT-5.4 (High)OpenAI |
1439±6.9 | 45 | 11,126 | 1458.4 | $2.5 / $15 | $5.625 | 256 |
| 46 | DeepSeek-V4-Pro (High, 20260813)DeepSeek |
1438.6±13.8 | 46 | 1,996 | 1442.7 | $0.955 / $1.911 | $1.194 | 1,205 |
| 47 | DeepSeek-V4.1-Flash-20260910 (Max)DeepSeek |
1438.5±11.8 | 47 | 2,830 | 1450.9 | $0.02 / $1 | $0.265 | 5,428 |
| 48 | Grok 4.20 Beta 1xAI |
1438.4±9.6 | 48 | 4,185 | 1427.6 | No price yet | ||
| 49 | Qwen3.7-PlusAlibaba |
1438±7.6 | 49 | 7,839 | 1437.6 | $0.32 / $1.28 | $0.56 | 2,568 |
| 50 | MiMo-V2.5-ProXiaomi |
1438±6.1 | 50 | 14,635 | 1451 | $0.305 / $0.609 | $0.381 | 3,778 |
Show all 416 models (showing top 50)
Data: LMArena (lmarena-ai), CC-BY-4.0 · Creative writing · 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
- $
- 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.