Live portfolios 15 15 open rounds
Completed rounds 31 scored rounds
Beat S&P 500 35.5% all completed tracks
Portfolio Minus S&P 500 +0.12 pp completed average
Portfolio pattern

How Does This Model Tend To Invest?

Calculated from eligible official saved portfolios using same-round peer comparisons. How labels and pills are determined

Saved portfolios 46
Average holdings 2.2
Average largest position 62.3%
Most common top holding S&P 500 (SPY)
Typical approach Peer-balanced allocator

No exposure or risk dimension is persistently far from same-round peer norms. Portfolios averaged 2.2 holdings, a 62.3% largest position, and 54.5% turnover.

Moderate evidence · based on 46 saved portfolios.
Near peer mix2.2 holdings · 62% top55% turnoverNow: SPY 48%
Risk taking 71.0 / 100 0 defensive to 100 aggressive
Typical largest position 62.3% average top holding
Typical holdings 2.2 average non-zero positions
Portfolio turnover 54.5% average change between rounds
Portfolio Difference / Combined

How different is this portfolio from the group?

A score of 59.1 means about 59.1% of allocation would need to change to match the average portfolio selected by the other models.

Compare every model
59.1 / 100
0 same as group to 100 completely different
monthly 66.5 22 same-round comparisons
weekly 51.8 22 same-round comparisons
Recent-winner tilt · Combined

Does this model follow recent winners?

Leans toward recent laggards. Combined gives monthly and weekly behavior equal weight. The score uses only prices available before each portfolio was frozen.

27.3 / 100
+7.3 points vs peers
monthly 31.8 0.00% in the top 20%
weekly 22.8 0.00% in the top 20%
Structured decision process

How the model builds its shortlist

Candidate-ledger evidence is available for 2 of 46 eligible portfolios. It is shown as context and does not determine the allocation-style label.

Avg candidates7.5 SPY included100.0% Forecast spread5.1% Stated confidence53.6%
Coverage — forecasts 2/46 · confidence 46/46 · key risks 46/46
Overall risk appetite

Growth

Usually favors equities, sectors, or thematic growth exposure.

3.47 / 5 allocation-weighted score
Grok 4.63.47
40.2% high-risk exposure 15.3% technology exposure 5.5% defensive holdings
Most frequently held assets
S&P 500 (SPY)US Broad Market 56.5% held 46.6% avg
Cybersecurity (CIBR)AI and Technology 30.4% held 10.3% avg
Aerospace and Defense (ITA)US Industry 23.9% held 8.2% avg
Healthcare Sector (XLV)US Sector 10.9% held 3.5% avg
US Small-Cap Value (IWN)US Style Factor 8.7% held 3.0% avg
Software (IGV)AI and Technology 8.7% held 2.9% avg
Industrials Sector (XLI)US Sector 8.7% held 2.7% avg
Average allocation by category
US Broad Market46.6%
US Sector14.0%
AI and Technology13.9%
US Industry9.6%
Commodities4.7%
US Style Factor3.0%
International Equity3.0%
Current portfolios

What Is This Model Holding Now?

15 open portfolios across weekly and monthly tests. Completed rounds are excluded.

Weekly1 open portfolio
1 assets
Completed rounds are excluded from this live view.Next scoring target: 2026-09-28
Still in progress

How Are Its Open Portfolios Doing?

Latest available close for live rounds only. These values are interim and move to official results after the ending close.

