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.
"Multi-turn" is LMArena's multi_turn category: only battles with several back-and-forth turns, reflecting how well a model keeps context and revises across a conversation.
- Claude vs GeminiGemini 4 Argon (High)1511.6 vs 1546.6 · Δ35vs Claude Opus 4.6 (High)
- Cheapest in top 20Gemini 3.7 Flash (High)$1.5 / 1MScore 1486.5 · #18
- Best score per $ in top 20Gemini 3.7 Flash (High)991 / $Score 1486.5 · $1.5
Claude vs Gemini: which is better for writing?
| Model | Score | Rank | Creative writing | Input / output | Score per $ |
|---|---|---|---|---|---|
 Claude Opus 4.6 (High)Top Claude | 1511.6±6.1 | 2 | 1504.8 #4 | $5 / $25 | 151 |
| Claude Opus 5.5 (High)Cheapest Claude in top 20 | 1504±16.6 | 8 | 1534.2 #1 | $4 / $20 | 188 |
| Gemini 4 Argon (High)Top Gemini | 1546.6±16.9 | 1 | 1523.1 #2 | $2 / $10 | 387 |
| Gemini 3.7 Flash (High)Cheapest Gemini in top 20 | 1486.5±9.5 | 18 | 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 · Multi-turn
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 | Creative writing | Input / output | Blended | Score per $ |
|---|---|---|---|---|---|---|---|---|
| 1 | ?Dolly 2.0 12B | 740.3±35.3 | 416 | 356 | 863.5 | No price yet | ||
| 2 |  LLaMA 13BMeta |
753.1±42.7 | 415 | 247 | 793.7 | No price yet | ||
| 3 | ?StableLM Tuned Alpha 7B | 820.6±33.3 | 414 | 354 | 867.6 | No price yet | ||
| 4 | ?FastChat-T5 3B | 852.9±30.4 | 413 | 387 | 901.9 | No price yet | ||
| 5 | ?ChatGLM 6B | 856.4±29.1 | 412 | 492 | 899.8 | No price yet | ||
| 6 | ?OpenAssistant Pythia 12B | 869.2±25.1 | 411 | 683 | 923.1 | No price yet | ||
| 7 | ?Alpaca 13B | 884.3±25.7 | 410 | 653 | 967.3 | No price yet | ||
| 8 | ?RWKV-4 Raven 14B | 893.7±26.9 | 409 | 556 | 933.5 | No price yet | ||
| 9 | ?MPT 7B Chat | 901.5±28.8 | 408 | 466 | 957.4 | No price yet | ||
| 10 | ?ChatGLM2 6B | 902±32.3 | 407 | 369 | 940.9 | No price yet | ||
| 11 | ?Koala 13B | 923.4±23.9 | 406 | 792 | 972.7 | No price yet | ||
| 12 | ?GPT4All 13B Snoozy | 926.6±37.6 | 405 | 253 | 971.8 | No price yet | ||
| 13 | Gemma 2B ITGoogle |
944.8±23.3 | 404 | 768 | 986.2 | No price yet | ||
| 14 | Gemma 1.1 2B ITGoogle |
958.5±17.9 | 403 | 1,478 | 997.7 | No price yet | ||
| 15 | ?ChatGLM3 6B | 961.8±25.6 | 402 | 637 | 969.8 | No price yet | ||
| 16 | Gemma 7B ITGoogle |
963.2±18.7 | 401 | 1,332 | 1023.3 | No price yet | ||
| 17 |  Qwen1.5-4B-ChatAlibaba |
977.4±18.7 | 400 | 1,136 | 969 | No price yet | ||
| 18 | ?Vicuna 7B | 987.8±20.9 | 399 | 935 | 1020.8 | No price yet | ||
| 19 |  Phi-3 Mini 128K InstructMicrosoft |
988.9±15.5 | 398 | 2,507 | 1024 | No price yet | ||
| 20 | ?SmolLM2 1.7B Instruct | 993±37.8 | 397 | 339 | 1031.2 | No price yet | ||
| 21 | PaLM 2Google |
994.3±19.5 | 396 | 1,163 | 991.2 | No price yet | ||
| 22 | ?Guanaco 33B | 1005.9±33.4 | 395 | 331 | 1079.7 | No price yet | ||
