CapitalBench

The benchmark for AI capital allocation

Each AI model gets the same market brief, builds one portfolio in one response, and uses no browsing or tools. Real market prices determine the result.

See how AI models perform against each other, how they invest and take risk, and how they perform in the real market.

Read the CapitalBench Manifesto

Open Live Positions & Returns Get score alerts Request API access

Model behavior patterns How do AI models allocate differently?

7 models

Claude Fable 5.1 Anthropic Tactical allocator Near peer mix2.8 holdings · 40% top66% turnoverNow: SPY 31%

Grok 4.5 xAI Peer-balanced allocator Near peer mix3.7 holdings · 35% top57% turnoverNow: IWN 18%

Grok 4.3 xAI Distinctive allocator Near peer mix3.1 holdings · 49% top55% turnoverNow: SPY 48%

Claude Opus 5 Anthropic Group-aligned allocator Near peer mix3.6 holdings · 36% top53% turnoverNow: SPY 22%

Gemini 3.1 Pro Google Distinctive allocator Near peer mix3.2 holdings · 40% top62% turnoverNow: ITA 20%

Grok 4.6 xAI Peer-balanced allocator Near peer mix2.2 holdings · 62% top55% turnoverNow: SPY 48%

GPT-6 Astra OpenAI Benchmark-anchored allocator S&P 500 core 33% · +16pp vs peers2.7 holdings · 45% top61% turnoverNow: SPY 35%

See full behavior

Benchmark results

Which models are performing best?

Monthly and weekly tracks stay separate.

A score of 30 means the model earned 30% of the best possible return across these rounds. Calculation

Claude Fable 5

GPT-5.6 Sol

Claude Opus 5

Grok 4.3

Grok 4.5

Grok 4.6

Gemini 3.1 Pro

S&P 500

Max possible What is this? hindsight best asset

A score of 30 means the model earned 30% of the best possible return across these rounds. Calculation

Claude Fable 5 Anthropic · 9/9 scored rounds

8.4

GPT-5.6 Sol OpenAI · 9/9 scored rounds

2.8

Claude Opus 5 Anthropic · 9/9 scored rounds

0.3

Grok 4.3 xAI · 9/9 scored rounds

-0.2

Grok 4.5 xAI · 9/9 scored rounds

-2.1

Grok 4.6 xAI · 9/9 scored rounds

-4.3

Gemini 3.1 Pro Google · 9/9 scored rounds

-6.8

S&P 500 S&P 500 · 9/9 scored rounds

-0.4

Max possible Hindsight ceiling, not a model portfolio

What is this? 100.0

9 shared resolved rounds7 equal-run models rankedQualified at 3+ shared roundsNewest included round: CB-2026-08-25-1M

Return context

Average Return Details

Average portfolio return across the same finished rounds.

Claude Fable 5

1.94%

GPT-5.6 Sol

0.65%

Claude Opus 5

0.07%

Grok 4.3

-0.05%

Grok 4.5

-0.49%

Grok 4.6

-0.99%

Gemini 3.1 Pro

-1.59%

S&P S&P 500

-0.10%

MAX Max possible What is this?

23.28%

Fairness rule: every ranked model completed every included round. A missed round is excluded from this set for everyone.

Monthly and weekly are separate comparison tracks. Scores are never mixed across horizons. Read scoring rules

View all comparison sets Read scoring rules

Model Risk Benchmark

Which AI models take the most risk?

Compare how aggressively each model allocates capital across its official portfolios.

Updated through September 21, 2026Higher means more risk-seeking, not better.

GPT-5.5OpenAI

79.7/100Risk-seeking

98portfolios34.1%largest position3.8%defensive assets

Claude Fable 5.1Anthropic

75.1/100Risk-seeking

18portfolios40.0%largest position7.5%defensive assets

GPT-5.6 SolOpenAI

73.6/100Risk-seeking

69portfolios36.1%largest position8.1%defensive assets

Grok 4.5xAI

73.4/100Risk-seeking

89portfolios34.8%largest position6.7%defensive assets

Grok 4.3xAI

72.7/100Risk-seeking

144portfolios49.2%largest position6.3%defensive assets

Claude Opus 5Anthropic

72.3/100Risk-seeking

68portfolios35.7%largest position7.5%defensive assets

Gemini 3.1 ProGoogle

71.4/100Risk-seeking

144portfolios39.9%largest position13.7%defensive assets

Claude Opus 4.7Anthropic

71.3/100Risk-seeking

70portfolios31.8%largest position16.6%defensive assets

Grok 4.6xAI

71.0/100Risk-seeking

46portfolios62.3%largest position5.5%defensive assets

Claude Fable 5Anthropic

70.8/100Risk-seeking

84portfolios31.3%largest position12.1%defensive assets

GPT-6 AstraOpenAI

69.7/100Risk-seeking

16portfolios44.7%largest position10.9%defensive assets

Claude Opus 4.8Anthropic

69.2/100Risk-seeking

99portfolios35.3%largest position11.7%defensive assets

Portfolio Difference

Which AI models invest most differently from the group?

Compare each model's portfolio with the choices made by the other models in the same rounds.

Updated through September 21, 2026Overall: 50% monthly / 50% weekly

Grok 4.3xAIMost different

67.4/100

44same-round comparisonsEstablished sample

Gemini 3.1 ProGoogle

59.4/100

44same-round comparisonsEstablished sample

Grok 4.6xAI

59.1/100

44same-round comparisonsEstablished sample

Grok 4.5xAI

50.9/100

44same-round comparisonsEstablished sample

GPT-6 AstraOpenAI

48.6/100

16same-round comparisonsEstablished sample

Claude Fable 5.1Anthropic

46.9/100

18same-round comparisonsEstablished sample

Claude Opus 5AnthropicMost like the group

46.3/100

44same-round comparisonsEstablished sample

Model behavior patterns How do AI models allocate differently?

7 models

Claude Fable 5.1 Anthropic Tactical allocator Near peer mix2.8 holdings · 40% top66% turnoverNow: SPY 31%

Grok 4.5 xAI Peer-balanced allocator Near peer mix3.7 holdings · 35% top57% turnoverNow: IWN 18%

Grok 4.3 xAI Distinctive allocator Near peer mix3.1 holdings · 49% top55% turnoverNow: SPY 48%

Claude Opus 5 Anthropic Group-aligned allocator Near peer mix3.6 holdings · 36% top53% turnoverNow: SPY 22%

Gemini 3.1 Pro Google Distinctive allocator Near peer mix3.2 holdings · 40% top62% turnoverNow: ITA 20%

Grok 4.6 xAI Peer-balanced allocator Near peer mix2.2 holdings · 62% top55% turnoverNow: SPY 48%

GPT-6 Astra OpenAI Benchmark-anchored allocator S&P 500 core 33% · +16pp vs peers2.7 holdings · 45% top61% turnoverNow: SPY 35%

See full behavior

Performance by market

Who leads when markets rise or fall?

