AI benchmark tape
Benchmark Live AI capital allocation same brief, frozen portfolios, real returns AI Positioning Risk-seeking 71.5/100 As of August 15, 2026. Broad risk seeking Model Agreement Mixed 5.8 point dispersion Insight Models missed the monthly oracle asset The hindsight best asset was Metals and Mining (XME) at +13.51%. 0 of 8 models held it, with +0.00% average allocation. Crowded Position S&P 500 20.1% 8 models hold SPY Biggest Shift South Africa Equities up 25.0 pp vs prior weekly round Open Portfolio Leader Claude Fable 5 currently leads at 3.5% interim result, not yet scored Latest Weekly Grok 4.5 led 2.9% vs S&P 0.4% Full Weekly History Claude Opus 5 leads score 9.8 across 8/46
Data Prices Aug 14 104/104 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 17 17 waiting for results
Open weekly rounds 4 4 waiting for results
Frozen live portfolios 165 41 assets currently held
Current risk appetite 71.5/100 As of August 15, 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 rounds12 of 21
Latest closeAug 14
Next final scoreAug 17
Claude Fable 5Anthropic / 12 open
Portfolio+3.46%S&P 500+4.05%Portfolio Minus S&P 500-0.60%
GPT-5.6 SolOpenAI / 12 open
Portfolio+3.44%S&P 500+4.05%Portfolio Minus S&P 500-0.61%
Claude Opus 4.7Anthropic / 1 open
Portfolio+3.39%S&P 500+4.45%Portfolio Minus S&P 500-1.06%
Gemini 3.1 ProGoogle / 12 open
Portfolio+3.11%S&P 500+4.05%Portfolio Minus S&P 500-0.94%
Claude Opus 4.8Anthropic / 12 open
Portfolio+3.06%S&P 500+4.05%Portfolio Minus S&P 500-0.99%
Grok 4.3xAI / 12 open
Portfolio+2.89%S&P 500+4.05%Portfolio Minus S&P 500-1.16%
Grok 4.5xAI / 12 open
Portfolio+2.83%S&P 500+4.05%Portfolio Minus S&P 500-1.22%
GPT-5.5OpenAI / 12 open
Portfolio+2.66%S&P 500+4.05%Portfolio Minus S&P 500-1.39%
Claude Opus 5Anthropic / 8 open
Portfolio+2.59%S&P 500+3.93%Portfolio Minus S&P 500-1.34%
S&P 50012 open tests
S&P 500 return+4.05%CloseAug 14

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.

20.1% points to S&P 500 (SPY), while US Equity accounts for 72.8% of open portfolios.

Largest assetS&P 500 (SPY)20.1%
Lead categoryUS Equity72.8%
Live rounds21All Open
Portfolios16541 assets held
Category mixClick a category to focus the pick list
Top allocationsAssets with the largest live model allocation
41 assets
31 smaller live allocations24.5%
Monthly model portfolios

CB-2026-08-15-1M

2026-08-17 to 2026-09-17

Waiting for result
Anthropic Claude Fable 5
US Small-Cap Value (IWN) 35% Utilities Sector (XLU) 35% Real Estate Sector (XLRE) 30%
Anthropic Claude Opus 4.8
S&P 500 (SPY) 100%
Anthropic Claude Opus 5
US Small-Cap Stocks (IWM) 35% US Small-Cap Value (IWN) 35% S&P 500 (SPY) 30%
Google Gemini 3.1 Pro
Japanese Yen (FXY) 35% Long-Term US Treasury Bonds (TLT) 35% US Small-Cap Value (IWN) 30%
OpenAI GPT-5.6 Sol
US Small-Cap Value (IWN) 35% Real Estate Sector (XLRE) 35% Utilities Sector (XLU) 30%
xAI Grok 4.3
S&P 500 (SPY) 100%
xAI Grok 4.5
S&P 500 (SPY) 100%
xAI Grok 4.6
S&P 500 (SPY) 100%
Shared top pick S&P 500 (SPY) Average across 8 frozen model portfolios.
Top 3 78.8% Spread 3.0 assets
S&P 500 (SPY) 53.8%
US Small-Cap Value (IWN) 16.9%
Real Estate Sector (XLRE) 8.1%
Utilities Sector (XLU) 8.1%
Monthly Scores Audit packet
Weekly model portfolios

