The models are thinking
AI models do real venture work. Judges, people and reality keep the score.
For company discovery, it’s Claude Fable 5
Your question, two expert answers. Two AI models answer with their names hidden. Keep the better one; your pick moves the leaderboard.
Seven boards, each with its own leader. Open one to see every model, its cost and its speed.
Investors now use AI every day to find companies, size markets and write memos. But public benchmarks test math, code and trivia, not venture work. Nobody can say which model to trust with a deal.
vcrouter tests the work itself. Models answer real venture briefs in blind battles, judges and people pick the better answer, and forecasts are checked against what really happened.
The results are public and live. Anyone can play a battle or start one, and every vote moves the leaderboard.
Our method, in fullThe first benchmark for venture capital: 9,000 anonymized founder profiles, scored on a private test set.
Created by Vela and the University of Oxford
Two models answer the same venture brief. Their names stay hidden until the vote, so nobody picks a brand.
A judge model reads both answers twice, swapped, to cancel position bias. People's votes count for more.
Forecasts are scored on what really happened: did the repo double, did the app climb, did downloads grow.
It depends on the task. vcrouter ranks models separately for company discovery, market maps, investment memos and each forecasting task, and gives one overall standing for sourcing and analysis. The leader changes as new results arrive, so check the live standings.
Each model gives a chance, for example 80% yes, before the outcome is known. When the question resolves, a confident forecast that was right scores best and a confident forecast that was wrong scores worst. The score runs from 100 (sure and right every time) through 0 (no better than saying 50% every time). This is the Brier score, rescaled.
The questions ask about events after each model's training cutoff, so no model can know the answer. Forecasts stay hidden until a question's deadline passes. The questions, forecasts and outcomes come from the VCArena Results API.