AI assistants that list OpenAI or GPT models
Which AI assistants use OpenAI's GPT models behind the scenes?
7 assistants ranked
Seven assistants in our catalog name OpenAI or a GPT model in their model line: Airtap, Buoy, Dots, Friday, Neo, Ollie and The Shadow. All seven took at least four of our ten tests and are ranked by their average: Neo 8.1 over ten, Dots 8.0 over seven, Ollie 7.8 over eight, Airtap 6.5 over four, Buoy 6.3 over eight, Friday 5.8 over six and The Shadow 5.3 over seven. Only Dots (a GPT model) and The Shadow (OpenAI) name nothing else.
Top picks
- 18.1NeoTop pick
Tested on 10 of 10Best: Travel9, Phone calls9
- 28.0DotsFastest that's still good
Tested on 7 of 10Best: Email10, Online tasks9Time to finish 6m 51s
- 37.8OllieBest free option
Tested on 8 of 10Best: Online tasks9, Routines9
- 46.5
Tested on 4 of 10Best: Routines8, Travel7
- 56.3
Tested on 8 of 10Best: Purchasing8, Online tasks7
Top pick: highest average here. Best free option: highest among assistants you can use for free. Fastest that's still good: quickest median time to finish among those averaging 7 or more.
Full ranking
| # | Assistant | Online tasks | Travel | Purchasing | Phone calls | Proactive | Routines | Connected apps | Permissions | Memory | Average | |
|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 1 | Neo | 7 | 9 | 8 | 9 | 6 | 9 | 8 | 9 | 8 | 8 | 8.1 |
| 2 | Dots | 9 | 6 | 7 | N/A | 10 | 9 | — | — | 7 | 8 | 8.0 |
| 3 | Ollie | 9 | 7 | 7 | N/A | 7 | 8 | 9 | 7 | 8 | — | 7.8 |
| 4 | Airtap | — | 7 | — | — | — | 6 | 8 | 5 | — | — | 6.5 |
| 5 | Buoy | 7 | 6 | 8 | — | — | 4 | 7 | 6 | 7 | 5 | 6.3 |
| 6 | Friday | — | 5 | — | 5 | — | — | 6 | 7 | 6 | 6 | 5.8 |
| 7 | The Shadow | — | 6 | 8 | — | 4 | — | 4 | 6 | 5 | 4 | 5.3 |
How this report works
Included are assistants whose catalog model line (checked 2026-10-26) names OpenAI, Azure OpenAI or a GPT model. The model line comes from each product's own pages and does not tell you which model answers a given request. They are ranked by the average of the tests they took, with at least four taken. Dots has no Phone calls score because that test does not apply, so its average covers seven tests; its catalog entry lists OpenAI as the company and GPT-6 Astra as the model.
How to choose
- Do not assume the model decides the result. The two assistants that name only OpenAI or GPT, Dots and The Shadow, average 8.0 and 5.3, so the label says little about quality.
- Read the full model line. Neo says it routes Claude, GPT and Gemini through OpenRouter, Ollie lists Anthropic, Google and OpenAI, Friday lists Azure OpenAI next to Anthropic through Amazon Bedrock and Google Gemini, and Buoy names OpenAI among several providers without naming a model.
- Compare price and access. Dots lists $100 a month, Neo $49 a month with a free tier of 750 credits, and Ollie $25 a month with a free tier; Airtap, Buoy and The Shadow list no price, and Airtap describes itself as invite-only.
Which AI assistants use GPT?
Seven in our catalog list OpenAI or GPT: Airtap, Buoy, Dots, Friday, Neo, Ollie and The Shadow. Only Dots (GPT-6 Astra) and The Shadow (OpenAI) list nothing else.
Which of the seven scores best?
Neo averages 8.1 over ten tests, Dots 8.0 over seven and Ollie 7.8 over eight.
Is an assistant that uses GPT the same as ChatGPT?
Not from our data. We only record the model line a product lists. It does not say which model answers a given request or how the product is built around it.
What users say
From there Buoy searched X, found my linked GitHub page (which currently 404s as I privated it), and even decided to look at my HuggingFace profile somehow. I’ve never seen an AI agent so willing to be proactive.
Open sourceBuoy says passwords stay out of chat and logs. Its privacy notice lists passwords among data it may collect. Not proof of exposure.
Open sourceUse Ollie if you want a text-only assistant that quietly watches your inbox and calendar and pings you; use Ohai if you want an app-based shared household workspace the whole family uses together.
Open sourceFrequently asked questions
Which assistant is best for this?
Neo leads with an average of 8.1, ahead of Dots and Ollie.
Is there a good free option?
Neo is the highest-ranked assistant with a free plan, averaging 8.1.
How did you test these assistants?
Every assistant got the same published tests, word for word, scored from three checkpoints and the number of corrections it needed. Each test is on the Dimensions page.