Weekly live
Portfolio
-0.28%
S&P 500
-0.28%
Portfolio Minus S&P 500
0.00 pp
1 open test
Monthly live
Portfolio
-0.29%
S&P 500
+0.69%
Portfolio Minus S&P 500
-0.98 pp
14 open tests
See all 15 open round returns
CB-2026-09-21-1M monthly / close 2026-09-25 Portfolio -0.89% S&P 500 -0.28% Portfolio Minus S&P 500 -0.61 pp CB-2026-09-16-1M monthly / close 2026-09-25 Portfolio -0.24% S&P 500 +1.15% Portfolio Minus S&P 500 -1.39 pp CB-2026-09-15-1M monthly / close 2026-09-25 Portfolio -0.78% S&P 500 +1.84% Portfolio Minus S&P 500 -2.63 pp CB-2026-09-13-1M monthly / close 2026-09-25 Portfolio +1.38% S&P 500 +1.38% Portfolio Minus S&P 500 0.00 pp CB-2026-09-11-1M monthly / close 2026-09-25 Portfolio +0.92% S&P 500 +0.92% Portfolio Minus S&P 500 0.00 pp CB-2026-09-10-1M monthly / close 2026-09-25 Portfolio +1.78% S&P 500 +1.78% Portfolio Minus S&P 500 -0.00 pp CB-2026-09-09-1M monthly / close 2026-09-25 Portfolio +0.99% S&P 500 +1.17% Portfolio Minus S&P 500 -0.18 pp CB-2026-09-04-1M monthly / close 2026-09-25 Portfolio -0.31% S&P 500 +0.15% Portfolio Minus S&P 500 -0.46 pp CB-2026-09-03-1M monthly / close 2026-09-25 Portfolio +0.57% S&P 500 +0.15% Portfolio Minus S&P 500 +0.42 pp CB-2026-09-02-1M monthly / close 2026-09-25 Portfolio -3.89% S&P 500 -0.24% Portfolio Minus S&P 500 -3.66 pp CB-2026-09-01-1M monthly / close 2026-09-25 Portfolio +0.81% S&P 500 +0.81% Portfolio Minus S&P 500 0.00 pp CB-2026-08-30-1M monthly / close 2026-09-25 Portfolio +0.56% S&P 500 +0.56% Portfolio Minus S&P 500 0.00 pp CB-2026-09-21-1W weekly / close 2026-09-25 Portfolio -0.28% S&P 500 -0.28% Portfolio Minus S&P 500 0.00 pp CB-2026-08-27-1M monthly / close 2026-09-25 Portfolio +0.26% S&P 500 +0.26% Portfolio Minus S&P 500 0.00 pp CB-2026-08-26-1M monthly / close 2026-09-25 Portfolio -5.15% S&P 500 +0.03% Portfolio Minus S&P 500 -5.18 pp
Completed results

How Has This Model Performed?

Weekly and monthly results stay separate because the holding periods are different.

Weekly record

2 wins / 22 completed

Avg return +0.37%
S&P 500 -0.16%
Avg Portfolio Minus S&P 500 +0.53 pp
Hit rate 45.5%
Avg rank 4.5
Best round CB-2026-09-09-1W
Monthly record

0 wins / 9 completed

Avg return -0.99%
S&P 500 -0.10%
Avg Portfolio Minus S&P 500 -0.89 pp
Hit rate 11.1%
Avg rank 4.6
Best round CB-2026-08-13-1M
Round by round

When Did It Beat The S&P 500?

Bars to the right beat the S&P 500. Bars to the left trailed it.

Ranking context

Where Does It Rank Against Comparable Models?

Each group uses only rounds completed by every included model.

See every comparison group 8
Weekly · Current

Sep 4, 2026 roster

Weekly comparison set automatically opened when the Sep 4 official roster first required a new equal-run benchmark group across 7 models.

Open full set
#2 Rank in set 17.9 CapitalBench Score 12.2% Total return 7 Shared rounds

Current Weekly Benchmark

CapitalBench Score

A score of 30 means the model earned 30% of the best possible return across these rounds. Calculation

Grok 4.5
Grok 4.6 This model
Gemini 3.1 Pro
Claude Opus 5
Claude Fable 5.1
GPT-6 Astra
Grok 4.3
S&P 500
Max possible What is this? Max possible is the best eligible asset after scoring for the same rounds. It is a hindsight ceiling, not a model portfolio. hindsight best asset

A score of 30 means the model earned 30% of the best possible return across these rounds. Calculation

Grok 4.5 xAI · 7/7 scored rounds
20.6
Grok 4.6 xAI · 7/7 scored rounds
17.9
Gemini 3.1 Pro Google · 7/7 scored rounds
16.6
Claude Opus 5 Anthropic · 7/7 scored rounds
14.2
Claude Fable 5.1 Anthropic · 7/7 scored rounds
7.6
GPT-6 Astra OpenAI · 7/7 scored rounds
3.9
Grok 4.3 xAI · 7/7 scored rounds
-1.4
S&P 500 S&P 500 · 7/7 scored rounds
2.8
Max possible Hindsight ceiling, not a model portfolio
What is this? Max possible is the best eligible asset after scoring for the same rounds. It is a hindsight ceiling, not a model portfolio. 100.0
7 shared resolved rounds7 equal-run models rankedQualified at 6+ shared roundsNewest included round: CB-2026-09-16-1W
Return context

