TreasuryBench
A public benchmark for AI financial advice
What it does
We tested Treasury, Origin, and Monarch on the same real personal-finance questions, scored by an independent AI judge. Treasury scored 89 to Origin’s 71 and Monarch’s 52 — winning all 12 categories with zero dangerous answers. The methodology, scoring code, and raw results are open source.
TreasuryBench compares Treasury, Origin, and Monarch on the same personal-finance questions and connected-account data. Review scores across 12 categories, response time, safety flags, methodology, and raw results.
We tested Treasury, Origin, and Monarch on realistic money questions with comparable financial context. Treasury scored highest overall and in every category. Treasury scored 89/100, compared with 71 for Origin and 52 for Monarch. It received the highest score in all 12 evaluated financial domains. Treasury scored 89 with a median response time of 11.6 seconds. Origin scored 71 at 46 seconds; Monarch scored 52 at 101 seconds. Treasury is the only app in the higher-score, faster-response quadrant. Selected domains show how the overall result maps to specific financial tasks. Evaluated merchant, category, and trend analysis, including whether the underlying numbers were correct. Evaluated…from treasury.sh
Does the same job
all alternatives →
More ai this month
the category →
I trained a 125M-parameter transformer to autocomplete piano performances in real time (~108 notes/sec on an iPhone 15). The idea is basically GitHub Copilot or Tabnine, except instead of prompting it with code, you prompt it by playing a few notes on a MIDI piano. The model then continues what you played, entirely on-device. The app is free if anyone wants to try it. Happy to answer questions about the model, training, Core ML, or the many things that didn't work.
AI · 17d ago · simedw.com
Astute▲585Automate your B2B brand going viral, with new media creators
AI · 18d ago · company-app.joinastute.com
Hey HN, Henry from Cactus here! We previously released Cactus Needle, a 14MB agentic LLM for tool call, device use, and structured extraction for phones, wearables, smart homes, small robots and microcontrollers. We got really great feedback here, and have now incorporated the suggestions to release Needle 2. The whole model is a single 14MB binary that runs a full session in 28MB of RAM; 45m parameters at 2bit compression. Needle hits 500 tokens/sec decode speed on a Raspberry Pi 5, sits between 400-1,500 tokens/sec on VR devices like Meta Quest 3S and Apple Vision Pro, and ranges…
AI · 26d ago · cactuscompute.com
Launched alongside, August 2026
the whole month →- TL
Life & fun · 10d ago · louisabraham.github.io
- SA
Hello HN! I found that picking out plausible but diverse skin tones for my digital art and game development projects was kind of difficult, and I got curious about if there was a way to define a color space that made it easy. I've built a color picker and procedural generation algorithm based on the space as well as a bunch of other fun js features and demos throughout the page that use the equations. If you find it interesting, I have lots of explanations of how I built it and what properties the space has. The methodology might be a bit shaky, but hopefully the result is as helpful for…
Life & fun · Aug 2026 · toneyalexander.github.io
I trained a 125M-parameter transformer to autocomplete piano performances in real time (~108 notes/sec on an iPhone 15). The idea is basically GitHub Copilot or Tabnine, except instead of prompting it with code, you prompt it by playing a few notes on a MIDI piano. The model then continues what you played, entirely on-device. The app is free if anyone wants to try it. Happy to answer questions about the model, training, Core ML, or the many things that didn't work.
AI · 17d ago · simedw.com