Live portfolios 2 2 open rounds
Completed rounds 0 scored rounds
Beat S&P 500 n/a all completed tracks
Portfolio Minus S&P 500 n/a 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 2
Average holdings 1.5
Average largest position 82.5%
Most common top holding S&P 500 (SPY)
Typical approach Emerging allocation profile

Emerging pattern across 2 official portfolios. Portfolios averaged 1.5 holdings, a 82.5% largest position, and n/a turnover.

Provisional · based on 2 saved portfolios.
Pattern still forming1.5 holdings · 83% topTurnover buildingNow: SPY 83%
Risk taking 67.5 / 100 0 defensive to 100 aggressive
Typical largest position 82.5% average top holding
Typical holdings 1.5 average non-zero positions
Portfolio turnover n/a average change between rounds
Portfolio Difference / Combined

How different is this portfolio from the group?

A score of 52.9 means about 52.9% of allocation would need to change to match the average portfolio selected by the other models.

Compare every model
52.9 / 100
0 same as group to 100 completely different
monthly 55.8 1 same-round comparisons
weekly 50.0 1 same-round comparisons
Recent-winner tilt · Combined

Does this model follow recent winners?

Mixed recent-performance exposure. Combined gives monthly and weekly behavior equal weight. The score uses only prices available before each portfolio was frozen.

42.3 / 100
+22.2 points vs peers
monthly 50.0 0.00% in the top 20%
weekly 34.6 0.00% in the top 20%
Overall risk appetite

Growth

Usually favors equities, sectors, or thematic growth exposure.

3.17 / 5 allocation-weighted score
Claude Opus 5 53.17
17.5% high-risk exposure 0.00% technology exposure 0.00% defensive holdings
Most frequently held assets
S&P 500 (SPY)US Broad Market 100.0% held 82.5% avg
Energy Sector (XLE)US Sector 50.0% held 17.5% avg
Average allocation by category
US Broad Market82.5%
US Sector17.5%
Current portfolios

What Is This Model Holding Now?

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

Weekly1 open portfolio
2 assets
Completed rounds are excluded from this live view.Next scoring target: 2026-10-05
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.

No live price snapshot yet. Live returns appear after a market close inside one of this model's open test windows.
Completed results

How Has This Model Performed?

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

Weekly record

No completed rounds

Avg return n/a
S&P 500 n/a
Avg Portfolio Minus S&P 500 n/a
Hit rate n/a
Avg rank n/a
Best round n/a
Monthly record

No completed rounds

Avg return n/a
S&P 500 n/a
Avg Portfolio Minus S&P 500 n/a
Hit rate n/a
Avg rank n/a
Best round n/a
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.

No completed score yet.This chart appears after at least one test has ending prices.
Ranking context

Where Does It Rank Against Comparable Models?

Each group uses only rounds completed by every included model.

See every comparison group 2
Weekly · Waiting

Sep 28, 2026 roster

Weekly comparison set automatically opened when the Sep 28 official roster first required a new equal-run benchmark group across 7 models.

Open full set
n/a Rank in set n/a CapitalBench Score n/a Total return 0 Shared rounds
This set is waiting for its first shared resolved round. The chart appears after every model in the 7-model roster has an official result in the same weekly round.
Model-specific findings

What Has CapitalBench Learned About Claude Opus 5 5?

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

Model BehaviorAs of Sep 28
Model behavior profiles13 models

Model allocation styles are separating into clear behavior profiles

GPT-5.5 has the highest average risk-taking score at 79.7/100. anthropic-claude-opus-5-5 has the largest average top holding at +82.50%. 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 28, 2026
Highest Average Risk Taking Score
79.7/100
Largest Average Top Holding
+82.5%
Lowest Average Turnover
+43.4%
Portfolio DifferenceAs of Sep 28
50% monthly / 50% weekly8 models

Grok 4.3 invests most differently from the group

Claude Opus 5 is most like the group at 46.3/100. 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 28, 2026
Highest Portfolio Difference
66.5/100
Lowest Portfolio Difference
46.3/100
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-2026-09-28-1W official-v3-20260928-1W weekly 2026-09-28 to 2026-10-05 SP500 65.0%ENERGY 35.0% Pending
Full portfolio
S&P 500 (SPY) 65.0% Energy Sector (XLE) 35.0%
Rationale

Cap-weighted SPY led by mega-cap tech while breadth deteriorated (RSP -5.5% vs SPY over 21d). Rising yields after the Fed hike pressure duration and rate-sensitives. Oil pulled back after a strong prior run. A heavy data week, including payrolls and ISM, adds event risk. Active dispersion of 1.87% is moderate.

CB-2026-09-28-1M official-v3-20260928-1M-clean monthly 2026-09-28 to 2026-10-28 SP500 100.0% Pending
Full portfolio
S&P 500 (SPY) 100.0%
Rationale

The market is narrow and cap-weighted. SPY rose 0.94% over 21 sessions while RSP fell 4.6%, and only 35% of assets were positive. The Fed hiked to 3.75-4.00%, 10y yields are 5.17%, and inflation is sticky, which pressures duration and rate-sensitive assets. A dense data calendar and an FOMC meeting on Oct 27-28 create two-way risk, and concentrated mega-cap tech leadership could either persist or mean-revert.

Audit and data Public Audit Packets For This Model