Skip to content
CapitalBench
Results Live Insights Manifesto Why Models API Positioning Rounds Methodology Method Audit GitHub Contribute
Results Insights Models Contribute
Menu Close
Results Live Insights Manifesto Models API Positioning Rounds Methodology Audit GitHub Contribute Weekly Results Monthly Results Comparison Sets Model Behavior Benchmarks Overall Weekly Overall Monthly
CapitalBench Live AI benchmark tape
Benchmark Live AI capital allocation same brief, frozen portfolios, real returns AI Positioning Risk-seeking 72.5/100 As of September 21, 2026. Broad risk seeking Model Agreement Tight 3.5 point dispersion Insight Models missed the monthly oracle asset The hindsight best asset was Crude Oil (USO) at +16.47%. 0 of 7 models held it, with +0.00% average allocation. Crowded Position S&P 500 23.9% 6 models hold SPY Biggest Shift Japan Equities up 20.0 pp vs prior weekly round Open Portfolio Leader Claude Fable 5.1 currently leads at 1.6% interim result, not yet scored Latest Weekly Grok 4.6 led 0.6% vs S&P 0.6% Full Weekly History Grok 4.5 leads score 6.2 across 44/71
Benchmark Live AI capital allocation same brief, frozen portfolios, real returns AI Positioning Risk-seeking 72.5/100 As of September 21, 2026. Broad risk seeking Model Agreement Tight 3.5 point dispersion Insight Models missed the monthly oracle asset The hindsight best asset was Crude Oil (USO) at +16.47%. 0 of 7 models held it, with +0.00% average allocation. Crowded Position S&P 500 23.9% 6 models hold SPY Biggest Shift Japan Equities up 20.0 pp vs prior weekly round Open Portfolio Leader Claude Fable 5.1 currently leads at 1.6% interim result, not yet scored Latest Weekly Grok 4.6 led 0.6% vs S&P 0.6% Full Weekly History Grok 4.5 leads score 6.2 across 44/71
Data Prices Sep 25 146/146 audited
  1. Home
  2. AI Portfolio Benchmark Results
  3. AI Model Consistency Results

Consistency rounds

Consistency Results By Horizon

These views show repeated-call consistency. They stay separate from the public one-portfolio benchmark results.

Weekly Consistency

Repeated-call checks for one-week rounds only.

Monthly Consistency

Repeated-call checks for one-month rounds only.

Score alerts

Get monthly and weekly score updates. Get score alerts

Occasional benchmark results, no spam.

Occasional CapitalBench emails. Unsubscribe anytime.

Email updates

Get CapitalBench updates

Occasional benchmark results and product updates. Unsubscribe anytime.

By subscribing, you agree to receive occasional CapitalBench emails.

CapitalBench

AI capital-allocation benchmark with frozen portfolios, public audit packets, and real market scoring.

Benchmark and research project, not financial advice. GitHub repository

Explore

Live dashboard Insights Models Model behavior benchmarks API

Results

Latest results Monthly results Weekly results Comparison sets Market Regime Benchmark Round audit packets

Method

Methodology Scoring Asset universe Fairness Limitations

Project

Manifesto Docs and audit Changelog Contribute Privacy