AI benchmark tape
Benchmark Live AI capital allocation same brief, frozen portfolios, real returns AI Positioning Risk-seeking 77.6/100 As of October 28, 2026. Broad risk seeking Model Agreement Mixed 5.7 point dispersion Insight Models missed the monthly oracle asset The hindsight best asset was Ethereum ETF (ETHA) at +152.31%. 0 of 7 models held it, with +0.00% average allocation. Crowded Position S&P 500 36.2% 5 models hold SPY Biggest Shift S&P 500 down 56.7 pp vs prior weekly round Open Portfolio Leader Gemini 3.1 Pro currently leads at 0.7% interim result, not yet scored Latest Weekly Gemini 4 Argon led 0.1% vs S&P -0.6% Full Weekly History Gemini 4 Argon leads score 17.6 across 2/80
Data Prices Nov 3 164/164 audited
Live dashboard

Live Positions & Returns

Open CapitalBench rounds before final scoring. This page shows frozen model portfolios, current exposure, mark-to-market returns, and the score dates still waiting on final closing prices.

Open live positions See mark-to-market returns Review open tests
Open monthly rounds 6 6 waiting for results
Open weekly rounds 1 1 waiting for results
Frozen live portfolios 45 20 assets currently held
Current risk appetite 77.6/100 As of October 28, 2026 / Risk-seeking
Live tests

Mark-To-Market Portfolio Returns

Open rounds priced to the latest available close. These are interim portfolio returns, not official benchmark scores.

Official results
Live tests

Live Portfolio Returns

Live rounds marked to the latest available close. These are not final scores.

Priced live rounds7 of 7
Latest closeNov 3
Next final scoreNov 4
Gemini 3.1 ProGoogle / 3 open
Portfolio+0.68%S&P 500-3.11%Portfolio Minus S&P 500+3.79%
Grok 4.3xAI / 3 open
Portfolio-0.34%S&P 500-3.11%Portfolio Minus S&P 500+2.77%
Grok 4.6xAI / 7 open
Portfolio-0.98%S&P 500-2.33%Portfolio Minus S&P 500+1.35%
GPT-6 AstraOpenAI / 7 open
Portfolio-1.54%S&P 500-2.33%Portfolio Minus S&P 500+0.79%
Grok 4.5xAI / 7 open
Portfolio-1.62%S&P 500-2.33%Portfolio Minus S&P 500+0.71%
Claude Opus 5 5Anthropic / 7 open
Portfolio-2.06%S&P 500-2.33%Portfolio Minus S&P 500+0.27%
Claude Fable 5.1Anthropic / 7 open
Portfolio-3.24%S&P 500-2.33%Portfolio Minus S&P 500-0.91%
Gemini 4 ArgonGoogle / 4 open
Portfolio-4.37%S&P 500-1.74%Portfolio Minus S&P 500-2.63%
S&P 5007 open tests
S&P 500 return-2.33%CloseNov 3

Interim returns use live rounds only. Completed rounds move to official scored results.

Marked to market from saved entry prices. Official results wait for the scheduled ending close.
Live positions

Current Frozen Model Portfolios

Current asset and model exposure across unresolved monthly and weekly rounds, with each frozen portfolio shown below.

Model profiles
Scope
View
All Open portfolios only
Live AI positioning

S&P 500 (SPY) is the largest live allocation.

36.2% points to S&P 500 (SPY), while US Equity accounts for 66.7% of open portfolios.

Largest assetS&P 500 (SPY)36.2%
Lead categoryUS Equity66.7%
Live rounds7All Open
Portfolios4520 assets held
Category mixClick a category to focus the pick list
Top allocationsAssets with the largest live model allocation
20 assets
10 smaller live allocations13.6%
Monthly model portfolios

CB-2026-10-27-1M

2026-10-28 to 2026-11-30

Waiting for result
Anthropic Claude Fable 5.1
Taiwan Equities (EWT) 35% Semiconductors (SMH) 35% South Korea Equities (EWY) 30%
Anthropic Claude Opus 5 5
Taiwan Equities (EWT) 35% Semiconductors (SMH) 35% S&P 500 (SPY) 30%
Google Gemini 4 Argon
Taiwan Equities (EWT) 35% Technology Sector (XLK) 35% Semiconductors (SMH) 30%
OpenAI GPT-6 Astra
Taiwan Equities (EWT) 35% Semiconductors (SMH) 35% S&P 500 (SPY) 30%
xAI Grok 4.5
Semiconductors (SMH) 35% Taiwan Equities (EWT) 35% Technology Sector (XLK) 30%
xAI Grok 4.6
S&P 500 (SPY) 100%
Shared top pick Taiwan Equities (EWT) Average across 6 frozen model portfolios.
Top 3 84.2% Spread 4.0 assets
Taiwan Equities (EWT) 29.2%
Semiconductors (SMH) 28.3%
S&P 500 (SPY) 26.7%
Technology Sector (XLK) 10.8%
Monthly Scores Audit packet
Weekly model portfolios

