Live portfolios 24 24 open rounds
Completed rounds 51 scored rounds
Beat S&P 500 62.7% all completed tracks
Portfolio Minus S&P 500 +0.49 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 75
Average holdings 3.8
Average largest position 34.8%
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 3.8 holdings, a 34.8% largest position, and 57.3% turnover.

Moderate evidence · based on 75 saved portfolios.
Near peer mix3.8 holdings · 35% top57% turnoverNow: SPY 11%
Risk taking 72.9 / 100 0 defensive to 100 aggressive
Typical largest position 34.8% average top holding
Typical holdings 3.8 average non-zero positions
Portfolio turnover 57.3% average change between rounds
Portfolio Difference / Combined

How different is this portfolio from the group?

A score of 48.9 means about 48.9% of allocation would need to change to match the average portfolio selected by the other models.

Compare every model
48.9 / 100
0 same as group to 100 completely different
monthly 56.0 15 same-round comparisons
weekly 41.7 15 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.

10.9 / 100
-6.0 points vs peers
monthly 16.8 0.00% in the top 20%
weekly 5.0 0.00% in the top 20%
Structured decision process

How the model builds its shortlist

Candidate-ledger evidence is available for 33 of 75 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 confidence57.3%
Coverage — forecasts 33/75 · confidence 75/75 · key risks 75/75
Overall risk appetite

Growth

Usually favors equities, sectors, or thematic growth exposure.

4.03 / 5 allocation-weighted score
Grok 4.54.03
76.5% high-risk exposure 23.9% technology exposure 6.3% defensive holdings
Most frequently held assets
Energy Sector (XLE)US Sector 49.3% held 13.1% avg
Financials Sector (XLF)US Sector 32.0% held 6.8% avg
Cybersecurity (CIBR)AI and Technology 25.3% held 7.1% avg
Healthcare Sector (XLV)US Sector 25.3% held 6.3% avg
Crude Oil (USO)Commodities 22.7% held 6.3% avg
Semiconductors (SMH)AI and Technology 17.3% held 5.4% avg
Aerospace and Defense (ITA)US Industry 16.0% held 4.7% avg
Average allocation by category
US Sector33.2%
AI and Technology18.2%
Commodities15.4%
US Industry8.6%
US Broad Market7.6%
US Style Factor4.9%
Healthcare And Biotech3.7%
Current portfolios

What Is This Model Holding Now?

