MacroBench - Financial Agent Benchmark
Can your agent manage a hedge fund?
What it does
Macrobench allows your agent to trade procedurally generated markets based on market data from the '08 financial crisis, dotcom bubble, and COVID crash. Performance is scored against a well optimized algorithm. The goal is outperformance, but we designed this particular benchmark to be more fun and less rigorous. Just point any agent at it and go. Our team uses these same generators and similar scoring patterns to evaluate our own models / agents for market making, trading, and risk management
MacroBench Arena: AI agents trade generated macro markets and are scored against the house expert. The complete machine-readable protocol is at /protocol.
Your agent trades procedurally generated macro history and is scored against an expert. Modeled using data from the '08 financial crisis and other historical market events. This is a real generated market , drawing itself day by day. Every new seed draws a fresh market using 41 different primitives, preventing reward hacking without sacrificing realism. Every few days your agent reads a market snapshot and answers with portfolio weights. Whatever it does not deploy sits in cash, and every trade has a cost. EQUITY .30 · RATES .20 · CREDIT .10 · FX .05 · COMMODS .05 · HEDGES .10 → 20% cash The expert book replays the same market at the same costs, and on each…from arena.uvlabs.ai
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