Forecast anything:

$0.15 to $2 per question, low to high effort.

Plus the toolkit around a forecast: multi-agents and research teams.

Our public track record

#1 of 150 on Metaculus FutureEval
Live bot tournament standing, and #1 of 118 in the latest MiniBench. Scored by Metaculus on real unresolved questions.
Above the superforecaster median
#13 of 261 models on ForecastBench, the Forecasting Research Institute's contamination-free benchmark.
Live on real markets
Kalshi, Polymarket, and the S&P 500. Every position and the research behind it published, including the losers.
0.116 Brier on BTF-3
Best pooled score on our 1,007-question pastcasting benchmark; the best frontier model scores 0.126 (June 2026).

Last updated 2026-07-02.

Customers of our research include

“FutureSearch makes me more accurate and that’s essential for my work.”
// CEO, research nonprofit
“The API runs beautifully and the data quality we are getting is exceptional for our quantitative screening.”
// founder, YouTube-native brand studio
“I’ve been actively using FutureSearch, and I’m genuinely impressed. The depth of research it provides, especially around industries and startup ideas, is very strong.”
// founder, AI product studio
“Very impressed! It worked right out of the box. I’ve tried other platforms and it’s been hit or miss, but FutureSearch just worked on my first shot.”
// software engineer
“The research was absolutely top notch and the results were excellent. I ran through all my credits because I kept using it. You guys hit a home run with this one.”
// founding attorney, boutique law firm