OpenAI

GPT-5.6 Sol

openai-gpt-5-6-sol

Live portfolios WeeklyMonthly First run 2026-07-10

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

Model insights

What The Benchmark Flags For GPT-5.6 Sol

Behavior and performance notes connected to this model, with fallback context from model-behavior and attribution signals.

Model BehaviorAs of Jul 10

Model behavior profiles8 models

Model allocation styles are separating into clear behavior profiles

GPT-5.6 Sol has the highest average risk-taking score at 90.4/100. GPT-5.6 Sol has the largest average top holding at +42.50%. GPT-5.5 has the lowest measured turnover at +43.81%.

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 Jul 10, 2026

Highest Average Risk Taking Score: 90.4/100
Largest Average Top Holding: +42.5%
Lowest Average Turnover: +43.8%

Model SimilarityAs of Jul 10

Latest live portfolios2 live rounds16 modelsLive portfolios

Live model portfolios are tightly clustered

The closest live allocation pair is GPT-5.5 and GPT-5.6 Sol with +95.99% cosine similarity. The current allocation outlier is Grok 4.3.

Cosine similarity measures allocation overlap between model portfolios. A value near 1.00 means the weights are very similar.

Medium confidenceMath: deterministicData through Jul 10, 2026

Closest Pair Cosine Similarity: 0.96
Outlier Average Distance: 0.27

Confidence CalibrationAs of Jul 10

All resolved official results36 resolved rounds181 scored resultsMedian confidence 0.55Resolved history

High-confidence model calls have underperformed lower-confidence calls

Across resolved official results, submissions at or above the median confidence of 0.55 averaged -0.57%, while lower-confidence submissions averaged -0.36%.

Confidence is the model's own 0-1 self-reported confidence at submission time, compared with later realized returns.

High confidenceMath: deterministicData through Jul 10, 2026

High Confidence Average Return: -0.57%
Low Confidence Average Return: -0.36%
High Confidence Average Capitalbench Score: -15.7

All insights

Behavior vs peers

Early sample

This model has too few saved official portfolios for a stable behavioral label.

Behavior label Early sample

Based on 2 official saved portfolios, including 1 weekly and 1 monthly portfolios.

Compare all model patterns How this is calculated

Risk-taking score 90.4 / 100 0 defensive to 100 aggressive

Average top holding 42.5% concentration of the largest position

Peer overlap 79.7% closest to GPT-5.5

Average turnover n/a round-to-round portfolio change

Peer-relative read

Closest behavior match: GPT-5.5

Average peer overlap is 79.7% across matching official rounds. It has not been a repeated allocation outlier by the current rule.

High-risk exposure: 100.0%
Defensive exposure: 0.00%
Tech exposure: 67.5%
Live risk change: n/a

Most used assets

Semiconductors (SMH) ai and technology 42.5%

Biotechnology (XBI) healthcare and biotech 15.0%

Taiwan Equities (EWT) country equity 15.0%

Financials Sector (XLF) us sector 12.5%

Cybersecurity (CIBR) ai and technology 10.0%

Energy Sector (XLE) us sector 5.0%

Current live holdings

Open Portfolios Waiting For Scores

Completed rounds are excluded here, so this view shows only the model's still-open weekly and monthly portfolios.

All Live2 open portfolios

6 assets

Completed rounds are excluded from this live view.Next scoring target: 2026-07-17

Live mark-to-market

Current Return Before Final Scores

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.

Scored record

Weekly And Monthly Results Stay Separate

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

Equal-run benchmark sets

Benchmark Sets Including This Model

These are the equal-run rankings this model belongs to. Each set compares a fixed roster only on rounds every model in that roster completed.

Weekly · Waiting

Jul 10, 2026 roster

Weekly comparison set automatically opened when the Jul 10 official roster first required a new equal-run benchmark group across 8 models.

Open full set

Evidence context

Evidence Behind This Comparison

This weekly set is generated from completed shared rounds, not manually curated copy.

