BenchLeader
Menu
Best LLMsChoose a modelCoding plansLeaderboardsModelsBenchmarksProvidersReleases8

LMArena Creative Writing leaderboard

As of 5 Nov 2026, the top score on LMArena Creative Writing is 1520 by Claude Opus 5.5 (Anthropic), ahead of Gemini 4 Argon at 1517, across 374 model configurations with a published result (Arena (LMArena), result dated 28 Oct 2026). Pairwise votes on stories, poems and other creative prompts. LMArena Creative Writing is shown for reference only and does not count toward the BenchLeader Index.

Key facts (as of 5 Nov 2026)

  • Claude Opus 5.5 holds the top Arena Creative Writing score at 1520 (Arena (LMArena), 28 Oct 2026).
  • Gemini 4 Argon is second on Arena Creative Writing at 1517 (Arena (LMArena), 28 Oct 2026).
  • Arena Creative Writing: Text arena rating on creative-writing prompts (Arena (LMArena)).
  • 374 model configurations have a published Arena Creative Writing result on BenchLeader (BenchLeader, 5 Nov 2026).
  • Arena Creative Writing does not feed the BenchLeader Index; it is shown for reference (BenchLeader methodology).

Text arena rating on creative-writing prompts.

Published by
Arena (LMArena)
Category
Human preference
Index weight
Reference only
Models
374
Data as of
5 Nov 2026

CC BY 4.0 — lmarena-ai/leaderboard-dataset on Hugging Face.

What the test looks like

Pairwise votes on stories, poems and other creative prompts.

How it is scored

Bradley-Terry rating from pairwise votes, in Elo-like units, with style control.

What to keep in mind

Taste-driven by design; the style control removes length and formatting effects but not voice preferences.

Top 15
  1. 1Claude Opus 5.5 (high)1520
  2. 2Gemini 4 Argon (high)1517
  3. 3Gemini 4 Carbon (high)1515
  4. 4Claude Fable 5 (high)1501
  5. 5Claude Opus 4.6 (high)1499
  6. 6Gemini 3.7 Flash (high)1490
  7. 7Claude Opus 4.7 (high)1489
  8. 8Claude Fable 5.1 (max)1489
  9. 9Muse Wonder (max)1487
  10. 10Gemini 3.8 Flash (high)1487
  11. 11Gemini 3 Pro1485
  12. 12Claude Opus 4.71483
  13. 13Gemini 3.1 Pro1481
  14. 14Claude Opus 4.61478
  15. 15Claude Opus 5 (max)1474
374 of 374
#
1Claude Opus 5.5high152065.82026-10-28
2Gemini 4 Argonhigh151765.92026-10-28
3NewGemini 4 Carbonhigh151569.12026-10-28
4Claude Fable 5high150164.32026-10-28
5Claude Opus 4.6high149962.62026-10-28
6Gemini 3.7 Flashhigh149062.22026-10-28
7Claude Opus 4.7high148960.92026-10-28
8Claude Fable 5.1max148967.22026-10-28
9Muse Wondermax148762.22026-10-28
10Gemini 3.8 Flashhigh148762.02026-10-28
11Gemini 3 Pro148560.22026-10-28
12Claude Opus 4.7148363.12026-10-28
13Gemini 3.1 Pro148160.52026-10-28
14Claude Opus 4.6147862.32026-10-28
15Claude Opus 5max147465.42026-10-28
16Claude Opus 5high147264.32026-10-28
17Gemini 3.6 Flashhigh147161.32026-10-28
18GPT-5.6 Solxhigh147064.22026-10-28
19Gemini 3.5 Flashmedium147061.92026-10-28
20Claude Opus 4.5high147059.12026-10-28
21Claude Opus 4.8high146960.62026-10-28
22Qwen3.8 Maxmax146958.82026-10-28
23Claude Sonnet 5.5xhigh146863.42026-10-28
24Gemini 3.5 Flashhigh146562.62026-10-28
25Muse Spark 1.3max146461.92026-10-28
26Muse Spark146464.22026-10-28
27Grok 4.20 11463–2026-10-28
28Claude Opus 4.8146360.02026-10-28
29Kimi K3max146362.12026-10-28
30Claude Opus 4.5146157.92026-10-28
31Gemini 3 Flash145757.02026-10-28
32GLM 5.3max145759.02026-10-28
33GPT-5.5 Instant145457.02026-10-28
34Claude Sonnet 4.5145453.72026-10-28
35GPT-6.1 Solmax145467.22026-10-28
36GLM 5.2max145260.22026-10-28
37Grok 4.5145259.82026-10-28
38GPT-5.5high145163.72026-10-28
39Claude Sonnet 4.5high145057.92026-10-28
40GPT-6 Astramax145067.82026-10-28
41Claude Sonnet 4.6144958.32026-10-28
42GPT-5.5144861.72026-10-28
43GLM-5144854.82026-10-28
44Grok 4.20 Multi-Agent144758.42026-10-28
45Gemini 3 Flashminimal144753.92026-10-28
46DeepSeek V4 Prohigh144757.52026-10-28
47DeepSeek V4 Pro144753.22026-10-28
48GLM 5.1144655.82026-10-28
49Grok 4.20thinking144558.42026-10-28
50Claude Opus 4.1thinking144557.92026-10-28
51Qwen3.5 Maxmax1445–2026-10-28
52Muse Spark 1.1144462.22026-10-28
53MiMo-V2.6-Pro144457.32026-10-28
54Gemini 2.5 Pro144354.52026-10-28
55Claude Opus 4.1144251.42026-10-28
56GPT-5.4high144258.82026-10-28
57Grok 4.6high144260.52026-10-28
58Muse Spark 1.2xhigh144161.72026-10-28
59DeepSeek V4.1 Flashmax144159.02026-10-28
60Qwen3.7max143760.32026-10-28

More human preference benchmarks · All LLM benchmarks

Related benchmarks

Top head-to-heads on Arena Creative Writing

Cite as: BenchLeader, “Arena Creative Writing leaderboard”, data as of 5 Nov 2026, https://www.benchleader.com/benchmarks/lmarena_text_creative.

Arena Creative Writing: questions

What does Arena Creative Writing measure?
Pairwise votes on stories, poems and other creative prompts. Scores are reported in Elo-style ratings from pairwise comparisons; higher is better.
What is the top score on LMArena Creative Writing?
As of 5 Nov 2026, the highest score on Arena Creative Writing is 1520 by Claude Opus 5.5 (result dated 28 Oct 2026), ahead of Gemini 4 Argon at 1517. Scores come from Arena (LMArena) and are re-read daily.
Which AI model leads Arena Creative Writing?
Claude Opus 5.5 leads Arena Creative Writing with 1520 as of 5 Nov 2026 (result dated 28 Oct 2026), ahead of Gemini 4 Argon at 1517.
How many models have Arena Creative Writing results?
374 model configurations have a Arena Creative Writing result on BenchLeader, all taken from Arena (LMArena).
Who runs Arena Creative Writing and how often is it updated?
Arena Creative Writing is published by Arena (LMArena). BenchLeader re-reads the published results once a day and records the date each result was published.
Does Arena Creative Writing count toward the BenchLeader Index?
No. Arena Creative Writing is shown for reference but left out of the composite index.