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

Weekly5 open portfolios
8 assets
Completed rounds are excluded from this live view.Next scoring target: 2026-09-08
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
-0.16%
S&P 500
+0.23%
Portfolio Minus S&P 500
-0.39 pp
3 open tests
Monthly live
Portfolio
+0.66%
S&P 500
+0.15%
Portfolio Minus S&P 500
+0.50 pp
17 open tests
See all 20 open round returns
CB-2026-09-02-1M monthly / close 2026-09-04 Portfolio -0.14% S&P 500 -0.39% Portfolio Minus S&P 500 +0.25 pp CB-2026-09-01-1M monthly / close 2026-09-04 Portfolio +0.87% S&P 500 +0.66% Portfolio Minus S&P 500 +0.21 pp CB-2026-08-30-1M monthly / close 2026-09-04 Portfolio +1.14% S&P 500 +0.41% Portfolio Minus S&P 500 +0.73 pp CB-2026-08-27-1M monthly / close 2026-09-04 Portfolio +0.11% S&P 500 +0.11% Portfolio Minus S&P 500 0.00 pp CB-2026-08-26-1M monthly / close 2026-09-04 Portfolio -0.08% S&P 500 -0.12% Portfolio Minus S&P 500 +0.04 pp CB-2026-08-25-1M monthly / close 2026-09-04 Portfolio -2.11% S&P 500 +0.54% Portfolio Minus S&P 500 -2.65 pp CB-2026-08-24-1M monthly / close 2026-09-04 Portfolio -0.59% S&P 500 +0.56% Portfolio Minus S&P 500 -1.15 pp CB-2026-08-23-1M monthly / close 2026-09-04 Portfolio +3.39% S&P 500 +0.88% Portfolio Minus S&P 500 +2.51 pp CB-2026-08-21-1M monthly / close 2026-09-04 Portfolio +0.35% S&P 500 +0.58% Portfolio Minus S&P 500 -0.23 pp CB-2026-08-20-1M monthly / close 2026-09-04 Portfolio +0.76% S&P 500 +1.00% Portfolio Minus S&P 500 -0.23 pp CB-2026-08-19-1M monthly / close 2026-09-04 Portfolio -1.40% S&P 500 +0.15% Portfolio Minus S&P 500 -1.54 pp CB-2026-08-18-1M monthly / close 2026-09-04 Portfolio -0.35% S&P 500 +0.36% Portfolio Minus S&P 500 -0.71 pp CB-2026-08-15-1M monthly / close 2026-09-04 Portfolio -0.32% S&P 500 -0.32% Portfolio Minus S&P 500 0.00 pp CB-2026-08-13-1M monthly / close 2026-09-04 Portfolio +1.36% S&P 500 -0.99% Portfolio Minus S&P 500 +2.35 pp CB-2026-09-02-1W weekly / close 2026-09-04 Portfolio -0.82% S&P 500 -0.39% Portfolio Minus S&P 500 -0.43 pp CB-2026-08-11-1M monthly / close 2026-09-04 Portfolio +5.61% S&P 500 -0.05% Portfolio Minus S&P 500 +5.66 pp CB-2026-09-01-1W weekly / close 2026-09-04 Portfolio +0.43% S&P 500 +0.66% Portfolio Minus S&P 500 -0.22 pp CB-2026-08-09-1M monthly / close 2026-09-04 Portfolio +0.82% S&P 500 -0.37% Portfolio Minus S&P 500 +1.19 pp CB-2026-08-30-1W weekly / close 2026-09-04 Portfolio -0.11% S&P 500 +0.41% Portfolio Minus S&P 500 -0.52 pp CB-2026-08-07-1M monthly / close 2026-09-04 Portfolio +1.75% S&P 500 -0.40% Portfolio Minus S&P 500 +2.15 pp
Completed results

How Has This Model Performed?

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

Weekly record

2 wins / 33 completed

Avg return +0.77%
S&P 500 +0.36%
Avg Portfolio Minus S&P 500 +0.41 pp
Hit rate 60.6%
Avg rank 4.0
Best round CB-2026-07-15-1W
Monthly record

3 wins / 18 completed

Avg return +3.66%
S&P 500 +3.04%
Avg Portfolio Minus S&P 500 +0.62 pp
Hit rate 66.7%
Avg rank 3.7
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.