| 23 |  OLMo 7B InstructAi2 |
1007±27.5 | 394 | 537 | 989.5 | No price yet | ||
| 24 | ?StripedHyena Nous 7B | 1007.6±22.8 | 393 | 738 | 1029 | No price yet | ||
| 25 |  Mistral 7B InstructMistral AI |
1008.1±19.2 | 392 | 1,259 | 1028.1 | No price yet | ||
| 26 | ?Falcon 180B Chat | 1012.9±39.8 | 391 | 207 | 1088.3 | No price yet | ||
| 27 | Code Llama 34B InstructMeta |
1015.3±18.4 | 390 | 1,155 | 1031.4 | No price yet | ||
| 28 | ?Zephyr 7B Alpha | 1017.6±34.4 | 389 | 283 | 1068.5 | No price yet | ||
| 29 | Phi-3 Mini 4K InstructMicrosoft |
1018.2±13.3 | 388 | 2,939 | 1036.7 | No price yet | ||
| 30 | ?Dolphin 2.2.1 Mistral 7B | 1020.6±40.3 | 387 | 208 | 1085.5 | No price yet | ||
| 31 | Qwen-14B-ChatAlibaba |
1022.1±23.3 | 386 | 753 | 1027.4 | No price yet | ||
| 32 | Llama 2 7B ChatMeta |
1029±15 | 385 | 1,851 | 1033 | No price yet | ||
| 33 | Llama 3.2 1B InstructMeta |
1029.8±18.5 | 384 | 1,236 | 1032.5 | No price yet | ||
| 34 | ?Vicuna 13B | 1030.8±13.9 | 383 | 2,552 | 1057.9 | No price yet | ||
| 35 | ?Zephyr 7B Beta | 1037.9±17.5 | 382 | 1,574 | 1102.1 | No price yet | ||
| 36 | Gemma 1.1 7B ITGoogle |
1039.8±11.7 | 381 | 3,635 | 1059.2 | No price yet | ||
| 37 |  SOLAR 10.7B Instruct v1.0Upstage |
1045.1±24.9 | 380 | 601 | 1089.1 | No price yet | ||
| 38 | WizardLM 13BMicrosoft |
1047±20 | 379 | 983 | 1090.2 | No price yet | ||
| 39 | Phi-3 Mini 4K Instruct (June 2024)Microsoft |
1049.1±14.7 | 378 | 1,839 | 1044.4 | No price yet | ||
| 40 | Llama 2 13B ChatMeta |
1050.1±13.8 | 377 | 2,596 | 1046.6 | No price yet | ||
| 41 |  Granite 3.0 2B InstructIBM |
1052.9±19 | 376 | 1,162 | 1046 | No price yet | ||
| 42 | ?MPT 30B Chat | 1054.5±32 | 375 | 341 | 1073.8 | No price yet | ||
| 43 |  Llama 2 70B SteerLM ChatNVIDIA |
1057.9±28.1 | 374 | 451 | 1090.3 | No price yet | ||
| 44 | Qwen1.5-7B-ChatAlibaba |
1061.5±24.9 | 373 | 589 | 1034.3 | No price yet | ||
| 45 | Mistral 7B Instruct v0.2Mistral AI |
1062.4±13.1 | 372 | 2,566 | 1067.4 | No price yet | ||
| 46 | Granite 3.0 8B InstructIBM |
1062.8±19.7 | 371 | 1,148 | 1070.4 | No price yet | ||
| 47 | ?OpenHermes 2.5 Mistral 7B | 1064.4±22.5 | 370 | 722 | 1096.9 | No price yet | ||
| 48 | Phi-3 Small 8K InstructMicrosoft |
1068.4±12.2 | 369 | 3,115 | 1082.6 | No price yet | ||
| 49 | ?Snowflake Arctic Instruct | 1072.2±12.5 | 368 | 3,963 | 1080.7 | No price yet | ||
| 50 |  GPT-3.5 Turbo (1106)OpenAI |
1077.8±15.8 | 367 | 2,374 | 1034.8 | No price yet | ||
Show all 416 models (showing top 50)
Data: LMArena (lmarena-ai), CC-BY-4.0 · Multi-turn · 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 is best at multi-turn conversations?
On LMArena's Multi-turn category (published Oct 22, 2026, 416 models), the top three are Gemini 4 Argon (High) (1546.6), Claude Opus 4.6 (High) (1511.6), Muse Wonder (Max) (1507.4).
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.