Emerging pattern across 4 official portfolios. Portfolios averaged 3.0 holdings, a 35.0% largest position, and 82.5% turnover.
Provisional · based on 4 saved portfolios.Claude Fable 5.1
anthropic-claude-fable-5-1
Portfolio pattern Emerging allocation profile Emerging pattern across 4 official portfolios. Portfolios averaged 3.0 holdings, a 35.0% largest position, and 82.5% turnover.How Does This Model Tend To Invest?
Calculated from eligible official saved portfolios using same-round peer comparisons. How labels and pills are determined
How different is this portfolio from the group?
A score of 54.0 means about 54.0% of allocation would need to change to match the average portfolio selected by the other models.
Compare every modelDoes 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.
Growth
Usually favors equities, sectors, or thematic growth exposure.
What Is This Model Holding Now?
4 open portfolios across weekly and monthly tests. Completed rounds are excluded.
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.
How Has This Model Performed?
Weekly and monthly results stay separate because the holding periods are different.
No completed rounds
No completed rounds
When Did It Beat The S&P 500?
Bars to the right beat the S&P 500. Bars to the left trailed it.
Where Does It Rank Against Comparable Models?
Each group uses only rounds completed by every included model.
See every comparison group 4
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.
Sep 3, 2026 roster
Weekly comparison set automatically opened when the Sep 3 official roster first required a new equal-run benchmark group across 7 models.
Sep 4, 2026 roster
Monthly comparison set automatically opened when the Sep 4 official roster first required a new equal-run benchmark group across 7 models.
Sep 3, 2026 roster
Monthly comparison set automatically opened when the Sep 3 official roster first required a new equal-run benchmark group across 7 models.
What Has CapitalBench Learned About Claude Fable 5.1?
Findings tied directly to this model's decisions or completed results.
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.
- Highest Portfolio Difference
- 65.9/100
- Lowest Portfolio Difference
- 45.5/100
Model allocation styles are separating into clear behavior profiles
Claude Fable 5.1 has the highest average risk-taking score at 80.2/100. Grok 4.6 has the largest average top holding at +63.12%. 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.
- Highest Average Risk Taking Score
- 80.2/100
- Largest Average Top Holding
- +63.1%
- Lowest Average Turnover
- +43.4%
What Did It Choose In Each Round?
Open a row to see the full portfolio, rationale, and audit files.
CB-2026-09-04-1W official-v3-20260904-weekly-clean weekly 2026-09-08 to 2026-09-15 SOFTWARE 35.0%MATERIALS 35.0%SP500 30.0% Pending
Macro backdrop is stagflationary: core PCE 3.3% y/y, oil up 19% over 21 sessions with diesel at $5.85, 10y at 4.78%, and a 58% market-implied probability of a September hike with a hawkish dissent already on record. Weekly window contains PPI (Sep 10), ECB (Sep 10), and CPI (Sep 11) but the FOMC decision falls after the exit. Active dispersion is moderate (2.03%), breadth is weak (RSP -0.87% vs SPY over 5 sessions). Cross-section shows high-beta tech/crypto strength alongside a sharp software/cyber pullback; energy continuation is supply-driven. With rate-hike risk unresolved and CPI in-window, edges are modest and reversal candidates need a defensible pullback plus a prior trend.
CB-2026-09-04-1M official-v3-20260904-monthly-clean monthly 2026-09-08 to 2026-10-08 CYBERSECURITY 35.0%REGIONAL_BANKS 35.0%COPPER 30.0% Pending
Stagflationary backdrop: payrolls slowed sharply after revisions, core PCE 3.3% and headline 3.7%, oil up 19% over 21 sessions, diesel near $5.85, and futures price a 58% chance of a September hike with 10y at 4.78%. SPY sits within 1% of its 52-week high, so the index is not pricing this. A hawkish FOMC on September 16 plus CPI/PPI is the key window event. Prefer candidates whose recent relative pullbacks are not tied to the hike/energy risk, and avoid long-duration growth and crypto whose short bursts lack in-window support.
CB-2026-09-03-1W official-v3-20260903-weekly weekly 2026-09-04 to 2026-09-14 METALS_MINING 35.0%SILVER 35.0%SEMICONDUCTORS 30.0% Pending
SPY is near its 52-week high with low realized vol while breadth is narrow (RSP lagging by 0.9% over 5 sessions) and only 41% of assets were positive in the last week. Macro is stagflation-tinged: PCE inflation 3.7%, ISM prices above 70, Fed's Waller open to a hike, 10y at 4.77%, oil up 24% in a month amid an active Iran conflict. The scoring window contains payrolls, PPI, CPI, OPEC+ and Oracle/Adobe earnings with the Fed in blackout, so event risk is high. Recent weekly losers in semis, metals, silver and biotech sit on strong prior trends and look like temporary pullbacks; oil and Brazil are momentum spikes with thin fundamental support at the horizon.
CB-2026-09-03-1M official-v3-20260903-monthly monthly 2026-09-04 to 2026-10-05 SEMICONDUCTORS 35.0%CYBERSECURITY 35.0%SP500 30.0% Pending
SPY is near its 52-week high with low realized vol, but breadth is weak (RSP lagging, 5-session positive share 41%), oil is up 24% over 21 sessions on active Iran conflict, headline PCE inflation is 3.7% and Waller has signaled a possible hike. The window contains payrolls, CPI, and a September FOMC with real two-sided rate risk. Recent laggards with strong prior trends (semis, cybersecurity, momentum) plus Broadcom's AI print give a fair reversal setup, while energy-driven inflation hurts duration-sensitive and consumer names.