CB-2026-07-08-1Mmonthly / rank 6 of 7 -2.55 pp CB-2026-07-08-1Wweekly / rank 2 of 7 +1.28 pp CB-2026-07-09-1Mmonthly / rank 7 of 7 -4.02 pp CB-2026-07-09-1Wweekly / rank 7 of 7 -4.88 pp CB-2026-07-10-1Mmonthly / rank 7 of 8 -6.10 pp CB-2026-07-10-1Wweekly / rank 6 of 8 -4.47 pp CB-2026-07-13-1Mmonthly / rank 2 of 8 +2.02 pp CB-2026-07-13-1Wweekly / rank 3 of 8 +4.62 pp CB-2026-07-14-1Mmonthly / rank 2 of 8 +2.01 pp CB-2026-07-14-1Wweekly / rank 4 of 8 +2.97 pp CB-2026-07-15-1Mmonthly / rank 5 of 8 +2.67 pp CB-2026-07-15-1Wweekly / rank 2 of 8 +5.71 pp CB-2026-07-17-1Mmonthly / rank 1 of 8 +0.15 pp CB-2026-07-17-1Wweekly / rank 4 of 8 +1.54 pp CB-2026-07-20-1Wweekly / rank 6 of 8 +0.75 pp CB-2026-07-21-1Mmonthly / rank 2 of 7 +4.22 pp CB-2026-07-21-1Wweekly / rank 6 of 7 -1.59 pp CB-2026-07-22-1Mmonthly / rank 2 of 7 +4.31 pp CB-2026-07-22-1Wweekly / rank 7 of 7 +1.62 pp CB-2026-07-23-1Mmonthly / rank 5 of 7 +1.23 pp CB-2026-07-23-1Wweekly / rank 4 of 7 -0.79 pp CB-2026-07-24-1Mmonthly / rank 6 of 8 +0.09 pp CB-2026-07-24-1Wweekly / rank 4 of 8 -0.90 pp CB-2026-07-27-1Mmonthly / rank 4 of 8 -0.62 pp CB-2026-07-27-1Wweekly / rank 5 of 8 -2.11 pp CB-2026-07-28-1Mmonthly / rank 7 of 8 -3.74 pp CB-2026-07-28-1Wweekly / rank 4 of 8 -3.85 pp CB-2026-07-29-1Mmonthly / rank 2 of 8 -1.75 pp CB-2026-07-29-1Wweekly / rank 4 of 8 -4.72 pp CB-2026-07-30-1Mmonthly / rank 1 of 8 +3.51 pp CB-2026-07-30-1Wweekly / rank 5 of 8 -1.82 pp CB-2026-07-31-1Mmonthly / rank 1 of 8 +3.81 pp CB-2026-07-31-1Wweekly / rank 3 of 8 -1.28 pp CB-2026-08-04-1Mmonthly / rank 4 of 8 +2.37 pp CB-2026-08-04-1Wweekly / rank 2 of 8 +1.07 pp CB-2026-08-05-1Mmonthly / rank 2 of 8 +3.64 pp CB-2026-08-05-1Wweekly / rank 1 of 8 +2.58 pp CB-2026-08-07-1Wweekly / rank 3 of 8 +2.20 pp CB-2026-08-09-1Wweekly / rank 4 of 8 +0.91 pp CB-2026-08-11-1Wweekly / rank 2 of 8 +2.15 pp CB-2026-08-13-1Wweekly / rank 2 of 8 +4.85 pp CB-2026-08-15-1Wweekly / rank 5 of 8 +3.24 pp CB-2026-08-18-1Wweekly / rank 6 of 8 -1.23 pp CB-2026-08-19-1Wweekly / rank 3 of 7 +1.53 pp CB-2026-08-20-1Wweekly / rank 7 of 7 +1.65 pp CB-2026-08-21-1Wweekly / rank 7 of 7 -0.55 pp CB-2026-08-23-1Wweekly / rank 6 of 7 +0.89 pp CB-2026-08-24-1Wweekly / rank 1 of 7 +0.49 pp CB-2026-08-25-1Wweekly / rank 2 of 7 +0.76 pp CB-2026-08-26-1Wweekly / rank 3 of 7 -0.09 pp CB-2026-08-27-1Wweekly / rank 3 of 7 +0.99 pp
Ranking context

Where Does It Rank Against Comparable Models?

Each group uses only rounds completed by every included model.

See every comparison group 16
Weekly · Current

Aug 19, 2026 roster

Weekly comparison set automatically opened when the Aug 19 official roster first required a new equal-run benchmark group across 7 models.

Open full set
#4 Rank in set 6.4 CapitalBench Score 10.6% Total return 11 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
GPT-5.6 Sol
Claude Fable 5
Grok 4.5 This model
Claude Opus 5
Gemini 3.1 Pro
Grok 4.6
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 · 11/11 scored rounds
7.4
GPT-5.6 Sol OpenAI · 11/11 scored rounds
7.2
Claude Fable 5 Anthropic · 11/11 scored rounds
7.1
Grok 4.5 xAI · 11/11 scored rounds
6.4
Claude Opus 5 Anthropic · 11/11 scored rounds
6.1
Gemini 3.1 Pro Google · 11/11 scored rounds
3.9
Grok 4.6 xAI · 11/11 scored rounds
2.6
S&P 500 S&P 500 · 11/11 scored rounds
-1.2
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
11 shared resolved rounds7 equal-run models rankedQualified at 6+ shared roundsNewest included round: CB-2026-08-27-1W
Return context

Average Return Details

Average portfolio return across the same finished rounds.