Average Return Details

Average portfolio return across the same finished rounds.

xAI Grok 4.5
2.02%
xAI Grok 4.6
1.75%
Google Gemini 3.1 Pro
1.62%
Anthropic Claude Opus 5
1.39%
Anthropic Claude Fable 5.1
0.75%
OpenAI GPT-6 Astra
0.38%
xAI Grok 4.3
-0.14%
S&P S&P 500
0.27%
MAX Max possible What is this? Max possible is the best eligible asset after scoring for the same rounds. It is a hindsight ceiling, not a model portfolio.
9.78%
Fairness rule: every ranked model completed every included round. A missed round is excluded from this set for everyone.
Model-specific findings

What Has CapitalBench Learned About Grok 4.6?

Findings tied directly to this model's decisions or completed results.

Model BehaviorAs of Sep 25
Model behavior profiles12 models

Model allocation styles are separating into clear behavior profiles

GPT-5.5 has the highest average risk-taking score at 79.7/100. Grok 4.6 has the largest average top holding at +62.28%. Claude Opus 4.8 has the lowest measured turnover at +43.35%.

Momentum exposure measures how much of the frozen portfolio went into assets that had already been recent winners before the model made its allocation.

High confidenceMath: deterministicData through Sep 25, 2026
Highest Average Risk Taking Score
79.7/100
Largest Average Top Holding
+62.3%
Lowest Average Turnover
+43.4%
Performance AttributionSep 16-Sep 24
Weekly resultCB-2026-09-16-1W7 models

Grok 4.6's result was driven by S&P 500

In the latest weekly result, S&P 500 contributed +0.60% to Grok 4.6's portfolio. No holding detracted from the portfolio in this one-holding attribution view.

Attribution multiplies each frozen holding's weight by its asset return to show what helped or hurt the model portfolio.

High confidenceMath: deterministicData through Sep 24, 2026
Largest Positive Contribution
+0.60%
Smallest Positive Contribution
+0.60%
Why it matters

Attribution turns a model score into an explanation of which holdings actually helped or hurt the frozen portfolio.

Model BehaviorSep 21-Sep 28
Weekly live roundCB-2026-09-21-1W7 models

Grok 4.6 has the strongest current weekly recent-winner tilt

Its score is 50.0 out of 100, with 0.0% in the top recent-return quintile. Gemini 3.1 Pro is lowest at 3.4.

Momentum exposure measures how much of the frozen portfolio went into assets that had already been recent winners before the model made its allocation.

High confidenceMath: deterministicData through Sep 21, 2026
Leader Recent Winner Tilt Score
50.0/100
Leader Top Recent Winner Quintile Allocation
0.00%
Leader Peer Delta
28.6
Why it matters

This compares how strongly current model portfolios favor assets that had already outperformed. It describes the allocation and does not infer why the model chose it.

Decision history

What Did It Choose In Each Round?

Open a row to see the full portfolio, rationale, and audit files.

Round Track Window Portfolio Result
CB-2026-09-21-1W official-v3-20260921-weekly weekly 2026-09-21 to 2026-09-28 SP500 100.0% Pending
Full portfolio
S&P 500 (SPY) 100.0%
Rationale

SPY is near a 52-week high with low 21-session vol while equal-weight and most assets lag; 10-year yield at 5.00% and flat industrial production favor a narrow, rate-sensitive week rather than a broad reversal or high-beta continuation.

CB-2026-09-21-1M official-v3-20260921-monthly monthly 2026-09-21 to 2026-10-21 SP500 65.0%BIOTECH 35.0% Pending
Full portfolio
S&P 500 (SPY) 65.0% Biotechnology (XBI) 35.0%
Rationale

SPY is near a 52-week high with a roughly flat week while equal-weight and most assets lagged, 10-year yields are at 5%, industrial production is unchanged, and leadership is concentrated in a few high-beta growth and crypto names versus cyclicals that sold off. One-month edge versus SPY is limited and mixed rather than a clean continuation or reversal regime.

CB-2026-09-16-1W official-v3-20260916-weekly weekly 2026-09-17 to 2026-09-24 SP500 100.0% 0.00 pp
Full portfolio
S&P 500 (SPY) 100.0%
Rationale

Hawkish unanimous 25bp hike with higher 2026 inflation and funds-rate medians, weak 5-session breadth (14.5% positive), and only 2.37% active-return dispersion favor the benchmark over high-beta shock names for a one-week window.