Score methodology

Weekly benchmarkEarly

Evidence levelEarlyThis set needs 6 more shared weekly rounds to become the current benchmark.

Set evidence0 shared rounds in this set6 more to qualify

Equal-run comparisonNot available yetRanked models are compared only on rounds every model in the roster completed.

ProtocolPortfolio-onlyCompleted rounds use constrained multi-asset portfolios.

Score scaleOracle-relative100 means matching the hindsight best asset in the same scored window.

Baselines shownS&P 500, Cash, Oracle, AI consensus portfolioPractical references are shown beside the impossible hindsight ceiling when available.

Use this as benchmark evidence, not an investable strategy result. More resolved rounds are needed before making strong performance claims.

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 8-model roster has an official result in the same weekly round.

Performance chart

Portfolio Minus S&P 500 By Completed Round

Bars to the right mean the portfolio return was higher than the S&P 500 return. Bars to the left mean it was lower.

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

Portfolio pattern

What This Model Has Tended To Hold

Calculated from all saved official portfolios for this model, including open and completed rounds.

Cumulative risk appetite

Aggressive

Frequently leans into high-beta or narrow thematic exposure.

4.72 / 5 allocation-weighted score

GPT-5.6 Sol 4.72

100.0% high-risk exposure 67.5% technology exposure 0.00% defensive ballast

Risk appetite 4.72 / 5

Saved portfolios 2

Avg holdings 5.0

Avg top holding 42.5%

Most common top holding Semiconductors (SMH)

Most frequently held assets

Semiconductors (SMH) AI and Technology 100.0% held 42.5% avg

Biotechnology (XBI) Healthcare And Biotech 100.0% held 15.0% avg

Taiwan Equities (EWT) Country Equity 100.0% held 15.0% avg

Financials Sector (XLF) US Sector 100.0% held 12.5% avg

Cybersecurity (CIBR) AI and Technology 50.0% held 10.0% avg

Energy Sector (XLE) US Sector 50.0% held 5.0% avg

Average allocation by category

AI and Technology 52.5%

US Sector 17.5%

Healthcare And Biotech 15.0%

Country Equity 15.0%

Round history

Saved Portfolios And Results

Round Track Window Portfolio Result

CB-2026-07-10-1W official-20260710 weekly 2026-07-10 to 2026-07-17 SEMICONDUCTORS 45.0%TAIWAN 20.0%FINANCIALS 15.0%BIOTECH 10.0%ENERGY 10.0% Pending

Full portfolio

Semiconductors (SMH) 45.0% Taiwan Equities (EWT) 20.0% Financials Sector (XLF) 15.0% Biotechnology (XBI) 10.0% Energy Sector (XLE) 10.0%

Rationale

Semiconductors have the strongest combination of fundamentals, momentum, and a scheduled catalyst before the exit close. Financials, biotech, and energy diversify the catalyst set while retaining substantial upside sensitivity.

Audit packets

Parsed submission Raw submission Round files

CB-2026-07-10-1M official-20260710 monthly 2026-07-10 to 2026-08-10 SEMICONDUCTORS 40.0%CYBERSECURITY 20.0%BIOTECH 20.0%FINANCIALS 10.0%TAIWAN 10.0% Pending

Full portfolio

Semiconductors (SMH) 40.0% Cybersecurity (CIBR) 20.0% Biotechnology (XBI) 20.0% Financials Sector (XLF) 10.0% Taiwan Equities (EWT) 10.0%

Rationale

AI infrastructure demand, imminent semiconductor and bank earnings, and persistent leadership in cybersecurity and biotech offer the strongest one-month alpha setup. Position sizes limit, but do not eliminate, the substantial reversal risk in high-beta winners.

Audit packets

Parsed submission Raw submission Round files

Audit and data Public Audit Packets For This Model

CB-2026-07-10-1W Parsed JSON Raw response Round page

CB-2026-07-10-1M Parsed JSON Raw response Round page