xAI Grok 4.3
1.10%
OpenAI GPT-5.6 Sol
1.07%
Anthropic Claude Fable 5
1.06%
xAI Grok 4.5
0.96%
Anthropic Claude Opus 5
0.90%
Google Gemini 3.1 Pro
0.58%
xAI Grok 4.6
0.39%
S&P S&P 500
-0.18%
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.
14.89%
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 Sep 8
50% monthly / 50% weekly7 models

Grok 4.3 invests most differently from the group

Claude Opus 5 is most like the group at 45.5/100. 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 Sep 8, 2026
Highest Portfolio Difference
65.9/100
Lowest Portfolio Difference
45.5/100
Model BehaviorSep 4-Sep 15
Weekly live roundCB-2026-09-04-1W7 models

GPT-6 Astra has the strongest current weekly recent-winner tilt

Its score is 36.2 out of 100, with 0.0% in the top recent-return quintile. Grok 4.5 is lowest at 3.7.

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 4, 2026
Leader Recent Winner Tilt Score
36.2/100
Leader Top Recent Winner Quintile Allocation
0.00%
Leader Peer Delta
21.9
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.

Market EnvironmentAs of Sep 4
Monthly market environments12 resolved rounds2 models

Monthly model leadership changes with the S&P 500 environment

Grok 4.3 leads down environments at -1.22% across 6 tests; Grok 4.5 leads up environments at +4.11% across 6 tests.

Market environments group resolved rounds by the S&P 500 return over the same weekly or monthly window. Models are compared only on shared rounds; high confidence requires at least six observations and stable leadership.

Medium confidenceMath: deterministicData through Sep 4, 2026
Down Leader Average Return
-1.22%
Down Shared Rounds
6
Down Leader Stability
1.00
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-2026-09-04-1W official-v3-20260904-weekly-clean weekly 2026-09-08 to 2026-09-15 SOFTWARE 35.0%CYBERSECURITY 35.0%AGRICULTURE 30.0% Pending
Full portfolio
Software (IGV) 35.0% Cybersecurity (CIBR) 35.0% Agriculture Commodities (DBA) 30.0%
Rationale

Modest SPY strength with low cross-sectional dispersion; mixed labor/inflation data and rate-hike odds favor selective quality pullbacks over pure continuation or deep losers with fundamental drag. High-vol tech pullbacks and commodity strength compete with defensive quality.

CB-2026-09-04-1M official-v3-20260904-monthly-clean monthly 2026-09-08 to 2026-10-08 CYBERSECURITY 35.0%AEROSPACE_DEFENSE 35.0%INDUSTRIALS 30.0% Pending
Full portfolio
Cybersecurity (CIBR) 35.0% Aerospace and Defense (ITA) 35.0% Industrials Sector (XLI) 30.0%
Rationale

Sticky PCE near 3.3-3.7%, soft Q2 GDP 1.5%, 58% odds of Sept hike, and elevated oil/diesel create mixed one-month backdrop; recent sector pullbacks in quality names offer selective reversal potential while mega-cap/tech continuation is fragile and crypto strength lacks fundamental support.

CB-2026-09-03-1W official-v3-20260903-weekly weekly 2026-09-04 to 2026-09-14 CYBERSECURITY 35.0%METALS_MINING 35.0%SILVER 30.0% Pending
Full portfolio
Cybersecurity (CIBR) 35.0% Metals and Mining (XME) 35.0% Silver (SLV) 30.0%
Rationale

Mixed cross-section with modest SPY gains, elevated oil/geopolitics, soft labor signals ahead of jobs data, and several high-quality pullbacks in prior-strong names amid normal 5s dispersion; FOMC blackout and Labor Day shorten effective window.

CB-2026-09-03-1M official-v3-20260903-monthly monthly 2026-09-04 to 2026-10-05 CYBERSECURITY 35.0%REGIONAL_BANKS 35.0%INDUSTRIALS 30.0% Pending
Full portfolio
Cybersecurity (CIBR) 35.0% Regional Banks (KRE) 35.0% Industrials Sector (XLI) 30.0%
Rationale

Softening labor signals, elevated services prices, and pending FOMC create mixed one-month setup; quality pullbacks in prior-strong tech/defense/industrials offer selective reversal edges while mega-cap resilience and crypto momentum limit broad risk-on continuation.