CB-2026-09-16-1M official-v3-20260916-monthly-clean monthly 2026-09-17 to 2026-10-19 SMALL_VALUE 35.0%INDUSTRIALS 35.0%AEROSPACE_DEFENSE 30.0% Pending
Full portfolio
US Small-Cap Value (IWN) 35.0% Industrials Sector (XLI) 35.0% Aerospace and Defense (ITA) 30.0%
Rationale

Hawkish unanimous 25bp hike with higher 2026 inflation and funds-rate medians, weak 5-session breadth (14.5% positive), and a modest SPY pullback create mixed one-month dynamics: quality pullbacks may mean-revert while high-beta growth, crypto, and solar remain rate- and vol-sensitive.

CB-2026-09-15-1W official-v3-20260915-weekly-clean weekly 2026-09-15 to 2026-09-22 TAIWAN 35.0%SOUTH_AFRICA 35.0%EMERGING_MARKETS 30.0% +1.73 pp
Full portfolio
Taiwan Equities (EWT) 35.0% South Africa Equities (EZA) 35.0% Emerging Markets (VWO) 30.0%
Rationale

SPY is only mildly negative with very low 5-session active-return dispersion and weak breadth, while an unknown FOMC outcome hits mid-window. Shock-lane Asia/tech and metals sold off hard versus a still-positive prior active trend, so the week is mixed: possible mean-reversion in quality pullbacks versus event-driven continuation risk in oil and crypto.

CB-2026-09-15-1M official-v3-20260915-monthly monthly 2026-09-15 to 2026-10-15 SMALL_VALUE 35.0%SMALL_CAP 35.0%INDUSTRIALS 30.0% Pending
Full portfolio
US Small-Cap Value (IWN) 35.0% US Small-Cap Stocks (IWM) 35.0% Industrials Sector (XLI) 30.0%
Rationale

SPY is modestly lower into FOMC with very few assets positive over 5 sessions, oil and crypto showing short continuation while semis/industrials/small-caps show shock or quality pullbacks; one-month edge is mixed and event-dominated rather than a clean trend.

CB-2026-09-13-1W official-v3-20260913-weekly weekly 2026-09-14 to 2026-09-21 SP500 100.0% 0.00 pp
Full portfolio
S&P 500 (SPY) 100.0%
Rationale

Five-session active-return dispersion is only 2.24% with just ~20% of assets positive, SPY is near a 52-week high, and the FOMC meeting plus inflation/sentiment prints dominate a one-week window. Oil shows independent continuation versus a slightly weaker equity tape; most shock-reversal names are high-vol pullbacks without in-window fundamental confirmation.

CB-2026-09-13-1M official-v3-20260913-monthly monthly 2026-09-14 to 2026-10-14 SP500 100.0% Pending
Full portfolio
S&P 500 (SPY) 100.0%
Rationale

Breadth is weak with only about one-fifth of assets positive over 5 and 21 sessions, SPY is modestly negative into an FOMC week, CPI is 3.4% with rising Michigan inflation expectations, and oil remains elevated. That mix favors mixed reversal-versus-continuation rather than a clean one-month trend.

CB-2026-09-11-1W official-v3-20260911-weekly weekly 2026-09-11 to 2026-09-18 HEALTHCARE 35.0%DIVIDEND 35.0%BIOTECH 30.0% +0.63 pp
Full portfolio
Healthcare Sector (XLV) 35.0% US Dividend Equities (SCHD) 35.0% Biotechnology (XBI) 30.0%
Rationale

SPY is modestly lower with weak equal-weight breadth while PPI and energy prices jumped and CPI/FOMC sit inside the week; quality sectors sold off versus prior relative strength while oil/commodities already ran to highs, so the week is mixed reversal-versus-continuation rather than a clean trend.

CB-2026-09-11-1M official-v3-20260911-monthly monthly 2026-09-11 to 2026-10-12 SP500 100.0% Pending
Full portfolio
S&P 500 (SPY) 100.0%
Rationale

Narrow equity weakness (SPY -0.96% 5s, RSP lagging, 21.7% positive share) coincides with a PPI goods/energy spike, ECB hike, 4.95% 10y, and a large oil continuation; breadth and rates argue against high-beta continuation while oil/crypto already stretched.

Audit and data Public Audit Packets For This Model