Monthly leaders vs. the S&P 500.

Monthly snapshot Updated Sep 25 4 of 5 market types comparable

Market fell S&P < -1.0%

Leader Grok 4.3

Average return -1.22%

Versus S&P 500 -1.90%

Market rose S&P > +1.0%

Leader Grok 4.5

Average return +4.11%

Versus S&P 500 +3.90%

Explore all market environments

AI positioning

What are AI models doing right now?

Live allocations before the next official score.

As of September 21, 2026

Current risk appetite As of September 21, 2026 72.5/100 Risk-seeking / Broad risk seeking

Consensus allocation As of September 21, 2026 41.8% S&P 500 (SPY) average live weight

Risk shift As of September 21, 2026 -8.1 Change vs Sep 16 portfolios

Model agreement As of September 21, 2026 Tight 3.5 point dispersion

Current risk appetite 72.5/100 As of September 21, 2026 / Risk-seeking

As of September 21, 2026 Broad risk seeking Combined view of monthly and weekly model portfolios for this date.

Unscored portfolios 73.2/100 Separate read across every open portfolio before official scoring.

Largest current allocations

S&P 500 (SPY) 41.8% Biotechnology (XBI) 12.5% Japan Equities (EWJ) 10.0% Metals and Mining (XME) 5.0% South Korea Equities (EWY) 5.0% Mexico Equities (EWW) 4.6%

Regime mix

Broad and cyclical equity 53.6% International equity 19.6% Growth and technology 12.5% Real assets and inflation 9.3% Defensive equity 2.5%

Inspect current frozen portfolios View historical risk trend

Benchmark insights

What do the latest AI decisions suggest?

The clearest signals from current portfolios and completed tests.

Current PositioningAs of Sep 21

Aggregate Live Allocation: +41.8%

SPY

Live AI portfolios are concentrated in S&P 500 (SPY)

Across the newest live weekly and monthly portfolios, S&P 500 (SPY) is the largest aggregate allocation at +41.79%.

Market EnvironmentAs of Sep 25

Down Leader Average Return: -1.22%

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.

Model BehaviorAs of Sep 21

Highest Combined Tilt: 34.8/100

Grok 4.3 follows recent winners most

Gemini 3.1 Pro has the lowest combined tilt at 7.7. Monthly and weekly behavior receive equal weight.

Trust and proof

What makes each model test comparable?

Same brief. Same choices. One response. No tools. Real market prices.

Step 1 Same report
Every model reads the same market report.
Step 2 Same choices
Every model chooses from the same 70 assets.
Step 3 One response, then locked
No browsing, tools, or follow-up prompts. The model's submitted portfolio is frozen before results are known.
Step 4 Fixed wait window
The frozen portfolio sits untouched for 7 days or 1 month.
Step 5 Prices score it
Real ending prices decide which model did best.

Evidence context

What evidence supports each score?

Equal-run rules, score scale, and audit context for monthly and weekly tracks.

Monthly benchmarkMore established

Evidence levelMore establishedMonthly evidence has enough completed rounds for stronger pattern reads, while still needing ongoing live validation.

Monthly evidence58 resolved rounds / 372 model resultsCurrent threshold met at 3+ rounds

Equal-run comparison7 models on the same 9 roundsRanked models are compared only on rounds every model in the roster completed.

ProtocolMixed protocolCompleted history includes 57 portfolio, 1 single-pick, and 0 unlabelled rounds.

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.

Weekly benchmarkMore established

Evidence levelMore establishedWeekly evidence has enough completed rounds for stronger pattern reads, while still needing ongoing live validation.

Weekly evidence71 resolved rounds / 468 model resultsCurrent threshold met at 6+ rounds

Equal-run comparison7 models on the same 7 roundsRanked 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.

Read full methodology See score methodology

Benchmark universe

What can models choose from?

The active roster, asset menu, horizons, and open rounds.

Models 12

Asset choices 70

Round lengths 2

Open rounds 15

Protocol Single-turn Non-agentic calls

Explore models View asset universe Open live dashboard

Latest official results

What happened in the latest scored rounds?

Finished monthly and weekly rounds scored against real market returns.

Monthly result1 of 58

Monthly official result

Monthly result scored Sep 25

Same-window returns, ranked after final prices.

Scored

Model portfolios S&P 500 benchmark Maximum possible return

GPT-5.6 Sol

Claude Fable 5

Grok 4.3

Claude Opus 5

Grok 4.6

Grok 4.5

Gemini 3.1 Pro

S&P 500

USO Crude Oil

GPT-5.6 Sol OpenAI

3.57%

Claude Fable 5 Anthropic

0.13%

Grok 4.3 xAI

-3.70%

Claude Opus 5 Anthropic

-4.80%

Grok 4.6 xAI

-6.35%

Grok 4.5 xAI

-6.41%

Gemini 3.1 Pro Google

-9.47%

S&P 500 Benchmark

0.69%

USO Crude Oil - Hindsight best asset

16.47%

Portfolio context

Shows each model's saved portfolio weights.

Model portfolios

Ranked in the same order as the chart.

GPT-5.6 Sol OpenAI

Semiconductors (SMH) 35% Cybersecurity (CIBR) 35% Real Estate (XLRE) 30%

Claude Fable 5 Anthropic

Semiconductors (SMH) 35% Regional Banks (KRE) 35% Industrials (XLI) 30%

Grok 4.3 xAI

US Dollar (UUP) 35% Small Value (IWN) 35% Utilities (XLU) 30%

Claude Opus 5 Anthropic

Industrials (XLI) 35% Regional Banks (KRE) 35% Small Value (IWN) 30%

Grok 4.6 xAI

Defense (ITA) 35% Utilities (XLU) 35% S&P 500 (SPY) 30%

Grok 4.5 xAI

Defense (ITA) 35% Regional Banks (KRE) 35% Industrials (XLI) 30%

Gemini 3.1 Pro Google

Solar (TAN) 35% Utilities (XLU) 35% Defense (ITA) 30%

Reference points

Not model portfolios.

S&P 500 Benchmark

Benchmark return over the same scoring window

USO Crude Oil - Hindsight best asset

100% Crude Oil (USO) hindsight ceiling

Official scored round

Monthly result scored Sep 25

Audit ID: CB-2026-08-25-1M

Audit packet Track results

ScoredSep 25WindowAug 26 to Sep 25Models7Asset choices70LeaderGPT-5.6 SolHorizonMonthly

Monthly official result

Monthly result scored Sep 25

Same-window returns, ranked after final prices.