CB-2026-09-02-1W official-v3-20260902-weekly weekly 2026-09-03 to 2026-09-11 SILVER 35.0%GOLD 35.0%MATERIALS 30.0% Pending
Full portfolio
Silver (SLV) 35.0% Gold (IAU) 35.0% Materials Sector (XLB) 30.0%
Rationale

Equities posted a third down day with rising yields and 66% September hike odds; oil surged on Hormuz/geopolitical reports while gold/silver sold off sharply after strong priors; labor and ISM data plus OPEC+ sit inside the one-week window, favoring selective mean-reversion in high-quality pullbacks over pure momentum continuation.

CB-2026-09-02-1M official-v3-20260902-monthly monthly 2026-09-03 to 2026-10-05 REGIONAL_BANKS 35.0%FINANCIALS 35.0%AEROSPACE_DEFENSE 30.0% Pending
Full portfolio
Regional Banks (KRE) 35.0% Financials Sector (XLF) 35.0% Aerospace and Defense (ITA) 30.0%
Rationale

Elevated cross-asset dispersion with oil spike on Hormuz/Iran risks, rising yields, mixed ISM/labor data, and Fed hike odds near 66% create mixed continuation/reversal setup; quality pullbacks in financials/banks favored over stretched momentum or rate-sensitive losers for 1M window.

CB-2026-09-01-1W official-v3-20260901-weekly weekly 2026-09-02 to 2026-09-10 HEALTHCARE 35.0%GOLD 35.0%SILVER 30.0% Pending
Full portfolio
Healthcare Sector (XLV) 35.0% Gold (IAU) 35.0% Silver (SLV) 30.0%
Rationale

Low cross-sectional dispersion with weak breadth (RSP lagging SPY), sticky inflation prints, upcoming employment data and FOMC later; recent sector/metal pullbacks after prior strength favor selective mean-reversion over pure momentum continuation into the short window.

CB-2026-09-01-1M official-v3-20260901-monthly monthly 2026-09-02 to 2026-10-02 REGIONAL_BANKS 35.0%SMALL_VALUE 35.0%REAL_ESTATE 30.0% Pending
Full portfolio
Regional Banks (KRE) 35.0% US Small-Cap Value (IWN) 35.0% Real Estate Sector (XLRE) 30.0%
Rationale

Sticky PCE/CPI near 3.4-3.7%, soft July payrolls and 1.5% Q2 GDP, 10y at 4.75% and Sept FOMC ahead create mixed one-month setup; recent breadth weak while energy/tech pockets held up, favoring selective quality pullbacks over pure momentum or deep rate-sensitive losers.

CB-2026-08-30-1W official-v3-20260830-weekly weekly 2026-08-31 to 2026-09-08 HEALTHCARE 35.0%SILVER 35.0%GOLD 30.0% Pending
Full portfolio
Healthcare Sector (XLV) 35.0% Silver (SLV) 35.0% Gold (IAU) 30.0%
Rationale

Low cross-sectional dispersion with mixed short-term signals: sticky inflation and hawkish Fed tone support limited risk appetite, while quality pullbacks in metals and select defensives offer modest reversal potential versus strong short-term software/cyber momentum that lacks fresh catalysts inside the one-week window.

CB-2026-08-30-1M official-v3-20260830-monthly monthly 2026-08-31 to 2026-09-30 REGIONAL_BANKS 35.0%SMALL_VALUE 35.0%REAL_ESTATE 30.0% Pending
Full portfolio
Regional Banks (KRE) 35.0% US Small-Cap Value (IWN) 35.0% Real Estate Sector (XLRE) 30.0%
Rationale

Elevated yields, firm Fed inflation stance, soft labor prints and mid-September FOMC create mixed one-month setup; quality pullbacks in rate-sensitive and small-value names offer better reversal odds than crowded momentum or high-vol laggards while broad equity beta remains supported but not strongly directional.

Audit and data Public Audit Packets For This Model