Best AI Models for Roleplay

AI models ranked by roleplay and creative conversation quality using Arena Elo ratings, normalized to a 0-100 scale.

Last updated: 24m ago

#1 Model

Claude Opus 4.6

Score: 100

Average Score

81.8

Across all ranked models

Models Ranked

With benchmark data

Weights:Arena Elo (100%)

Top Best for Roleplay Models by Weighted Score

Top 15 models by weighted score

LMMarketCap.com

#	Model	Provider	Score	Arena Elo
1	Claude Opus 4.6Anthropic	Anthropic	100	100
2	Gemini 3.1 Pro PreviewGoogle	Google	99	99
3	Claude Opus 4.7Anthropic	Anthropic	98.5	98.5
4	GPT-5.4OpenAI	OpenAI	97.5	97.5
5	GPT-5.2OpenAI	OpenAI	96.8	96.8
6	Claude Opus 4.8Anthropic	Anthropic	96.5	96.5
7	Gemini 3.5 FlashGoogle	Google	96.2	96.2
8	GPT-5.1OpenAI	OpenAI	95.8	95.8
9	GPT-5.5OpenAI	OpenAI	95.8	95.8
10	Gemini 3 Flash PreviewGoogle	Google	95.7	95.7
11	GPT-5OpenAI	OpenAI	94.2	94.2
12	Claude Sonnet 4.6Anthropic	Anthropic	93.3	93.3
13	Claude Sonnet 4.5Anthropic	Anthropic	92	92
14	Gemini 2.5 ProGoogle	Google	90.7	90.7
15	Claude Opus 4.5Anthropic	Anthropic	88.3	88.3
16	DeepSeek V3.2DeepSeek	DeepSeek	87.5	87.5
17	o3OpenAI	OpenAI	85.8	85.8
18	Gemini 2.5 FlashGoogle	Google	82.5	82.5
19	R1 0528DeepSeek	DeepSeek	80	80
20	DeepSeek V3 0324DeepSeek	DeepSeek	74.2	74.2
21	Llama 4 MaverickMeta	Meta	70.8	70.8
22	DeepSeek V3DeepSeek	DeepSeek	69.7	69.7
23	GPT-4.1OpenAI	OpenAI	66.7	66.7
24	GPT-4oOpenAI	OpenAI	64.3	64.3
25	Mistral LargeMistral AI	Mistral AI	63.3	63.3
26	Command ACohere	Cohere	60.2	60.2
27	Llama 3.3 70B InstructMeta	Meta	57.2	57.2
28	Claude Haiku 4.5Anthropic	Anthropic	56.7	56.7
29	GPT-4o-miniOpenAI	OpenAI	53.7	53.7
30	Llama 3.1 70B InstructMeta	Meta	49.7	49.7

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 Writing Best for Instructions Best for Data Analysis Best for Multilingual

Frequently Asked Questions

Based on our benchmark analysis, Claude Opus 4.6 by Anthropic is currently the #1 ranked model for roleplay, 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 30 models that have relevant benchmark data for roleplay tasks.