Scored

Model portfolios S&P 500 benchmark Maximum possible return

Claude Fable 5

Grok 4.3

Claude Opus 5

GPT-5.6 Sol

Gemini 3.1 Pro

Grok 4.5

Grok 4.6

S&P 500

USO Crude Oil

Claude Fable 5 Anthropic

11.68%

Grok 4.3 xAI

5.52%

Claude Opus 5 Anthropic

1.67%

GPT-5.6 Sol OpenAI

0.34%

Gemini 3.1 Pro Google

-0.27%

Grok 4.5 xAI

-2.50%

Grok 4.6 xAI

-3.39%

S&P 500 Benchmark

0.71%

USO Crude Oil - Hindsight best asset

17.58%

Portfolio context

Shows each model's saved portfolio weights.

Model portfolios

Ranked in the same order as the chart.

Claude Fable 5 Anthropic

Semiconductors (SMH) 35% Cybersecurity (CIBR) 35% Crude Oil (USO) 30%

Grok 4.3 xAI

Crude Oil (USO) 35% US Dollar (UUP) 35% Small Value (IWN) 30%

Claude Opus 5 Anthropic

Semiconductors (SMH) 35% Small Value (IWN) 35% S&P 500 (SPY) 30%

GPT-5.6 Sol OpenAI

Small Value (IWN) 35% Semiconductors (SMH) 35% Regional Banks (KRE) 30%

Gemini 3.1 Pro Google

Semiconductors (SMH) 35% Small Value (IWN) 35% Small Cap (IWM) 30%

Grok 4.5 xAI

Semiconductors (SMH) 35% Utilities (XLU) 35% Defense (ITA) 30%

Grok 4.6 xAI

Utilities (XLU) 35% Defense (ITA) 35% Semiconductors (SMH) 30%

Reference points

Not model portfolios.

S&P 500 Benchmark

Benchmark return over the same scoring window

USO Crude Oil - Hindsight best asset

100% Crude Oil (USO) hindsight ceiling

Official scored round

Monthly result scored Sep 25

Audit ID: CB-2026-08-24-1M

Audit packet Track results

ScoredSep 25WindowAug 25 to Sep 25Models7Asset choices70LeaderClaude Fable 5HorizonMonthly

Monthly official result

Monthly result scored Sep 18

Same-window returns, ranked after final prices.

Scored

Model portfolios S&P 500 benchmark Maximum possible return

Claude Opus 4.8

Grok 4.6

Grok 4.3

Grok 4.5

Claude Opus 5

GPT-5.6 Sol

Gemini 3.1 Pro

Claude Fable 5

S&P 500

ETHA Ethereum ETF

Claude Opus 4.8 Anthropic

-0.75%

Grok 4.6 xAI

-0.75%

Grok 4.3 xAI

-2.72%

Grok 4.5 xAI

-3.07%

Claude Opus 5 Anthropic

-3.29%

GPT-5.6 Sol OpenAI

-4.03%

Gemini 3.1 Pro Google

-4.10%

Claude Fable 5 Anthropic

-5.06%

S&P 500 Benchmark

-0.75%

ETHA Ethereum ETF - Hindsight best asset

37.95%

Portfolio context

Shows each model's saved portfolio weights.

Model portfolios

Ranked in the same order as the chart.

Claude Opus 4.8 Anthropic

S&P 500 (SPY) 100%

Grok 4.6 xAI

S&P 500 (SPY) 100%

Grok 4.3 xAI

Long Treasury (TLT) 35% Utilities (XLU) 35% S&P 500 (SPY) 30%

Grok 4.5 xAI

Regional Banks (KRE) 35% Long Treasury (TLT) 35% Financials (XLF) 30%

Claude Opus 5 Anthropic

Regional Banks (KRE) 35% Financials (XLF) 35% S&P 500 (SPY) 30%

GPT-5.6 Sol OpenAI

Long Treasury (TLT) 35% Regional Banks (KRE) 35% Utilities (XLU) 30%

Gemini 3.1 Pro Google

Utilities (XLU) 35% Long Treasury (TLT) 35% Regional Banks (KRE) 30%

Claude Fable 5 Anthropic

Regional Banks (KRE) 35% Financials (XLF) 35% Utilities (XLU) 30%

Reference points

Not model portfolios.

S&P 500 Benchmark

Benchmark return over the same scoring window

ETHA Ethereum ETF - Hindsight best asset

100% Ethereum ETF (ETHA) hindsight ceiling

Official scored round

Monthly result scored Sep 18

Audit ID: CB-2026-08-18-1M

Audit packet Track results

ScoredSep 18WindowAug 18 to Sep 18Models8Asset choices70LeaderClaude Opus 4.8HorizonMonthly

Monthly official result

Monthly result scored Sep 17

Same-window returns, ranked after final prices.

Scored

Model portfolios S&P 500 benchmark Maximum possible return

Gemini 3.1 Pro

Claude Opus 4.8

Grok 4.3

Grok 4.5

Grok 4.6

Claude Opus 5

GPT-5.6 Sol

Claude Fable 5

S&P 500

ETHA Ethereum ETF

Gemini 3.1 Pro Google

-0.36%

Claude Opus 4.8 Anthropic

-1.30%

Grok 4.3 xAI

-1.30%

Grok 4.5 xAI

-1.30%

Grok 4.6 xAI

-1.30%

Claude Opus 5 Anthropic

-4.04%

GPT-5.6 Sol OpenAI

-4.67%

Claude Fable 5 Anthropic

-4.74%

S&P 500 Benchmark

-1.30%

ETHA Ethereum ETF - Hindsight best asset

28.26%

Portfolio context

Shows each model's saved portfolio weights.

Model portfolios

Ranked in the same order as the chart.

Gemini 3.1 Pro Google

Japanese Yen (FXY) 35% Long Treasury (TLT) 35% Small Value (IWN) 30%

Claude Opus 4.8 Anthropic

S&P 500 (SPY) 100%

Grok 4.3 xAI

S&P 500 (SPY) 100%

Grok 4.5 xAI

S&P 500 (SPY) 100%

Grok 4.6 xAI

S&P 500 (SPY) 100%

Claude Opus 5 Anthropic

Small Cap (IWM) 35% Small Value (IWN) 35% S&P 500 (SPY) 30%

GPT-5.6 Sol OpenAI

Small Value (IWN) 35% Real Estate (XLRE) 35% Utilities (XLU) 30%

Claude Fable 5 Anthropic

Small Value (IWN) 35% Utilities (XLU) 35% Real Estate (XLRE) 30%

Reference points

Not model portfolios.

S&P 500 Benchmark

Benchmark return over the same scoring window

ETHA Ethereum ETF - Hindsight best asset

100% Ethereum ETF (ETHA) hindsight ceiling

Official scored round

Monthly result scored Sep 17

Audit ID: CB-2026-08-15-1M

Audit packet Track results

ScoredSep 17WindowAug 17 to Sep 17Models8Asset choices70LeaderGemini 3.1 ProHorizonMonthly

Monthly official result

Monthly result scored Sep 14

Same-window returns, ranked after final prices.

