Live portfolios 22 22 open rounds
Completed rounds 27 scored rounds
Beat S&P 500 40.7% all completed tracks
Portfolio Minus S&P 500 -0.09 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 53
Average holdings 3.6
Average largest position 36.4%
Most common top holding Semiconductors (SMH)
Typical approach High-risk tactical allocator

Risk taking averaged 72.5/100, with a median 4.3 points above same-round peers; the difference had the same direction in 68% of 53 matched portfolios. Portfolios averaged 3.6 holdings, a 36.4% largest position, and 67.6% turnover.

Moderate evidence · based on 53 saved portfolios.
Risk 72/100 · +4 pts vs peers3.6 holdings · 36% top68% turnoverNow: CIBR 19%
Risk taking 72.5 / 100 0 defensive to 100 aggressive
Typical largest position 36.4% average top holding
Typical holdings 3.6 average non-zero positions
Portfolio turnover 67.6% average change between rounds
Portfolio Difference / Combined

How different is this portfolio from the group?

A score of 49.2 means about 49.2% of allocation would need to change to match the average portfolio selected by the other models.

Compare every model
49.2 / 100
0 same as group to 100 completely different
monthly 65.1 6 same-round comparisons
weekly 33.3 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.

11.0 / 100
-8.3 points vs peers
monthly 17.4 0.00% in the top 20%
weekly 4.5 0.00% in the top 20%
Structured decision process

How the model builds its shortlist

Candidate-ledger evidence is available for 33 of 53 eligible portfolios. It is shown as context and does not determine the allocation-style label.

Avg candidates7.4 SPY included100.0% Forecast spread11.1% Stated confidence58.6%
Coverage — forecasts 33/53 · confidence 53/53 · key risks 53/53
Overall risk appetite

Growth

Usually favors equities, sectors, or thematic growth exposure.

4.00 / 5 allocation-weighted score
GPT-5.6 Sol4.00
76.4% high-risk exposure 28.3% technology exposure 8.7% defensive holdings
Most frequently held assets
Energy Sector (XLE)US Sector 41.5% held 11.7% avg
Cybersecurity (CIBR)AI and Technology 35.8% held 10.3% avg
Financials Sector (XLF)US Sector 32.1% held 6.7% avg
Healthcare Sector (XLV)US Sector 26.4% held 7.0% avg
Semiconductors (SMH)AI and Technology 24.5% held 9.1% avg
Biotechnology (XBI)Healthcare And Biotech 17.0% held 4.6% avg
US Dividend Equities (SCHD)US Factor Equity 17.0% held 4.4% avg
Average allocation by category
US Sector32.7%
AI and Technology22.3%
Commodities7.3%
US Factor Equity5.5%
US Industry5.0%
Healthcare And Biotech4.6%
International Equity4.2%
Current portfolios

What Is This Model Holding Now?

22 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: 2026-08-25
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
-0.69%
S&P 500
-0.74%
Portfolio Minus S&P 500
+0.04 pp
2 open tests
Monthly live
Portfolio
+0.59%
S&P 500
+0.36%
Portfolio Minus S&P 500
+0.24 pp
14 open tests
See all 16 open round returns
CB-2026-08-19-1M monthly / close 2026-08-20 Portfolio -0.77% S&P 500 -0.84% Portfolio Minus S&P 500 +0.07 pp CB-2026-08-18-1M monthly / close 2026-08-20 Portfolio -0.85% S&P 500 -0.63% Portfolio Minus S&P 500 -0.22 pp CB-2026-08-15-1M monthly / close 2026-08-20 Portfolio -0.49% S&P 500 -1.30% Portfolio Minus S&P 500 +0.81 pp CB-2026-08-13-1M monthly / close 2026-08-20 Portfolio -2.54% S&P 500 -1.96% Portfolio Minus S&P 500 -0.57 pp CB-2026-08-11-1M monthly / close 2026-08-20 Portfolio -1.56% S&P 500 -1.03% Portfolio Minus S&P 500 -0.52 pp CB-2026-08-09-1M monthly / close 2026-08-20 Portfolio +0.79% S&P 500 -1.35% Portfolio Minus S&P 500 +2.14 pp CB-2026-08-07-1M monthly / close 2026-08-20 Portfolio -2.23% S&P 500 -1.38% Portfolio Minus S&P 500 -0.85 pp CB-2026-08-05-1M monthly / close 2026-08-20 Portfolio +2.77% S&P 500 -0.93% Portfolio Minus S&P 500 +3.70 pp CB-2026-08-04-1M monthly / close 2026-08-20 Portfolio -0.28% S&P 500 -1.13% Portfolio Minus S&P 500 +0.85 pp CB-2026-07-31-1M monthly / close 2026-08-20 Portfolio +2.72% S&P 500 +2.08% Portfolio Minus S&P 500 +0.64 pp CB-2026-07-30-1M monthly / close 2026-08-20 Portfolio +3.53% S&P 500 +2.82% Portfolio Minus S&P 500 +0.71 pp CB-2026-07-29-1M monthly / close 2026-08-20 Portfolio +0.92% S&P 500 +4.54% Portfolio Minus S&P 500 -3.62 pp CB-2026-07-28-1M monthly / close 2026-08-20 Portfolio +2.97% S&P 500 +2.93% Portfolio Minus S&P 500 +0.04 pp CB-2026-07-27-1M monthly / close 2026-08-20 Portfolio +3.31% S&P 500 +3.18% Portfolio Minus S&P 500 +0.13 pp CB-2026-08-19-1W weekly / close 2026-08-20 Portfolio -1.44% S&P 500 -0.84% Portfolio Minus S&P 500 -0.60 pp CB-2026-08-18-1W weekly / close 2026-08-20 Portfolio +0.06% S&P 500 -0.63% Portfolio Minus S&P 500 +0.69 pp
Completed results

How Has This Model Performed?

