Dachi-1.0
Tomo's first model of its own.
October 16, 2026
The Conversational Frontier
Frontier models are judged on exams and code. A personal agent is judged on whether you keep coming back to it. So we put Dachi-1.0 up against the frontier on what a conversation is made of.
- 01Do people text back?
- 02Do they keep talking?
- 03Does it answer in seconds, like a person?
- 04Can it afford to always be there?
Head to head
Texted back within 10 minutes
vs. GPT-6.1 Sol- Dachi-1.0+7%
- Claude Opus 5.5+1%
- GPT-6.1 SolBaseline
Messages per person
vs. GPT-6.1 Sol- Dachi-1.0+17%
- Claude Opus 5.5+4%
- GPT-6.1 SolBaseline
Time to first reply, median
Lower is better- Dachi-1.04.4s
- Claude Opus 5.57.4s
- GPT-6.1 Sol5.5s
Cost per 1,000 replies
Lower is better- Dachi-1.0$2.24
- Claude Opus 5.5$35.50
- GPT-6.1 Sol$17.75
Live randomized test on production usage, October 2026. Reply and message rates show the improvement over GPT-6.1 Sol. Cost at list token prices.
One text, three replies
Dachi-1.0 is tuned to be delightful to text. It reacts the way a person would, matches your energy and keeps the thread going. Frontier models fall back on the assistant script: a congratulations, a feelings check and an offer to help.
- 6:42Tomo
iMessage
Today 6:42 PMthey offered me the jobWAIT WHATthey offered it?? that's huge, you must be buzzing right nowok i need the whole story. are you taking it??Dachi-1.0In the Tomo harness - 6:42
Opus 5.5iMessage
Today 6:42 PMthey offered me the jobThat's big news! How are you feeling about it? Excited, nervous, still deciding?If you want to talk anything through, like the offer itself, negotiating, or whether to take it, I'm happy to help. Or if you just want to celebrate, congrats! 🎉Claude Opus 5.5Anthropic - 6:42
GPT-6.1 SoliMessage
Today 6:42 PMthey offered me the jobCongratulations! 🎉 How are you feeling about the offer—excited, unsure, or a bit of both?GPT-6.1 SolOpenAI