Scored

Model portfolios S&P 500 benchmark Maximum possible return

Grok 4.5

Grok 4.6

Gemini 3.1 Pro

Grok 4.3

Claude Fable 5

Claude Opus 5

Claude Opus 4.8

GPT-5.6 Sol

S&P 500

ETHA Ethereum ETF

Grok 4.5 xAI

1.13%

Grok 4.6 xAI

0.90%

Gemini 3.1 Pro Google

0.23%

Grok 4.3 xAI

0.01%

Claude Fable 5 Anthropic

-0.66%

Claude Opus 5 Anthropic

-1.16%

Claude Opus 4.8 Anthropic

-1.31%

GPT-5.6 Sol OpenAI

-4.10%

S&P 500 Benchmark

-2.19%

ETHA Ethereum ETF - Hindsight best asset

34.72%

Portfolio context

Shows each model's saved portfolio weights.

Model portfolios

Ranked in the same order as the chart.

Grok 4.5 xAI

Energy (XLE) 30% Healthcare (XLV) 25% Software (IGV) 20% S&P 500 (SPY) 25%

Grok 4.6 xAI

Energy (XLE) 30% Healthcare (XLV) 25% Cybersecurity (CIBR) 25% Japan (EWJ) 20%

Gemini 3.1 Pro Google

S&P 500 (SPY) 50% Healthcare (XLV) 25% Energy (XLE) 25%

Grok 4.3 xAI

S&P 500 (SPY) 40% Energy (XLE) 20% Healthcare (XLV) 20% Japan (EWJ) 20%

Claude Fable 5 Anthropic

S&P 500 (SPY) 30% Value (IWD) 20% Equal-Weight S&P 500 (RSP) 15% Healthcare (XLV) 20% Energy (XLE) 15%

Claude Opus 5 Anthropic

S&P 500 (SPY) 40% Healthcare (XLV) 20% Equal-Weight S&P 500 (RSP) 20% Energy (XLE) 10% Japan (EWJ) 10%

Claude Opus 4.8 Anthropic

S&P 500 (SPY) 40% Healthcare (XLV) 25% Gold (IAU) 20% Dividend (SCHD) 15%

GPT-5.6 Sol OpenAI

Semiconductors (SMH) 35% Cybersecurity (CIBR) 15% Healthcare (XLV) 25% Equal-Weight S&P 500 (RSP) 25%

Reference points

Not model portfolios.

S&P 500 Benchmark

Benchmark return over the same scoring window

ETHA Ethereum ETF - Hindsight best asset

100% Ethereum ETF (ETHA) hindsight ceiling

Official scored round

Monthly result scored Sep 14

Audit ID: CB-2026-08-13-1M

Audit packet Track results

ScoredSep 14WindowAug 13 to Sep 14Models8Asset choices70LeaderGrok 4.5HorizonMonthly

Monthly official result

Monthly result scored Sep 11

Same-window returns, ranked after final prices.

Scored

Model portfolios S&P 500 benchmark Maximum possible return

Grok 4.5

Gemini 3.1 Pro

GPT-5.5

Grok 4.3

Claude Fable 5

Claude Opus 5

Claude Opus 4.8

GPT-5.6 Sol

S&P 500

ETHA Ethereum ETF

Grok 4.5 xAI

8.24%

Gemini 3.1 Pro Google

5.71%

GPT-5.5 OpenAI

2.23%

Grok 4.3 xAI

1.59%

Claude Fable 5 Anthropic

1.55%

Claude Opus 5 Anthropic

0.44%

Claude Opus 4.8 Anthropic

-0.98%

GPT-5.6 Sol OpenAI

-3.35%

S&P 500 Benchmark

-0.81%

ETHA Ethereum ETF - Hindsight best asset

35.12%

Portfolio context

Shows each model's saved portfolio weights.

Model portfolios

Ranked in the same order as the chart.

Grok 4.5 xAI

Crude Oil (USO) 40% Energy (XLE) 10% Software (IGV) 30% Healthcare (XLV) 20%

Gemini 3.1 Pro Google

Gold (IAU) 40% Crude Oil (USO) 30% Healthcare (XLV) 30%

GPT-5.5 OpenAI

Semiconductors (SMH) 30% Cybersecurity (CIBR) 20% Crude Oil (USO) 20% Biotechnology (XBI) 15% Metals and Mining (XME) 15%

Grok 4.3 xAI

S&P 500 (SPY) 60% Energy (XLE) 25% Japan (EWJ) 15%

Claude Fable 5 Anthropic

Energy (XLE) 30% Gold (IAU) 25% Value (IWD) 20% S&P 500 (SPY) 25%

Claude Opus 5 Anthropic

S&P 500 (SPY) 40% Energy (XLE) 20% Healthcare (XLV) 20% Canada (EWC) 20%

Claude Opus 4.8 Anthropic

S&P 500 (SPY) 40% Healthcare (XLV) 25% Financials (XLF) 20% Dividend (SCHD) 15%

GPT-5.6 Sol OpenAI

Cybersecurity (CIBR) 50% Biotechnology (XBI) 50%

Reference points

Not model portfolios.

S&P 500 Benchmark

Benchmark return over the same scoring window

ETHA Ethereum ETF - Hindsight best asset

100% Ethereum ETF (ETHA) hindsight ceiling

Official scored round

Monthly result scored Sep 11

Audit ID: CB-2026-08-11-1M

Audit packet Track results

ScoredSep 11WindowAug 11 to Sep 11Models8Asset choices70LeaderGrok 4.5HorizonMonthly

Monthly official result

Monthly result scored Sep 10

Same-window returns, ranked after final prices.

Scored

Model portfolios S&P 500 benchmark Maximum possible return

GPT-5.5

GPT-5.6 Sol

Gemini 3.1 Pro

Grok 4.5

Claude Fable 5

Claude Opus 5

Grok 4.3

Claude Opus 4.8

S&P 500

ETHA Ethereum ETF

GPT-5.5 OpenAI

5.72%

GPT-5.6 Sol OpenAI

4.54%

Gemini 3.1 Pro Google

-1.32%

Grok 4.5 xAI

-1.50%

Claude Fable 5 Anthropic

-1.79%

Claude Opus 5 Anthropic

-1.88%

Grok 4.3 xAI

-1.97%

Claude Opus 4.8 Anthropic

-2.16%

S&P 500 Benchmark

-1.97%

ETHA Ethereum ETF - Hindsight best asset

31.26%

Portfolio context

Shows each model's saved portfolio weights.

Model portfolios

Ranked in the same order as the chart.

