Best AI Models for Writing

AI models ranked by writing quality using Arena Elo ratings, normalized to a 0-100 scale.

Last updated: just now

#1 Model

Claude Opus 4.6

Score: 100

Average Score

76.8

Across all ranked models

Models Ranked

With benchmark data

Weights:Arena Elo (100%)

#	Model	Provider	Score	Arena Elo
1	Claude Opus 4.6Anthropic	Anthropic	100	100
2	Grok 4.20 BetaxAI	xAI	99.3	99.3
3	Gemini 3.1 Pro PreviewGoogle	Google	98.7	98.7
4	Gemini 3 Pro PreviewGoogle	Google	97.7	97.7
5	GPT-5.4OpenAI	OpenAI	97.5	97.5
6	GPT-5.2 ChatOpenAI	OpenAI	96.8	96.8
7	GPT-5.2OpenAI	OpenAI	96.8	96.8
8	Gemini 3 Flash PreviewGoogle	Google	95.7	95.7
9	Grok 4.1 FastxAI	xAI	95.5	95.5
10	GPT-5OpenAI	OpenAI	94.2	94.2
11	Grok 4xAI	xAI	93.7	93.7
12	Claude Sonnet 4.6Anthropic	Anthropic	93.3	93.3
13	GPT-5.1OpenAI	OpenAI	92.7	92.7
14	Claude Sonnet 4.5Anthropic	Anthropic	92	92
15	Qwen3.5 397B A17BAlibaba	Alibaba	91.7	91.7
16	Claude Opus 4.1Anthropic	Anthropic	91.5	91.5
17	Gemini 2.5 ProGoogle	Google	90.7	90.7
18	Gemini 3.1 Flash Lite PreviewGoogle	Google	89.5	89.5
19	Claude Opus 4.5Anthropic	Anthropic	88.3	88.3
20	GPT-5 ChatOpenAI	OpenAI	87.8	87.8
21	DeepSeek V3.2 ExpDeepSeek	DeepSeek	87.3	87.3
22	DeepSeek V3.2DeepSeek	DeepSeek	87.2	87.2
23	Grok 4 FastxAI	xAI	87	87
24	Claude Opus 4Anthropic	Anthropic	86.7	86.7
25	Qwen3.5-122B-A10BAlibaba	Alibaba	86.5	86.5
26	DeepSeek V3.1DeepSeek	DeepSeek	86.5	86.5
27	DeepSeek V3.1 TerminusDeepSeek	DeepSeek	86.2	86.2
28	Qwen3 VL 235B A22B InstructAlibaba	Alibaba	86	86
29	o3OpenAI	OpenAI	85.8	85.8
30	Qwen3.5-27BAlibaba	Alibaba	85	85
31	MiniMax M2.5MiniMax	MiniMax	84	84
32	Qwen3 Next 80B A3B InstructAlibaba	Alibaba	83.7	83.7
33	LongCat Flash ChatMeituan	Meituan	83.5	83.5
34	Qwen3.5-FlashAlibaba	Alibaba	83.3	83.3
35	Qwen3.5-35B-A3BAlibaba	Alibaba	83	83
36	Qwen3 VL 235B A22B ThinkingAlibaba	Alibaba	82.7	82.7
37	Gemini 2.5 FlashGoogle	Google	82.5	82.5
38	GPT-5 MiniOpenAI	OpenAI	81.8	81.8
39	Step 3.5 FlashStepFun	StepFun	81.5	81.5
40	Claude 3.7 Sonnet (thinking)Anthropic	Anthropic	81.3	81.3
41	Claude Sonnet 4Anthropic	Anthropic	81.2	81.2
42	R1 0528DeepSeek	DeepSeek	80	80
43	o4 MiniOpenAI	OpenAI	80	80
44	o3 MiniOpenAI	OpenAI	78.5	78.5
45	R1DeepSeek	DeepSeek	78.2	78.2
46	Qwen3 Next 80B A3B ThinkingAlibaba	Alibaba	78.2	78.2
47	MiniMax M1MiniMax	MiniMax	77.8	77.8
48	o3 Mini HighOpenAI	OpenAI	77.3	77.3
49	Grok 3 Mini BetaxAI	xAI	76.3	76.3
50	gpt-oss-120bOpenAI	OpenAI	75.8	75.8
51	Claude 3.7 SonnetAnthropic	Anthropic	75.7	75.7
52	Command ACohere	Cohere	75.7	75.7
53	Gemini 2.0 FlashGoogle	Google	75.3	75.3
54	o1OpenAI	OpenAI	75	75
55	MiniMax M2MiniMax	MiniMax	74.7	74.7
