LLMBenchmark.ai

Enter opens the highlighted result. Esc closes.

Best LLM for creative writing

Claude Opus 5.5 leads
1535
models ranked
156
lead over #2
+7 Elo

LMArena Text: creative writing · read October 21

As of October 21, 2026, Anthropic Claude Opus 5.5 leads 156 models on LMArena Text: creative writing with 1535, ahead of Google Gemini 4 Argon (1527) and Anthropic Claude Fable 5.1 (1509).

This list narrows the best LLM for general use ranking.

Top 20 of 156, higher is better

Embed this data
Best LLM for creative writing
Rank Model LMArena Text: creative writing Evidence Coding index Output $/Mtok
1
Claude Opus 5.5 Anthropic
1535
92.2 $20.00
2
1527
80.5 $10.00
3
Claude Fable 5.1 Anthropic
1509
89.1 $50.00
4
Claude Opus 4.6 Anthropic
1505
66.9 $25.00
5
Claude Fable 5 Anthropic
1494
82.1 $50.00
6
Claude Opus 5 Anthropic
1493
81.8 $25.00
7
1491
64.5 $20.00
8
1488
69.9 $3.75
9
1488
70.5 $4.125
10
Claude Opus 4.7 Anthropic
1486
51.1 $25.00
11
1482
35.3 $12.00
12
1477
63.5 $6.00
13
1470
42.8 $9.00
14
Claude Sonnet 5.5 Anthropic
1467
88.9 $10.00
15
1466
48.3 $3.75
16
MiMo-V2.6-Pro Xiaomi
1466
72.6 $0.87
17
GLM 5.2 Z.ai
1463
57.7 $7.00
18
1462
79.7 $4.25
19
GLM 5.3 Z.ai
1458
73.1 $1.40
20
Kimi K3 Moonshot AI
1457
61.8 $11.936

How this list is built

Generated from the dataset on every refresh. Nobody picks the order by hand.

Models by their LMArena Text: creative writing result, as the board publishes it, best first. Prompts that ask for creative writing. People ask a question, compare two anonymous answers and vote for the better one; the rating is built from those votes, as LMArena publishes it.

Other lists

Rankings beyond coding · Methodology