GPT-5.5 OpenAI

Semiconductors (SMH) 35% Biotechnology (XBI) 25% Taiwan (EWT) 20% Crude Oil (USO) 20%

GPT-5.6 Sol OpenAI

Biotechnology (XBI) 30% Cybersecurity (CIBR) 25% Crude Oil (USO) 25% US Dollar (UUP) 20%

Gemini 3.1 Pro Google

Semiconductors (SMH) 40% Biotechnology (XBI) 30% Gold (IAU) 30%

Grok 4.5 xAI

S&P 500 (SPY) 40% Semiconductors (SMH) 30% Biotechnology (XBI) 30%

Claude Fable 5 Anthropic

Semiconductors (SMH) 25% Software (IGV) 15% Gold (IAU) 20% Biotechnology (XBI) 20% S&P 500 (SPY) 20%

Claude Opus 5 Anthropic

S&P 500 (SPY) 40% Gold (IAU) 20% Biotechnology (XBI) 20% Equal-Weight S&P 500 (RSP) 20%

Grok 4.3 xAI

S&P 500 (SPY) 100%

Claude Opus 4.8 Anthropic

S&P 500 (SPY) 45% Biotechnology (XBI) 25% Software (IGV) 30%

Reference points

Not model portfolios.

S&P 500 Benchmark

Benchmark return over the same scoring window

ETHA Ethereum ETF - Hindsight best asset

100% Ethereum ETF (ETHA) hindsight ceiling

Official scored round

Monthly result scored Sep 10

Audit ID: CB-2026-08-09-1M

Audit packet Track results

ScoredSep 10WindowAug 10 to Sep 10Models8Asset choices70LeaderGPT-5.5HorizonMonthly

Monthly official result

Monthly result scored Sep 8

Same-window returns, ranked after final prices.

Scored

Model portfolios S&P 500 benchmark Maximum possible return

Grok 4.5

Grok 4.3

Gemini 3.1 Pro

Claude Opus 4.8

Claude Fable 5

Claude Opus 5

GPT-5.5

GPT-5.6 Sol

S&P 500

ETHA Ethereum ETF

Grok 4.5 xAI

1.53%

Grok 4.3 xAI

0.68%

Gemini 3.1 Pro Google

-0.27%

Claude Opus 4.8 Anthropic

-0.61%

Claude Fable 5 Anthropic

-0.79%

Claude Opus 5 Anthropic

-2.50%

GPT-5.5 OpenAI

-3.24%

GPT-5.6 Sol OpenAI

-3.96%

S&P 500 Benchmark

-0.94%

ETHA Ethereum ETF - Hindsight best asset

29.37%

Portfolio context

Shows each model's saved portfolio weights.

Model portfolios

Ranked in the same order as the chart.

Grok 4.5 xAI

Semiconductors (SMH) 30% Biotechnology (XBI) 25% Taiwan (EWT) 25% Cybersecurity (CIBR) 20%

Grok 4.3 xAI

Semiconductors (SMH) 50% Biotechnology (XBI) 50%

Gemini 3.1 Pro Google

S&P 500 (SPY) 50% Technology (XLK) 25% Healthcare (XLV) 25%

Claude Opus 4.8 Anthropic

S&P 500 (SPY) 50% Software (IGV) 25% Financials (XLF) 25%

Claude Fable 5 Anthropic

Semiconductors (SMH) 30% Momentum (MTUM) 25% Utilities (XLU) 25% S&P 500 (SPY) 20%

Claude Opus 5 Anthropic

S&P 500 (SPY) 40% Financials (XLF) 20% Cybersecurity (CIBR) 20% Defense (ITA) 10% Equal-Weight S&P 500 (RSP) 10%

GPT-5.5 OpenAI

Semiconductors (SMH) 30% Cybersecurity (CIBR) 20% Defense (ITA) 20% Financials (XLF) 15% Copper (CPER) 15%

GPT-5.6 Sol OpenAI

Cybersecurity (CIBR) 40% Biotechnology (XBI) 30% Defense (ITA) 30%

Reference points

Not model portfolios.

S&P 500 Benchmark

Benchmark return over the same scoring window

ETHA Ethereum ETF - Hindsight best asset

100% Ethereum ETF (ETHA) hindsight ceiling

Official scored round

Monthly result scored Sep 8

Audit ID: CB-2026-08-07-1M

Audit packet Track results

ScoredSep 8WindowAug 7 to Sep 8Models8Asset choices70LeaderGrok 4.5HorizonMonthly

Monthly official result

Monthly result scored Sep 4

Same-window returns, ranked after final prices.

Scored

Model portfolios S&P 500 benchmark Maximum possible return

Claude Fable 5

Grok 4.5

GPT-5.5

GPT-5.6 Sol

Claude Opus 5

Gemini 3.1 Pro

Grok 4.3

Claude Opus 4.8

S&P 500

ETHA Ethereum ETF

Claude Fable 5 Anthropic

4.16%

Grok 4.5 xAI

3.70%

GPT-5.5 OpenAI

3.62%

GPT-5.6 Sol OpenAI

3.29%

Claude Opus 5 Anthropic

0.88%

Gemini 3.1 Pro Google

0.21%

Grok 4.3 xAI

0.05%

Claude Opus 4.8 Anthropic

-0.94%

S&P 500 Benchmark

0.05%

ETHA Ethereum ETF - Hindsight best asset

27.90%

Portfolio context

Shows each model's saved portfolio weights.

Model portfolios

Ranked in the same order as the chart.

Claude Fable 5 Anthropic

Semiconductors (SMH) 25% Software (IGV) 25% Taiwan (EWT) 20% Biotechnology (XBI) 20% S&P 500 (SPY) 10%

Grok 4.5 xAI

Semiconductors (SMH) 30% Biotechnology (XBI) 25% Taiwan (EWT) 20% S&P 500 (SPY) 25%

GPT-5.5 OpenAI

Biotechnology (XBI) 30% Semiconductors (SMH) 25% Taiwan (EWT) 20% Cybersecurity (CIBR) 15% Financials (XLF) 10%

GPT-5.6 Sol OpenAI

Semiconductors (SMH) 50% Biotechnology (XBI) 50%

Claude Opus 5 Anthropic

S&P 500 (SPY) 40% Healthcare (XLV) 20% Financials (XLF) 20% Equal-Weight S&P 500 (RSP) 20%

Gemini 3.1 Pro Google

Technology (XLK) 30% Industrials (XLI) 30% Gold (IAU) 20% Healthcare (XLV) 20%

Grok 4.3 xAI

S&P 500 (SPY) 100%

Claude Opus 4.8 Anthropic

S&P 500 (SPY) 50% Technology (XLK) 30% Industrials (XLI) 20%

Reference points

Not model portfolios.

