Live portfolios 24 24 open rounds
Completed rounds 29 scored rounds
Beat S&P 500 55.2% all completed tracks
Portfolio Minus S&P 500 -0.01 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 57
Average holdings 4.1
Average largest position 33.6%
Most common top holding Energy Sector (XLE)
Typical approach Group-aligned allocator

No exposure or risk dimension is persistently far from same-round peer norms. Portfolios averaged 4.1 holdings, a 33.6% largest position, and 57.8% turnover.

Moderate evidence · based on 57 saved portfolios.
Near peer mix4.1 holdings · 34% top58% turnoverNow: CIBR 10%
Risk taking 72.6 / 100 0 defensive to 100 aggressive
Typical largest position 33.6% average top holding
Typical holdings 4.1 average non-zero positions
Portfolio turnover 57.8% average change between rounds
Portfolio Difference / Combined

How different is this portfolio from the group?

A score of 46.2 means about 46.2% of allocation would need to change to match the average portfolio selected by the other models.

Compare every model
46.2 / 100
0 same as group to 100 completely different
monthly 57.5 6 same-round comparisons
weekly 34.9 6 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.

12.4 / 100
-4.4 points vs peers
monthly 21.2 0.00% in the top 20%
weekly 3.7 0.00% in the top 20%
Structured decision process

How the model builds its shortlist

Candidate-ledger evidence is available for 33 of 57 eligible portfolios. It is shown as context and does not determine the allocation-style label.

Avg candidates7.8 SPY included100.0% Forecast spread7.1% Stated confidence57.2%
Coverage — forecasts 33/57 · confidence 57/57 · key risks 57/57
Overall risk appetite

Growth

Usually favors equities, sectors, or thematic growth exposure.

4.03 / 5 allocation-weighted score
Grok 4.54.03
76.6% high-risk exposure 24.2% technology exposure 6.0% defensive holdings
Most frequently held assets
Energy Sector (XLE)US Sector 59.6% held 15.4% avg
Financials Sector (XLF)US Sector 40.4% held 8.3% avg
Crude Oil (USO)Commodities 29.8% held 8.2% avg
Healthcare Sector (XLV)US Sector 29.8% held 7.1% avg
Cybersecurity (CIBR)AI and Technology 22.8% held 5.7% avg
Semiconductors (SMH)AI and Technology 21.1% held 6.5% avg
Biotechnology (XBI)Healthcare And Biotech 19.3% held 4.3% avg
Average allocation by category
US Sector35.2%
AI and Technology17.3%
Commodities14.6%
US Broad Market8.2%
US Industry5.4%
US Style Factor4.6%
Healthcare And Biotech4.3%
Current portfolios

What Is This Model Holding Now?

