What is the best AI model for agents?

The model at the top of this board, ranked by Artificial Analysis's agentic index. It updates every week.

What does the agentic index measure?

How well a model completes multi-step tasks with tools, such as working in a terminal or automating software through its API.

An AI model that works through a task on its own, step by step, using tools like a browser, a terminal or other apps.

What does the chart show?

Each dot is a model, placed by its agentic score and its price. The line joins the models no cheaper model beats, so anything under it costs more for less.

Is the top model always the best choice?

Not always. A model a little lower on the board can cost far less or read more at once, so match it to your job.

How often is this board updated?

Every week, from OpenRouter's public model list. The date under the table shows when the board was last checked.

Where do these numbers come from?

Every model and price comes from OpenRouter's public model list. The scores are Artificial Analysis's and Design Arena's, carried in that same list.

Can I download the data?

Yes: every board has a CSV of its models, next to its chart.

What does open weights mean?

The maker publishes the model's weights, so anyone can download the model and run it on their own hardware.

What is a context window?

It's the most text a model can work with at once, counted in tokens. Your prompt and the model's reply both count toward it.

Why do some models have no score?

Not every model on OpenRouter has been tested on every measure yet. A board lists only the models with a result on its own measure.

How do I use these models?

Through each maker's own app or API, or through OpenRouter, which gives you most of them with one account.

Best AI model for agents

Find the best AI model for agents among 96 AI models, ranked by Artificial Analysis's agentic index, which scores how well a model completes tasks with tools.

Updated Oct 1, 2026

Rank	Model
1	Claude Fable 5.1Anthropic	57.9Lead	53.4#3	81.6Lead	$20	1M	Sept 1, 2026
2	Claude Opus 5Anthropic	56.5#2	50.8	78.0#2	$10	1M	Jul 24, 2026
3	Qwen3.8 Max (0902)Qwen	56.0#3	45.4	76.2	$3	1M	Sept 3, 2026
4	GLM 5.3Open weightsZ.ai	53.1	44.8	74.8	$1.01	1M	Aug 18, 2026
5	Grok 4.6xAI	53.0	44.3	76.8	$3	500K	Aug 12, 2026
6	GPT-6 AstraOpenAI	51.0	52.7	76.9	$20	1.1M	Sept 4, 2026
7	GLM 5.3 FlashOpen weightsZ.ai	50.9	41.8	71.5	$0.24	1M	Aug 26, 2026
8	Claude Fable 5Anthropic	50.7	49.6	76.5	$20	1M	Jun 9, 2026
9	GPT-5.6 SolOpenAI	50.2	47.0	77.4#3	$4	1.1M	Jul 9, 2026
10	Qwen3.8 2.4T A95BOpen weightsQwen	50.1	39.9	71.9	$3	1M	Aug 12, 2026
11	Kimi K3Open weightsMoonshot AI	50.0	43.6	76.2	$3.00	1M	Jul 16, 2026
12	Qwen3.8 27BOpen weightsQwen	45.8	33.7	68.1	$1.07	1M	Aug 14, 2026
13	Claude Sonnet 5Anthropic	43.6	38.2	71.5	$4	1M	Jun 30, 2026
14	Muse Spark 1.2Meta	43.2	39.6	72.2	$2	1M	Aug 5, 2026
15	GPT-5.6 TerraOpenAI	43.2	42.1	76.7	$4.50	1.1M	Jul 9, 2026
16	GPT-5.6 LunaOpenAI	42.1	37.3	71.4	$0.45	1.1M	Jul 9, 2026
17	Claude Opus 4.8Anthropic	41.9	41.8	74.3	$10	1M	May 27, 2026
18	DeepSeek V4 Pro 0813Open weightsDeepSeek	41.3	36.0	68.8	$0.99	1M	Aug 12, 2026
19	Grok 4.5xAI	41.2	38.8	72.4	$3	500K	Jul 8, 2026
20	DeepSeek V4 Flash 0731Open weightsDeepSeek	41.0	34.3	69.1	$0.33	1M	Jul 31, 2026
21	Gemini 3.8 FlashGoogle	40.2	40.9	76.3	$1.50	1M	Sept 2, 2026
22	Claude Opus 4.7Anthropic	38.6	40.7	73.6	$10	1M	Apr 16, 2026
23	GLM 5.2Open weightsZ.ai	38.4	33.7	68.8	$1.31	1M	Jun 16, 2026
24	GPT-5.5OpenAI	36.4	38.4	74.9	$11.25	1.1M	Apr 24, 2026
25	Gemini 3.7 FlashGoogle	35.2	39.1	76.1	$1.50	1M	Aug 13, 2026

Source: Artificial Analysis's indexes and OpenRouter's prices, in US dollars per million tokens, checked Oct 1, 2026

Data by

Independent benchmark · Artificial Analysis

Top 10: Agents

Oct 1, 2026

157.9Claude Fable 5.1
256.5Claude Opus 5
356.0Qwen3.8 Max (0902)
453.1GLM 5.3
553.0Grok 4.6
651.0GPT-6 Astra
750.9GLM 5.3 Flash
850.7Claude Fable 5
950.2GPT-5.6 Sol
1050.1Qwen3.8 2.4T A95B

Source: Artificial Analysis's indexes and OpenRouter's prices, in US dollars per million tokens, checked Oct 1, 2026

Data by

How to read this chart

The bars show this board's 10 best models, best first, with the top 3 in the brand's blue. The bars start just below the lowest score, so small gaps show: read the numbers on the bars. Hover a bar for its maker, or switch to Price to see what each one costs.

Comparison details

Prices are OpenRouter's list prices in US dollars per million tokens, blended 3 parts input to 1 part output, as Artificial Analysis does. Scores are Artificial Analysis's, checked Oct 1, 2026. Speed, latency and each provider's own price aren't part of the score.

Every leaderboard

Each board has its own page with every model, a chart and a CSV.

LLM leaderboard

Claude Opus 5.5 leads, from Anthropic

Best AI model for coding

Claude Fable 5.1 leads, from Anthropic

AI model pricing

Cheapest now: Mistral Nemo

Best AI model for writing

Best AI model for website design

Muse Spark 1.3 leads, from Meta

Best AI model for game development

Claude Opus 5.5 leads, from Anthropic

Best AI model for UI design

Claude Opus 5.5 leads, from Anthropic

Best AI model for data visualization

Claude Opus 5.5 leads, from Anthropic

Best AI model for SVG graphics

Claude Opus 5.5 leads, from Anthropic

Best AI model for 3D scenes

Claude Opus 5.5 leads, from Anthropic

Best AI model for building mobile apps

Claude Opus 5 leads, from Anthropic

Best AI model for building full-stack apps

Claude Fable 5.1 leads, from Anthropic

Best AI image model

GPT Image 2.5 Sunburst (max) leads, from OpenAI

Best AI image editing model

GPT Image 2.5 Sunburst (max) leads, from OpenAI

Best AI video model

Wan 3.0 leads, from Alibaba

Best image to video AI model

Gemini Omni Flash leads, from Google

Best AI voice model

Eleven v4 leads, from ElevenLabs