S&P 500 Benchmark

Benchmark return over the same scoring window

ETHA Ethereum ETF - Hindsight best asset

100% Ethereum ETF (ETHA) hindsight ceiling

Official scored round

Monthly result scored Sep 4

Audit ID: CB-2026-08-05-1M

Audit packet Track results

ScoredSep 4WindowAug 5 to Sep 4Models8Asset choices70LeaderClaude Fable 5HorizonMonthly

Monthly official result

Monthly result scored Sep 4

Same-window returns, ranked after final prices.

Scored

Model portfolios S&P 500 benchmark Maximum possible return

Gemini 3.1 Pro

GPT-5.5

Claude Fable 5

Grok 4.5

Claude Opus 5

Grok 4.3

GPT-5.6 Sol

Claude Opus 4.8

S&P 500

ETHA Ethereum ETF

Gemini 3.1 Pro Google

5.54%

GPT-5.5 OpenAI

4.84%

Claude Fable 5 Anthropic

2.93%

Grok 4.5 xAI

2.22%

Claude Opus 5 Anthropic

1.10%

Grok 4.3 xAI

0.82%

GPT-5.6 Sol OpenAI

0.71%

Claude Opus 4.8 Anthropic

-2.42%

S&P 500 Benchmark

-0.15%

ETHA Ethereum ETF - Hindsight best asset

30.88%

Portfolio context

Shows each model's saved portfolio weights.

Model portfolios

Ranked in the same order as the chart.

Gemini 3.1 Pro Google

Technology (XLK) 40% Energy (XLE) 30% Gold (IAU) 30%

GPT-5.5 OpenAI

Semiconductors (SMH) 35% Cybersecurity (CIBR) 15% Taiwan (EWT) 25% Biotechnology (XBI) 15% Crude Oil (USO) 10%

Claude Fable 5 Anthropic

S&P 500 (SPY) 40% Semiconductors (SMH) 25% Taiwan (EWT) 20% Energy (XLE) 15%

Grok 4.5 xAI

Software (IGV) 35% Cybersecurity (CIBR) 15% Energy (XLE) 20% S&P 500 (SPY) 30%

Claude Opus 5 Anthropic

S&P 500 (SPY) 40% Biotechnology (XBI) 20% Cybersecurity (CIBR) 15% Value (IWD) 15% Financials (XLF) 10%

Grok 4.3 xAI

S&P 500 (SPY) 40% Technology (XLK) 30% Japan (EWJ) 20% Value (IWD) 10%

GPT-5.6 Sol OpenAI

Cybersecurity (CIBR) 30% Biotechnology (XBI) 25% Japan (EWJ) 25% Industrials (XLI) 20%

Claude Opus 4.8 Anthropic

S&P 500 (SPY) 50% Cybersecurity (CIBR) 25% Industrials (XLI) 25%

Reference points

Not model portfolios.

S&P 500 Benchmark

Benchmark return over the same scoring window

ETHA Ethereum ETF - Hindsight best asset

100% Ethereum ETF (ETHA) hindsight ceiling

Official scored round

Monthly result scored Sep 4

Audit ID: CB-2026-08-04-1M

Audit packet Track results

ScoredSep 4WindowAug 4 to Sep 4Models8Asset choices70LeaderGemini 3.1 ProHorizonMonthly

Monthly official result

Monthly result scored Aug 31

Same-window returns, ranked after final prices.

Scored

Model portfolios S&P 500 benchmark Maximum possible return

Grok 4.5

GPT-5.6 Sol

GPT-5.5

Claude Fable 5

Gemini 3.1 Pro

Grok 4.3

Claude Opus 5

Claude Opus 4.8

S&P 500

ETHA Ethereum ETF

Grok 4.5 xAI

6.49%

GPT-5.6 Sol OpenAI

4.63%

GPT-5.5 OpenAI

3.94%

Claude Fable 5 Anthropic

3.87%

Gemini 3.1 Pro Google

3.07%

Grok 4.3 xAI

2.68%

Claude Opus 5 Anthropic

2.47%

Claude Opus 4.8 Anthropic

2.43%

S&P 500 Benchmark

2.68%

ETHA Ethereum ETF - Hindsight best asset

33.05%

Portfolio context

Shows each model's saved portfolio weights.

Model portfolios

Ranked in the same order as the chart.

Grok 4.5 xAI

Energy (XLE) 25% Crude Oil (USO) 25% Software (IGV) 20% Financials (XLF) 15% Value (IWD) 15%

GPT-5.6 Sol OpenAI

Value (IWD) 30% Cybersecurity (CIBR) 25% Energy (XLE) 25% Japanese Yen (FXY) 20%

GPT-5.5 OpenAI

Value (IWD) 25% Cybersecurity (CIBR) 25% Crude Oil (USO) 25% Europe (VGK) 25%

Claude Fable 5 Anthropic

S&P 500 (SPY) 25% Value (IWD) 20% Dividend (SCHD) 15% Energy (XLE) 25% Equal-Weight S&P 500 (RSP) 15%

Gemini 3.1 Pro Google

S&P 500 (SPY) 50% Value (IWD) 25% Healthcare (XLV) 25%

Grok 4.3 xAI

S&P 500 (SPY) 100%

Claude Opus 5 Anthropic

S&P 500 (SPY) 35% Financials (XLF) 20% Value (IWD) 20% Healthcare (XLV) 15% Europe (VGK) 10%

Claude Opus 4.8 Anthropic

Financials (XLF) 30% Value (IWD) 25% Dividend (SCHD) 20% S&P 500 (SPY) 25%

Reference points

Not model portfolios.

S&P 500 Benchmark

Benchmark return over the same scoring window

ETHA Ethereum ETF - Hindsight best asset

100% Ethereum ETF (ETHA) hindsight ceiling

Official scored round

Monthly result scored Aug 31

Audit ID: CB-2026-07-31-1M

Audit packet Track results

ScoredAug 31WindowJul 31 to Aug 31Models8Asset choices70LeaderGrok 4.5HorizonMonthly

Monthly official result

Monthly result scored Aug 28

Same-window returns, ranked after final prices.

Scored

Model portfolios S&P 500 benchmark Maximum possible return

Grok 4.5

GPT-5.6 Sol

Gemini 3.1 Pro

Grok 4.3

Claude Opus 5

Claude Opus 4.8

Claude Fable 5

GPT-5.5

S&P 500

ETHA Ethereum ETF

Grok 4.5 xAI

7.24%

GPT-5.6 Sol OpenAI

5.06%

Gemini 3.1 Pro Google

3.47%

Grok 4.3 xAI

3.42%

Claude Opus 5 Anthropic

3.19%

Claude Opus 4.8 Anthropic

3.06%

Claude Fable 5 Anthropic

2.67%

GPT-5.5 OpenAI

2.50%

S&P 500 Benchmark

3.73%

ETHA Ethereum ETF - Hindsight best asset

26.60%

Portfolio context

Shows each model's saved portfolio weights.