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

Weekly6 open portfolios
11 assets
Completed rounds are excluded from this live view.Next scoring target: 2026-08-24
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
-0.21%
S&P 500
-0.93%
Portfolio Minus S&P 500
+0.72 pp
3 open tests
Monthly live
Portfolio
+1.44%
S&P 500
+0.55%
Portfolio Minus S&P 500
+0.89 pp
15 open tests
See all 18 open round returns
CB-2026-08-19-1M monthly / close 2026-08-20 Portfolio -0.63% S&P 500 -0.84% Portfolio Minus S&P 500 +0.21 pp CB-2026-08-18-1M monthly / close 2026-08-20 Portfolio -1.14% S&P 500 -0.63% Portfolio Minus S&P 500 -0.51 pp CB-2026-08-15-1M monthly / close 2026-08-20 Portfolio -1.30% S&P 500 -1.30% Portfolio Minus S&P 500 0.00 pp CB-2026-08-13-1M monthly / close 2026-08-20 Portfolio +0.60% S&P 500 -1.96% Portfolio Minus S&P 500 +2.57 pp CB-2026-08-11-1M monthly / close 2026-08-20 Portfolio +2.58% S&P 500 -1.03% Portfolio Minus S&P 500 +3.61 pp CB-2026-08-09-1M monthly / close 2026-08-20 Portfolio +0.12% S&P 500 -1.35% Portfolio Minus S&P 500 +1.47 pp CB-2026-08-07-1M monthly / close 2026-08-20 Portfolio -0.74% S&P 500 -1.38% Portfolio Minus S&P 500 +0.64 pp CB-2026-08-05-1M monthly / close 2026-08-20 Portfolio +1.56% S&P 500 -0.93% Portfolio Minus S&P 500 +2.49 pp CB-2026-08-04-1M monthly / close 2026-08-20 Portfolio +0.73% S&P 500 -1.13% Portfolio Minus S&P 500 +1.86 pp CB-2026-07-31-1M monthly / close 2026-08-20 Portfolio +4.61% S&P 500 +2.08% Portfolio Minus S&P 500 +2.53 pp CB-2026-07-30-1M monthly / close 2026-08-20 Portfolio +3.76% S&P 500 +2.82% Portfolio Minus S&P 500 +0.95 pp CB-2026-07-29-1M monthly / close 2026-08-20 Portfolio +4.04% S&P 500 +4.54% Portfolio Minus S&P 500 -0.50 pp CB-2026-07-28-1M monthly / close 2026-08-20 Portfolio -0.00% S&P 500 +2.93% Portfolio Minus S&P 500 -2.94 pp CB-2026-07-27-1M monthly / close 2026-08-20 Portfolio +3.55% S&P 500 +3.18% Portfolio Minus S&P 500 +0.37 pp CB-2026-08-19-1W weekly / close 2026-08-20 Portfolio -1.43% S&P 500 -0.84% Portfolio Minus S&P 500 -0.59 pp CB-2026-08-18-1W weekly / close 2026-08-20 Portfolio -0.86% S&P 500 -0.63% Portfolio Minus S&P 500 -0.22 pp CB-2026-08-15-1W weekly / close 2026-08-20 Portfolio +1.66% S&P 500 -1.30% Portfolio Minus S&P 500 +2.96 pp CB-2026-07-24-1M monthly / close 2026-08-20 Portfolio +3.82% S&P 500 +3.20% Portfolio Minus S&P 500 +0.61 pp
Completed results

How Has This Model Performed?

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

Weekly record

1 wins / 19 completed

Avg return +0.51%
S&P 500 +0.73%
Avg Portfolio Minus S&P 500 -0.22 pp
Hit rate 47.4%
Avg rank 4.2
Best round CB-2026-07-15-1W
Monthly record

1 wins / 10 completed

Avg return +3.53%
S&P 500 +3.14%
Avg Portfolio Minus S&P 500 +0.39 pp
Hit rate 70.0%
Avg rank 3.9
Best round CB-2026-07-22-1M
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 12
Weekly · Current

Jul 24, 2026 roster

Weekly comparison set automatically opened when the Jul 24 official roster first required a new equal-run benchmark group across 8 models.

Open full set
#2 Rank in set 10.8 CapitalBench Score 9.6% Total return 8 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 4.3
Grok 4.5 This model
Claude Opus 5
GPT-5.6 Sol
Claude Opus 4.8
Claude Fable 5
GPT-5.5
Gemini 3.1 Pro
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 4.3 xAI · 8/8 scored rounds
11.5
Grok 4.5 xAI · 8/8 scored rounds
10.8
Claude Opus 5 Anthropic · 8/8 scored rounds
9.8
GPT-5.6 Sol OpenAI · 8/8 scored rounds
8.8
Claude Opus 4.8 Anthropic · 8/8 scored rounds
7.2
Claude Fable 5 Anthropic · 8/8 scored rounds
6.2
GPT-5.5 OpenAI · 8/8 scored rounds
4.4
Gemini 3.1 Pro Google · 8/8 scored rounds
2.3
S&P 500 S&P 500 · 8/8 scored rounds
23.1
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
8 shared resolved rounds8 equal-run models rankedQualified at 6+ shared roundsNewest included round: CB-2026-08-05-1W
Return context

Average Return Details

Average portfolio return across the same finished rounds.

xAI Grok 4.3
1.29%
xAI Grok 4.5
1.20%
Anthropic Claude Opus 5
1.10%
OpenAI GPT-5.6 Sol
0.98%
Anthropic Claude Opus 4.8
0.80%
Anthropic Claude Fable 5
0.69%
OpenAI GPT-5.5
0.50%
Google Gemini 3.1 Pro
0.26%
S&P S&P 500
2.58%
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.
11.18%
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 4.5?