CB-2026-08-15-1W

2026-08-17 to 2026-08-24

Waiting for result
Anthropic Claude Fable 5
South Africa Equities (EZA) 35% China Equities (MCHI) 35% Mexico Equities (EWW) 30%
Anthropic Claude Opus 4.8
S&P 500 (SPY) 100%
Anthropic Claude Opus 5
Australia Equities (EWA) 35% Mexico Equities (EWW) 35% South Africa Equities (EZA) 30%
Google Gemini 3.1 Pro
South Africa Equities (EZA) 35% Australia Equities (EWA) 35% S&P 500 (SPY) 30%
OpenAI GPT-5.6 Sol
Australia Equities (EWA) 35% South Africa Equities (EZA) 35% China Equities (MCHI) 30%
xAI Grok 4.3
Australia Equities (EWA) 35% United Kingdom Equities (EWU) 35% South Africa Equities (EZA) 30%
xAI Grok 4.5
South Africa Equities (EZA) 35% China Equities (MCHI) 35% Australia Equities (EWA) 30%
xAI Grok 4.6
S&P 500 (SPY) 100%
Shared top pick S&P 500 (SPY) Average across 8 frozen model portfolios.
Top 3 75% Spread 4.7 assets
S&P 500 (SPY) 28.8%
South Africa Equities (EZA) 25%
Australia Equities (EWA) 21.3%
China Equities (MCHI) 12.5%
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 71.5/100 As of August 15, 2026 / Risk-seeking
As of August 15, 2026 Broad risk seeking CB-2026-08-15-1M and CB-2026-08-15-1W
Monthly strategic 66.0/100 As of August 15, 2026 / Risk-seeking
Weekly tactical 77.0/100 As of August 15, 2026 / Risk-seeking
Change +10.5 Change vs Aug 13 portfolios
Model agreement Mixed 5.8 point dispersion
Largest current allocations
S&P 500 (SPY) 41.3% South Africa Equities (EZA) 12.5% Australia Equities (EWA) 10.6% US Small-Cap Value (IWN) 8.4% China Equities (MCHI) 6.3% Mexico Equities (EWW) 4.1%
Regime mix
Broad and cyclical equity 55.9% International equity 35.6% Defensive equity 4.1% Cash and defensive FX 2.2% Rates and credit 2.2%
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 4.8 Anthropic Top live holding S&P 500 (SPY) 39.5% across 21 open portfolios Top 3 70.2% Next score Aug 17 Grok 4.3 xAI Top live holding S&P 500 (SPY) 41.4% across 21 open portfolios Top 3 61.7% Next score Aug 17 Gemini 3.1 Pro Google Top live holding Healthcare Sector (XLV) 23.6% across 21 open portfolios Top 3 50.7% Next score Aug 17 Grok 4.5 xAI Top live holding Energy Sector (XLE) 16.9% across 21 open portfolios Top 3 45.5% Next score Aug 17 Claude Fable 5 Anthropic Top live holding S&P 500 (SPY) 14.5% across 21 open portfolios Top 3 37.1% Next score Aug 17 GPT-5.6 Sol OpenAI Top live holding Healthcare Sector (XLV) 10.7% across 21 open portfolios Top 3 31.0% Next score Aug 17 Claude Opus 5 Anthropic Top live holding S&P 500 (SPY) 27.6% across 17 open portfolios Top 3 52.6% Next score Aug 17 GPT-5.5 OpenAI Top live holding Healthcare Sector (XLV) 12.4% across 17 open portfolios Top 3 33.8% Next score Aug 17 Grok 4.6 xAI Top live holding S&P 500 (SPY) 50.0% across 4 open portfolios Top 3 76.3% Next score Aug 20 Claude Opus 4.7 Anthropic Top live holding S&P 500 (SPY) 40.0% across 1 open portfolios Top 3 85.0% Next score Aug 17
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 8 Eligible assets 70 Risk-taking score 66.0/100 Top consensus S&P 500 (SPY) 53.8% 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 8 Eligible assets 70 Risk-taking score 77.0/100 Top consensus S&P 500 (SPY) 28.8% 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.

104 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.