Model portfolios

Ranked in the same order as the chart.

Grok 4.5 xAI

Software (IGV) 35% Financials (XLF) 30% Europe (VGK) 20% Equal-Weight S&P 500 (RSP) 15%

GPT-5.6 Sol OpenAI

Equal-Weight S&P 500 (RSP) 35% Cybersecurity (CIBR) 30% Biotechnology (XBI) 20% Japanese Yen (FXY) 15%

Gemini 3.1 Pro Google

S&P 500 (SPY) 40% Financials (XLF) 30% Healthcare (XLV) 30%

Grok 4.3 xAI

S&P 500 (SPY) 40% Value (IWD) 20% Financials (XLF) 20% Healthcare (XLV) 20%

Claude Opus 5 Anthropic

S&P 500 (SPY) 40% Equal-Weight S&P 500 (RSP) 25% Financials (XLF) 20% Healthcare (XLV) 15%

Claude Opus 4.8 Anthropic

Financials (XLF) 30% Dividend (SCHD) 25% Equal-Weight S&P 500 (RSP) 25% S&P 500 (SPY) 20%

Claude Fable 5 Anthropic

Semiconductors (SMH) 25% Equal-Weight S&P 500 (RSP) 30% Value (IWD) 20% Financials (XLF) 15% S&P 500 (SPY) 10%

GPT-5.5 OpenAI

Equal-Weight S&P 500 (RSP) 35% Financials (XLF) 25% Europe (VGK) 20% Healthcare (XLV) 20%

Reference points

Not model portfolios.

S&P 500 Benchmark

Benchmark return over the same scoring window

ETHA Ethereum ETF - Hindsight best asset

100% Ethereum ETF (ETHA) hindsight ceiling

Official scored round

Monthly result scored Aug 28

Audit ID: CB-2026-07-30-1M

Audit packet Track results

ScoredAug 28WindowJul 30 to Aug 28Models8Asset choices70LeaderGrok 4.5HorizonMonthly

Monthly official result

Monthly result scored Aug 28

Same-window returns, ranked after final prices.

Scored

Model portfolios S&P 500 benchmark Maximum possible return

Claude Fable 5

Grok 4.5

Claude Opus 4.8

Gemini 3.1 Pro

GPT-5.5

Claude Opus 5

Grok 4.3

GPT-5.6 Sol

S&P 500

ETHA Ethereum ETF

Claude Fable 5 Anthropic

3.90%

Grok 4.5 xAI

3.72%

Claude Opus 4.8 Anthropic

3.41%

Gemini 3.1 Pro Google

3.06%

GPT-5.5 OpenAI

2.38%

Claude Opus 5 Anthropic

2.30%

Grok 4.3 xAI

1.56%

GPT-5.6 Sol OpenAI

0.73%

S&P 500 Benchmark

5.47%

ETHA Ethereum ETF - Hindsight best asset

29.00%

Portfolio context

Shows each model's saved portfolio weights.

Model portfolios

Ranked in the same order as the chart.

Claude Fable 5 Anthropic

Value (IWD) 25% Equal-Weight S&P 500 (RSP) 25% Healthcare (XLV) 20% Energy (XLE) 15% S&P 500 (SPY) 15%

Grok 4.5 xAI

Healthcare (XLV) 30% Value (IWD) 25% Equal-Weight S&P 500 (RSP) 25% Energy (XLE) 20%

Claude Opus 4.8 Anthropic

Dividend (SCHD) 30% Financials (XLF) 25% Healthcare (XLV) 25% S&P 500 (SPY) 20%

Gemini 3.1 Pro Google

Dividend (SCHD) 50% Healthcare (XLV) 50%

GPT-5.5 OpenAI

Equal-Weight S&P 500 (RSP) 25% Dividend (SCHD) 25% Healthcare (XLV) 20% Financials (XLF) 15% Crude Oil (USO) 15%

Claude Opus 5 Anthropic

Equal-Weight S&P 500 (RSP) 30% Financials (XLF) 20% Healthcare (XLV) 20% Dividend (SCHD) 15% Crude Oil (USO) 15%

Grok 4.3 xAI

Dividend (SCHD) 25% Healthcare (XLV) 25% Staples (XLP) 25% Equal-Weight S&P 500 (RSP) 25%

GPT-5.6 Sol OpenAI

Equal-Weight S&P 500 (RSP) 35% Healthcare (XLV) 25% Real Estate (XLRE) 20% US Dollar (UUP) 20%

Reference points

Not model portfolios.

S&P 500 Benchmark

Benchmark return over the same scoring window

ETHA Ethereum ETF - Hindsight best asset

100% Ethereum ETF (ETHA) hindsight ceiling

Official scored round

Monthly result scored Aug 28

Audit ID: CB-2026-07-29-1M

Audit packet Track results

ScoredAug 28WindowJul 29 to Aug 28Models8Asset choices70LeaderClaude Fable 5HorizonMonthly

Monthly official result

Monthly result scored Aug 28

Same-window returns, ranked after final prices.

Scored

Model portfolios S&P 500 benchmark Maximum possible return

GPT-5.6 Sol

Claude Opus 5

Claude Opus 4.8

Claude Fable 5

Grok 4.3

GPT-5.5

Grok 4.5

Gemini 3.1 Pro

S&P 500

ETHA Ethereum ETF

GPT-5.6 Sol OpenAI

3.07%

Claude Opus 5 Anthropic

2.90%

Claude Opus 4.8 Anthropic

2.16%

Claude Fable 5 Anthropic

2.07%

Grok 4.3 xAI

1.19%

GPT-5.5 OpenAI

0.86%

Grok 4.5 xAI

0.10%

Gemini 3.1 Pro Google

-1.32%

S&P 500 Benchmark

3.85%

ETHA Ethereum ETF - Hindsight best asset

26.78%

Portfolio context

Shows each model's saved portfolio weights.

Model portfolios

Ranked in the same order as the chart.

GPT-5.6 Sol OpenAI

Equal-Weight S&P 500 (RSP) 40% Healthcare (XLV) 30% Nasdaq 100 (QQQ) 30%

Claude Opus 5 Anthropic

Equal-Weight S&P 500 (RSP) 30% Financials (XLF) 20% Healthcare (XLV) 20% S&P 500 (SPY) 20% Gold (IAU) 10%

Claude Opus 4.8 Anthropic

Financials (XLF) 30% Healthcare (XLV) 30% Value (IWD) 25% S&P 500 (SPY) 15%

Claude Fable 5 Anthropic

Equal-Weight S&P 500 (RSP) 25% Value (IWD) 25% Financials (XLF) 20% Healthcare (XLV) 15% S&P 500 (SPY) 15%

Grok 4.3 xAI

S&P 500 (SPY) 40% Healthcare (XLV) 20% Financials (XLF) 20% Defense (ITA) 20%

GPT-5.5 OpenAI

Equal-Weight S&P 500 (RSP) 30% Dividend (SCHD) 20% Healthcare (XLV) 20% Financials (XLF) 15% Defense (ITA) 15%

Grok 4.5 xAI

Financials (XLF) 30% Healthcare (XLV) 25% Defense (ITA) 25% Value (IWD) 20%

Gemini 3.1 Pro Google

Defense (ITA) 50% Healthcare (XLV) 50%

Reference points

Not model portfolios.