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

Portfolio DifferenceAs of Aug 24
50% monthly / 50% weekly7 models

Grok 4.6 invests most differently from the group

Claude Opus 5 is most like the group at 45.7/100. Monthly and weekly behavior receive equal weight.

Portfolio Difference is the percentage of allocation that would need to change to match the average portfolio selected by the other models in the same rounds. Different does not mean better.

Medium confidenceMath: deterministicData through Aug 24, 2026
Highest Portfolio Difference
60.2/100
Lowest Portfolio Difference
45.7/100
Model BehaviorAug 23-Sep 24
Monthly live roundCB-2026-08-23-1M7 models

Grok 4.6 has the strongest current monthly recent-winner tilt

Its score is 50.0 out of 100, with 0.0% in the top recent-return quintile. Grok 4.5 is lowest at 2.5.

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 Aug 23, 2026
Leader Recent Winner Tilt Score
50.0/100
Leader Top Recent Winner Quintile Allocation
0.00%
Leader Peer Delta
35.0
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.

Performance AttributionAug 5-Aug 12
Weekly resultCB-2026-08-05-1W8 models

Grok 4.5's result was driven by Energy Sector

In the latest weekly result, Energy Sector contributed +1.62% to Grok 4.5's portfolio. The largest drag came from Financials Sector at -0.02%.

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

High confidenceMath: deterministicData through Aug 12, 2026
Largest Positive Contribution
+1.62%
Largest Negative Contribution
-0.02%
Why it matters

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

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-2026-08-23-1W official-v3-20260823-weekly weekly 2026-08-24 to 2026-08-31 AEROSPACE_DEFENSE 35.0%CYBERSECURITY 35.0%REGIONAL_BANKS 30.0% Pending
Full portfolio
Aerospace and Defense (ITA) 35.0% Cybersecurity (CIBR) 35.0% Regional Banks (KRE) 30.0%
Rationale

SPY soft on the week amid sticky inflation prints, softer labor revisions, elevated long rates, and geopolitics supporting oil; Friday bounce and strong PMI contrast with crypto/precious-metal surges and selective equity pullbacks, yielding mixed continuation versus shock-reversal setups into NVDA and data releases.

CB-2026-08-23-1M official-v3-20260823-monthly monthly 2026-08-24 to 2026-09-24 SEMICONDUCTORS 35.0%UTILITIES 35.0%OIL 30.0% Pending
Full portfolio
Semiconductors (SMH) 35.0% Utilities Sector (XLU) 35.0% Crude Oil (USO) 30.0%
Rationale

SPY soft on the week amid sticky inflation, soft payrolls, and elevated long rates; oil/geopolitics and crypto/precious-metal spikes create cross-asset dispersion while quality pullbacks in semis and utilities offer selective mean-reversion setups into the one-month window.

CB-2026-08-21-1W official-v3-20260821-weekly weekly 2026-08-21 to 2026-08-28 CYBERSECURITY 35.0%AEROSPACE_DEFENSE 35.0%AUTONOMOUS_ROBOTICS 30.0% Pending
Full portfolio
Cybersecurity (CIBR) 35.0% Aerospace and Defense (ITA) 35.0% Autonomous Technology and Robotics (ARKQ) 30.0%
Rationale

SPY pulled back ~2% with VIX at 16 amid sticky inflation prints, rising yields near 4.7%, and soft retail/payroll data; quality tech/defense names show sharp relative pullbacks after strong priors while crypto extended hard on volume; NVIDIA print and PCE/GDP revisions dominate the one-week window, favoring selective mean-reversion over broad continuation.

CB-2026-08-21-1M official-v3-20260821-monthly monthly 2026-08-21 to 2026-09-21 SEMICONDUCTORS 35.0%MOMENTUM 35.0%SMALL_VALUE 30.0% Pending
Full portfolio
Semiconductors (SMH) 35.0% US Momentum Equities (MTUM) 35.0% US Small-Cap Value (IWN) 30.0%
Rationale

Recent equity pullback with elevated rates, sticky inflation signals, and oil strength creates mixed continuation/reversal setup; high cross-asset dispersion and quality pullbacks in semis/momentum favor selective mean-reversion over broad beta.