56	Qwen3 8BAlibaba	Alibaba	74.7	74.7
57	GPT-4o (2024-05-13)OpenAI	OpenAI	74.3	74.3
58	DeepSeek V3 0324DeepSeek	DeepSeek	74.2	74.2
59	Grok 3xAI	xAI	73.7	73.7
60	Llama 3.3 Nemotron Super 49B V1.5NVIDIA	NVIDIA	73.7	73.7
61	GPT-5 NanoOpenAI	OpenAI	73	73
62	Nova 2 LiteAmazon	Amazon	73	73
63	QwQ 32BAlibaba	Alibaba	72.7	72.7
64	GPT-4o (2024-08-06)OpenAI	OpenAI	72.5	72.5
65	Olmo 3.1 32B InstructAllen AI	Allen AI	71.8	71.8
66	Llama 4 MaverickMeta	Meta	70.8	70.8
67	DeepSeek V3DeepSeek	DeepSeek	69.7	69.7
68	GPT-4o-mini (2024-07-18)OpenAI	OpenAI	69.7	69.7
69	gpt-oss-20bOpenAI	OpenAI	69.7	69.7
70	Mistral Large 2407Mistral AI	Mistral AI	69	69
71	MercuryInception	Inception	68.2	68.2
72	Olmo 3 32B ThinkAllen AI	Allen AI	67.8	67.8
73	Qwen2.5 72B InstructAlibaba	Alibaba	67.2	67.2
74	GPT-4.1OpenAI	OpenAI	66.7	66.7
75	Llama 3.1 Nemotron 70B InstructNVIDIA	NVIDIA	66.5	66.5
76	GPT-4oOpenAI	OpenAI	64.3	64.3
77	Olmo 3.1 32B ThinkAllen AI	Allen AI	64.2	64.2
78	Mistral LargeMistral AI	Mistral AI	63.3	63.3
79	Llama 3 70B InstructMeta	Meta	62.7	62.7
80	Qwen2.5 Coder 32B InstructAlibaba	Alibaba	61.8	61.8
81	Claude 3.5 SonnetAnthropic	Anthropic	61.8	61.8
82	Claude 3 HaikuAnthropic	Anthropic	60.2	60.2
83	Phi 4Microsoft	Microsoft	59.3	59.3
84	GPT-4 TurboOpenAI	OpenAI	59.2	59.2
85	Command R+ (08-2024)Cohere	Cohere	58.3	58.3
86	Llama 3.3 70B InstructMeta	Meta	57.2	57.2
87	Claude Haiku 4.5Anthropic	Anthropic	56.7	56.7
88	Llama 3 8B InstructMeta	Meta	53.8	53.8
89	GPT-4o-miniOpenAI	OpenAI	53.7	53.7
90	Llama 3.1 8B InstructMeta	Meta	52	52
91	Llama 3.1 70B InstructMeta	Meta	49.7	49.7
92	Claude 3.5 HaikuAnthropic	Anthropic	46.3	46.3
93	Llama 3.2 3B InstructMeta	Meta	44.5	44.5
94	Llama 3.2 1B InstructMeta	Meta	35.2	35.2

How scores are calculated

Each model's score is a weighted average of its available benchmark results. When a model is missing some benchmarks, the weights are re-normalized across the benchmarks that are available. All scores are on a 0-100 scale. Data sourced from official model cards, published papers, and third-party evaluation platforms.

Other Specialty Leaderboards

Best for Coding Best for Math Best for Reasoning Best for Instructions Best for Data Analysis Best for Roleplay Best for Multilingual

Frequently Asked Questions

Based on our benchmark analysis, Claude Opus 4.6 by Anthropic is currently the #1 ranked model for writing, with a weighted score of 100/100.

Models are ranked using a weighted average of Arena Elo benchmark scores. All scores are normalized to a 0-100 scale.

We currently rank 94 models that have relevant benchmark data for writing tasks.