CB-2026-10-27-1W

2026-10-28 to 2026-11-04

Waiting for result
Anthropic Claude Fable 5.1
Brazil Equities (EWZ) 35% Communication Services Sector (XLC) 35% S&P 500 (SPY) 30%
Anthropic Claude Opus 5 5
Consumer Staples Sector (XLP) 35% S&P 500 (SPY) 65%
Google Gemini 4 Argon
Consumer Discretionary Sector (XLY) 35% Consumer Staples Sector (XLP) 35% US Large-Cap Value (IWD) 30%
OpenAI GPT-6 Astra
Consumer Staples Sector (XLP) 35% S&P 500 (SPY) 65%
xAI Grok 4.5
Brazil Equities (EWZ) 35% Communication Services Sector (XLC) 35% Consumer Staples Sector (XLP) 30%
xAI Grok 4.6
Brazil Equities (EWZ) 35% Communication Services Sector (XLC) 35% Consumer Staples Sector (XLP) 30%
Shared top pick Consumer Staples Sector (XLP) Average across 6 frozen model portfolios.
Top 3 71.7% Spread 4.7 assets
Consumer Staples Sector (XLP) 27.5%
S&P 500 (SPY) 26.7%
Brazil Equities (EWZ) 17.5%
Communication Services Sector (XLC) 17.5%
Weekly Scores Audit packet
Current allocation signal

AI Risk Appetite

Latest monthly and weekly portfolios, equal-weighted by track. This measures current model positioning, not market returns or a trading recommendation.

Historical trend and methodology
Current risk appetite 77.6/100 As of October 28, 2026 / Risk-seeking
As of October 28, 2026 Broad risk seeking CB-2026-10-27-1M and CB-2026-10-27-1W
Monthly strategic 86.6/100 As of October 28, 2026 / Aggressive
Weekly tactical 68.6/100 As of October 28, 2026 / Risk-seeking
Change +0.3 Change vs Oct 22 portfolios
Model agreement Mixed 5.7 point dispersion
Largest current allocations
S&P 500 (SPY) 26.7% Taiwan Equities (EWT) 14.6% Semiconductors (SMH) 14.2% Consumer Staples Sector (XLP) 13.8% Brazil Equities (EWZ) 8.8% Communication Services Sector (XLC) 8.8%
Regime mix
Broad and cyclical equity 32.1% Growth and technology 28.3% International equity 25.8% Defensive equity 13.8%
Model live holdings

Open Portfolios By Model

A compact readout of each model's unresolved CapitalBench exposure. Open the model profile for the full holdings breakdown.

Claude Opus 5 5 Anthropic Top live holding S&P 500 (SPY) 75.0% across 7 open portfolios Top 3 90.0% Next score Nov 4 GPT-6 Astra OpenAI Top live holding S&P 500 (SPY) 60.0% across 7 open portfolios Top 3 80.0% Next score Nov 4 Grok 4.6 xAI Top live holding S&P 500 (SPY) 56.4% across 7 open portfolios Top 3 75.7% Next score Nov 4 Claude Fable 5.1 Anthropic Top live holding S&P 500 (SPY) 27.1% across 7 open portfolios Top 3 56.4% Next score Nov 4 Grok 4.5 xAI Top live holding Taiwan Equities (EWT) 14.3% across 7 open portfolios Top 3 34.3% Next score Nov 4 Gemini 4 Argon Google Top live holding Taiwan Equities (EWT) 25.0% across 4 open portfolios Top 3 58.8% Next score Nov 4 Grok 4.3 xAI Top live holding S&P 500 (SPY) 33.3% across 3 open portfolios Top 3 76.7% Next score Nov 6 Gemini 3.1 Pro Google Top live holding Financials Sector (XLF) 23.3% across 3 open portfolios Top 3 55.0% Next score Nov 6
Open tests

Live Monthly And Weekly Tests

These are the open tests you can inspect now. Models already submitted portfolios; official scores wait for final closing prices.

Monthly test

One-month test

Live now

Longer test of AI allocation over one month.

Portfolios locked; scoring pending.

Model portfolios 6 Eligible assets 70 Risk-taking score 86.6/100 Top consensus Taiwan Equities (EWT) 29.2% average weight
Live positions Asset universe Audit packet
Weekly test

One-week test

Live now

Short-term test of AI positioning over one market week.

Portfolios locked; scoring pending.

Model portfolios 6 Eligible assets 70 Risk-taking score 68.6/100 Top consensus Consumer Staples Sector (XLP) 27.5% average weight
Live positions Asset universe Audit packet

Internal IDs and full reproducibility files are inside each audit packet.

Scoring calendar

Current Scoring Calendar

Models have already picked portfolios. Official scores publish only after the market window ends and final closing prices are available.

164 official rounds recorded Internal round and run IDs stay in the public audit trail.
View audit trail
Live data is interim.

Positions are frozen model outputs from open rounds. Returns are marked to the latest available close. Official benchmark scores publish only after the scheduled ending close is collected.