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)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 |  LLaMA 13BMeta |
793.7±31.9 | 416 | 431 | 809 | No price yet | ||
| 2 | ?Dolly 2.0 12B | 863.5±26.9 | 415 | 565 | 872.2 | No price yet | ||
| 3 | ?StableLM Tuned Alpha 7B | 867.6±27.4 | 414 | 536 | 867.9 | No price yet | ||
| 4 | ?ChatGLM 6B | 899.8±23.8 | 413 | 771 | 925.3 | No price yet | ||
| 5 | ?FastChat-T5 3B | 901.9±23.3 | 412 | 744 | 907.5 | No price yet | ||
| 6 | ?OpenAssistant Pythia 12B | 923.1±19.9 | 411 | 1,094 | 928.2 | No price yet | ||
| 7 | ?RWKV-4 Raven 14B | 933.5±22.2 | 410 | 874 | 934 | No price yet | ||
| 8 | ?ChatGLM2 6B | 940.9±26.2 | 409 | 566 | 952.7 | No price yet | ||
| 9 | ?MPT 7B Chat | 957.4±23.7 | 408 | 683 | 972.8 | No price yet | ||
| 10 | ?Alpaca 13B | 967.3±22.1 | 407 | 954 | 968.2 | No price yet | ||
| 11 |  Qwen1.5-4B-ChatAlibaba |
969±18.7 | 406 | 1,080 | 1000.8 | No price yet | ||
| 12 | ?ChatGLM3 6B | 969.8±22.9 | 405 | 816 | 972.5 | No price yet | ||
| 13 | ?GPT4All 13B Snoozy | 971.8±37.5 | 404 | 250 | 973.1 | No price yet | ||
| 14 | ?Koala 13B | 972.7±20.2 | 403 | 1,200 | 979.4 | No price yet | ||
| 15 | Gemma 2B ITGoogle |
986.2±23 | 402 | 696 | 978.3 | No price yet | ||
| 16 |  OLMo 7B InstructAi2 |
989.5±20.1 | 401 | 1,019 | 1003.1 | No price yet | ||
| 17 | PaLM 2Google |
991.2±17.3 | 400 | 1,576 | 1006.8 | No price yet | ||
| 18 | Gemma 1.1 2B ITGoogle |
997.7±16.8 | 399 | 1,486 | 1006 | No price yet | ||
| 19 | ?Vicuna 7B | 1020.8±17.8 | 398 | 1,323 | 1048.5 | No price yet | ||
| 20 | Gemma 7B ITGoogle |
1023.3±17.6 | 397 | 1,345 | 1033.8 | No price yet | ||
| 21 |  Phi-3 Mini 128K InstructMicrosoft |
1024±13.9 | 396 | 2,949 | 1040.3 | No price yet | ||
| 22 | Qwen-14B-ChatAlibaba |
1027.4±20.7 | 395 | 898 | 1049.9 | No price yet | ||
| 23 |  Mistral 7B InstructMistral AI |
1028.1±16.9 | 394 | 1,689 | 1030.3 | No price yet | ||
| 24 | ?StripedHyena Nous 7B | 1029±20.7 | 393 | 869 | 1034.6 | No price yet | ||
| 25 | ?SmolLM2 1.7B Instruct | 1031.2±34.1 | 392 | 341 | 1024.5 | No price yet | ||
| 26 | Code Llama 34B InstructMeta |
1031.4±16.6 | 391 | 1,507 | 1048.3 | No price yet | ||
| 27 | Llama 3.2 1B InstructMeta |
1032.5±19.8 | 390 | 1,091 | 1029.7 | No price yet | ||
| 28 | Llama 2 7B ChatMeta |
1033±13.6 | 389 | 2,341 | 1037.1 | No price yet | ||
| 29 | Qwen1.5-7B-ChatAlibaba |
1034.3±22.4 | 388 | 701 | 1064.3 | No price yet | ||
| 30 |  GPT-3.5 Turbo (1106)OpenAI |
1034.8±15.3 | 387 | 2,828 | 1091 | No price yet | ||
| 31 | Phi-3 Mini 4K InstructMicrosoft |
1036.7±12.6 | 386 | 2,812 | 1054.4 | No price yet | ||
| 32 | Phi-3 Mini 4K Instruct (June 2024)Microsoft |
1044.4±14.5 | 385 | 1,955 | 1056.6 | No price yet | ||
| 33 |  Granite 3.0 2B InstructIBM |
1046±20.7 | 384 | 916 | 1050.5 | No price yet | ||
| 34 | Llama 2 13B ChatMeta |
1046.6±12.5 | 383 | 3,296 | 1061.5 | No price yet | ||
| 35 | ?Vicuna 13B | 1057.9±12.6 | 382 | 3,346 | 1078.9 | No price yet | ||
| 36 | Gemma 1.1 7B ITGoogle |
1059.2±11.7 | 381 | 3,409 | 1073.1 | No price yet | ||
| 37 |  DeepSeek LLM 67B ChatDeepSeek |
1067.2±21.8 | 380 | 789 | 1110.6 | No price yet | ||
| 38 | Mistral 7B Instruct v0.2Mistral AI |
1067.4±12.5 | 379 | 2,952 | 1073 | No price yet | ||
| 39 | ?Zephyr 7B Alpha | 1068.5±29.9 | 378 | 399 | 1081.6 | No price yet | ||
| 40 | Granite 3.0 8B InstructIBM |
1070.4±20.4 | 377 | 895 | 1078.4 | No price yet | ||
| 41 | ?MPT 30B Chat | 1073.8±28.6 | 376 | 452 | 1079.3 | No price yet | ||
| 42 | Llama 2 70B ChatMeta |
1074.6±10 | 375 | 6,376 | 1092.7 | No price yet | ||
| 43 | ?Guanaco 33B | 1079.7±27.2 | 374 | 515 | 1066.3 | No price yet | ||
| 44 | ?Snowflake Arctic Instruct | 1080.7±12 | 373 | 4,777 | 1100.9 | No price yet | ||
| 45 | Phi-3 Small 8K InstructMicrosoft |
1082.6±12.9 | 372 | 2,400 | 1093.7 | No price yet | ||
| 46 | Qwen1.5-32B-ChatAlibaba |
1082.7±12.3 | 371 | 3,022 | 1118.1 | No price yet | ||
| 47 | ?Dolphin 2.2.1 Mistral 7B | 1085.5±33.1 | 370 | 291 | 1085.9 | No price yet | ||
| 48 | ?Falcon 180B Chat | 1088.3±36.5 | 369 | 270 | 1105.1 | No price yet | ||
| 49 |  SOLAR 10.7B Instruct v1.0Upstage |
1089.1±24 | 368 | 698 | 1087.8 | No price yet | ||
| 50 | WizardLM 13BMicrosoft |
1090.2±17.8 | 367 | 1,375 | 1098.2 | No price yet | ||
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
- 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.