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

Weekly record

3 wins / 18 completed

Avg return +0.67%
S&P 500 +0.64%
Avg Portfolio Minus S&P 500 +0.02 pp
Hit rate 50.0%
Avg rank 4.4
Best round CB-2026-07-15-1W
Monthly record

0 wins / 9 completed

Avg return +2.80%
S&P 500 +3.12%
Avg Portfolio Minus S&P 500 -0.32 pp
Hit rate 22.2%
Avg rank 5.9
Best round CB-2026-07-15-1M
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 10
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
#4 Rank in set 8.8 CapitalBench Score 7.9% 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
Claude Opus 5
GPT-5.6 Sol This model
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%
Excluded for fairness: CB-2026-08-15-1W missing openai-gpt-5-5 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 GPT-5.6 Sol?

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
Live PerformanceAs of Aug 20
Open-round interim performance19 open rounds9 models

Gemini 3.1 Pro has the strongest live alpha

Using the latest available interim close, Gemini 3.1 Pro in CB-2026-08-04-1M is ahead of the S&P 500 by +6.30 percentage points, while GPT-5.6 Sol in CB-2026-07-29-1M is at -3.62 percentage points.

Live alpha is interim model return minus interim S&P 500 return. It is provisional until the round reaches its official score date.

Medium confidenceMath: deterministicData through Aug 20, 2026
Best Live Alpha
+6.30%
Worst Live Alpha
-3.62%
Why it matters

Live alpha is provisional, but it shows how open model portfolios are moving before the final official score.

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 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

Active-return dispersion is elevated at 5.20%, while only 39.13% of assets rose over five sessions despite broad 21-session strength. This favors selective reversals in high-quality prior leaders rather than indiscriminate momentum chasing.

CB-2026-08-23-1M official-v3-20260823-monthly monthly 2026-08-24 to 2026-09-24 SEMICONDUCTORS 35.0%OIL 35.0%US_DOLLAR 30.0% Pending
Full portfolio
Semiconductors (SMH) 35.0% Crude Oil (USO) 35.0% US Dollar (UUP) 30.0%
Rationale

Wide cross-asset performance gaps, weakening labor and spending data, hawkish rate risk, and near-term geopolitical and earnings catalysts favor selective reversals rather than broad continuation.

CB-2026-08-21-1W official-v3-20260821-weekly weekly 2026-08-21 to 2026-08-28 CYBERSECURITY 35.0%AEROSPACE_DEFENSE 35.0%SOFTWARE 30.0% Pending
Full portfolio
Cybersecurity (CIBR) 35.0% Aerospace and Defense (ITA) 35.0% Software (IGV) 30.0%
Rationale

High cross-sectional dispersion, weak near-term breadth, rising yields, and major inflation and NVIDIA event risk favor selective reversal trades over broad continuation. Strong prior trends followed by sharp relative pullbacks offer the clearest one-week opportunities.

CB-2026-08-21-1M official-v3-20260821-monthly monthly 2026-08-21 to 2026-09-21 US_DOLLAR 35.0%SEMICONDUCTORS 35.0%MOMENTUM 30.0% Pending
Full portfolio
US Dollar (UUP) 35.0% Semiconductors (SMH) 35.0% US Momentum Equities (MTUM) 30.0%
Rationale

Large cross-asset return gaps, elevated candidate volatility, firm long yields, and multiple macro events favor selective pullback reversals and defensive exposure rather than broad continuation.

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

Breadth is healthier than cap-weighted performance, but the one-week window includes major macro releases and NVIDIA earnings. Favor high-quality pullback reversals while avoiding unsupported extrapolation of crypto and commodity gains.

CB-2026-08-20-1M official-v3-20260820-monthly monthly 2026-08-20 to 2026-09-21 SEMICONDUCTORS 35.0%CYBERSECURITY 35.0%REAL_ESTATE 30.0% Pending
Full portfolio
Semiconductors (SMH) 35.0% Cybersecurity (CIBR) 35.0% Real Estate Sector (XLRE) 30.0%
Rationale

Broad participation and falling long yields support selective pullback reversals, but weak employment, persistent inflation risk, and major earnings and central-bank events make continuation unreliable and dispersion likely to remain high.

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

Moderate dispersion and broad 21-session participation favor selective reversals, but weak labor and retail data, elevated long yields, and major exit-day macro releases limit conviction. Pullbacks backed by prior relative strength and quality dominate unsupported momentum.

CB-2026-08-19-1M official-v3-20260819-monthly monthly 2026-08-19 to 2026-09-18 SMALL_VALUE 35.0%LARGE_VALUE 35.0%INVESTMENT_GRADE_CREDIT 30.0% Pending
Full portfolio
US Small-Cap Value (IWN) 35.0% US Large-Cap Value (IWD) 35.0% Investment Grade Corporate Bonds (LQD) 30.0%
Rationale

Weak labor and softer inflation favor selective duration and defensive reversals, but elevated services prices, a hawkish FOMC split, and strong manufacturing argue against an aggressive rates bet. High cross-asset volatility favors quality pullbacks over extreme losers.

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

Breadth is positive but macro signals conflict: softer inflation supports risk assets while weak payrolls, retail sales, and consumer sentiment constrain cyclicals. High-quality pullbacks offer better one-week asymmetry than extended high-beta winners.

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

Cooling inflation and weakening labor and retail data favor selective reversals in duration and defensives, but elevated producer inflation, a divided Fed, and strong activity surveys limit conviction. Extreme commodity and thematic moves face substantial reversal risk.

Audit and data Public Audit Packets For This Model