CB-2026-08-20-1W official-v3-20260820-weekly weekly 2026-08-20 to 2026-08-27 CYBERSECURITY 35.0%AEROSPACE_DEFENSE 35.0%JAPAN 30.0% Pending
Full portfolio
Cybersecurity (CIBR) 35.0% Aerospace and Defense (ITA) 35.0% Japan Equities (EWJ) 30.0%
Rationale

Equity indices modestly lower WTD with low VIX near 15.7, stable Fed funds after July hold, mixed inflation prints, and Asia equity shock; one-week window includes NVDA results and Jackson Hole start, favoring selective quality pullback reversals over crowded crypto continuation or high-beta semis.

CB-2026-08-20-1M official-v3-20260820-monthly monthly 2026-08-20 to 2026-09-21 SEMICONDUCTORS 35.0%SMALL_VALUE 35.0%CYBERSECURITY 30.0% Pending
Full portfolio
Semiconductors (SMH) 35.0% US Small-Cap Value (IWN) 35.0% Cybersecurity (CIBR) 30.0%
Rationale

SPY near flat on 5s after solid 21s; equal-weight outperforming; VIX mid-teens; sticky inflation and elevated long yields with Sept FOMC and Jackson Hole ahead; AI/semicap prior strength with recent pullbacks; commodity and factor dispersion mixed rather than one-way trend.

CB-2026-08-19-1W official-v3-20260819-weekly weekly 2026-08-19 to 2026-08-26 METALS_MINING 35.0%MATERIALS 35.0%CYBERSECURITY 30.0% Pending
Full portfolio
Metals and Mining (XME) 35.0% Materials Sector (XLB) 35.0% Cybersecurity (CIBR) 30.0%
Rationale

Low cross-sectional dispersion with soft recent equity tape, energy short-term strength, and quality pullbacks in materials/tech after prior relative strength; mixed macro (soft payrolls, sticky services prices, solid ISM) favors selective mean-reversion over broad continuation into the one-week window.

CB-2026-08-19-1M official-v3-20260819-monthly monthly 2026-08-19 to 2026-09-18 LONG_TREASURY 35.0%UTILITIES 35.0%INVESTMENT_GRADE_CREDIT 30.0% Pending
Full portfolio
Long-Term US Treasury Bonds (TLT) 35.0% Utilities Sector (XLU) 35.0% Investment Grade Corporate Bonds (LQD) 30.0%
Rationale

Soft July payrolls and downward revisions plus solid but moderating GDP sit against still-elevated inflation and a hold-biased FOMC; cross-section shows recent equity softness with rate-sensitive and EM laggards extended lower while oil and some quality factors are firmer, favoring selective reversal over broad continuation into the Sept FOMC window.

CB-2026-08-18-1W official-v3-20260818-weekly weekly 2026-08-18 to 2026-08-25 CHINA 35.0%SOFTWARE 35.0%CYBERSECURITY 30.0% Pending
Full portfolio
China Equities (MCHI) 35.0% Software (IGV) 35.0% Cybersecurity (CIBR) 30.0%
Rationale

SPY near flat on the week with low 5s dispersion; soft July payrolls and retail sales contrast with still-elevated ISM prices and sticky core inflation while Fed remains on hold. Quality pullbacks in prior-strong tech/EM names offer selective reversal setups against a low-vol benchmark near highs; extreme high-beta continuations carry mean-reversion risk over one week.

CB-2026-08-18-1M official-v3-20260818-monthly-clean monthly 2026-08-18 to 2026-09-18 REGIONAL_BANKS 35.0%LONG_TREASURY 35.0%FINANCIALS 30.0% Pending
Full portfolio
Regional Banks (KRE) 35.0% Long-Term US Treasury Bonds (TLT) 35.0% Financials Sector (XLF) 30.0%
Rationale

Soft July payrolls, sticky but cooling CPI/PCE mix, and held funds rate leave a one-month window of modest equity drift with selective mean-reversion in rate-sensitive and EM laggards; oil strength and high ISM prices keep cyclical/commodity dispersion elevated versus pure growth continuation.

Audit and data Public Audit Packets For This Model