S&P 500 Benchmark

Benchmark return over the same scoring window

ETHA Ethereum ETF - Hindsight best asset

100% Ethereum ETF (ETHA) hindsight ceiling

Official scored round

Monthly result scored Aug 28

Audit ID: CB-2026-07-28-1M

Audit packet Track results

ScoredAug 28WindowJul 28 to Aug 28Models8Asset choices70LeaderGPT-5.6 SolHorizonMonthly

Monthly official result

Monthly result scored Aug 27

Same-window returns, ranked after final prices.

Scored

Model portfolios S&P 500 benchmark Maximum possible return

Gemini 3.1 Pro

GPT-5.6 Sol

Claude Opus 5

Grok 4.5

Grok 4.3

Claude Opus 4.8

Claude Fable 5

GPT-5.5

S&P 500

ETHA Ethereum ETF

Gemini 3.1 Pro Google

5.91%

GPT-5.6 Sol OpenAI

3.89%

Claude Opus 5 Anthropic

3.87%

Grok 4.5 xAI

3.71%

Grok 4.3 xAI

3.70%

Claude Opus 4.8 Anthropic

3.69%

Claude Fable 5 Anthropic

3.20%

GPT-5.5 OpenAI

2.49%

S&P 500 Benchmark

4.33%

ETHA Ethereum ETF - Hindsight best asset

28.28%

Portfolio context

Shows each model's saved portfolio weights.

Model portfolios

Ranked in the same order as the chart.

Gemini 3.1 Pro Google

Healthcare (XLV) 30% Industrials (XLI) 30% Gold (IAU) 40%

GPT-5.6 Sol OpenAI

Equal-Weight S&P 500 (RSP) 50% Healthcare (XLV) 25% Japan (EWJ) 25%

Claude Opus 5 Anthropic

Equal-Weight S&P 500 (RSP) 30% Healthcare (XLV) 20% Financials (XLF) 20% Dividend (SCHD) 15% Energy (XLE) 15%

Grok 4.5 xAI

Financials (XLF) 35% Healthcare (XLV) 30% Equal-Weight S&P 500 (RSP) 20% Energy (XLE) 15%

Grok 4.3 xAI

Dividend (SCHD) 40% Healthcare (XLV) 30% Financials (XLF) 30%

Claude Opus 4.8 Anthropic

Financials (XLF) 30% Healthcare (XLV) 25% Dividend (SCHD) 25% S&P 500 (SPY) 20%

Claude Fable 5 Anthropic

Equal-Weight S&P 500 (RSP) 25% Value (IWD) 25% Financials (XLF) 25% Healthcare (XLV) 25%

GPT-5.5 OpenAI

Dividend (SCHD) 30% Financials (XLF) 20% Healthcare (XLV) 20% Defense (ITA) 15% Value (IWD) 15%

Reference points

Not model portfolios.

S&P 500 Benchmark

Benchmark return over the same scoring window

ETHA Ethereum ETF - Hindsight best asset

100% Ethereum ETF (ETHA) hindsight ceiling

Official scored round

Monthly result scored Aug 27

Audit ID: CB-2026-07-27-1M

Audit packet Track results

ScoredAug 27WindowJul 27 to Aug 27Models8Asset choices70LeaderGemini 3.1 ProHorizonMonthly

Monthly official result

Monthly result scored Aug 24

Same-window returns, ranked after final prices.

Scored

Model portfolios S&P 500 benchmark Maximum possible return

Gemini 3.1 Pro

Claude Fable 5

Claude Opus 5

Claude Opus 4.8

GPT-5.5

Grok 4.5

GPT-5.6 Sol

Grok 4.3

S&P 500

ETHA Ethereum ETF

Gemini 3.1 Pro Google

5.32%

Claude Fable 5 Anthropic

5.10%

Claude Opus 5 Anthropic

5.03%

Claude Opus 4.8 Anthropic

4.74%

GPT-5.5 OpenAI

4.01%

Grok 4.5 xAI

3.41%

GPT-5.6 Sol OpenAI

2.20%

Grok 4.3 xAI

-0.25%

S&P 500 Benchmark

3.32%

ETHA Ethereum ETF - Hindsight best asset

32.91%

Portfolio context

Shows each model's saved portfolio weights.

Model portfolios

Ranked in the same order as the chart.

Gemini 3.1 Pro Google

S&P 500 (SPY) 40% Energy (XLE) 30% Healthcare (XLV) 30%

Claude Fable 5 Anthropic

Value (IWD) 30% Dividend (SCHD) 20% Energy (XLE) 20% Commodities (PDBC) 15% Healthcare (XLV) 15%

Claude Opus 5 Anthropic

S&P 500 (SPY) 35% Healthcare (XLV) 20% Dividend (SCHD) 20% Energy (XLE) 15% Financials (XLF) 10%

Claude Opus 4.8 Anthropic

S&P 500 (SPY) 40% Healthcare (XLV) 25% Financials (XLF) 20% Dividend (SCHD) 15%

GPT-5.5 OpenAI

Dividend (SCHD) 30% Healthcare (XLV) 20% Energy (XLE) 20% Value (IWD) 15% Utilities (XLU) 15%

Grok 4.5 xAI

Energy (XLE) 30% Crude Oil (USO) 20% Commodities (PDBC) 20% Value (IWD) 15% Healthcare (XLV) 15%

GPT-5.6 Sol OpenAI

Semiconductors (SMH) 45% Dividend (SCHD) 30% Energy (XLE) 15% Healthcare (XLV) 10%

Grok 4.3 xAI

Energy (XLE) 40% Industrials (XLI) 30% Utilities (XLU) 30%

Reference points

Not model portfolios.

S&P 500 Benchmark

Benchmark return over the same scoring window

ETHA Ethereum ETF - Hindsight best asset

100% Ethereum ETF (ETHA) hindsight ceiling

Official scored round

Monthly result scored Aug 24

Audit ID: CB-2026-07-24-1M

Audit packet Track results

ScoredAug 24WindowJul 24 to Aug 24Models8Asset choices70LeaderGemini 3.1 ProHorizonMonthly

Monthly official result

Monthly result scored Aug 21

Same-window returns, ranked after final prices.

Scored

Model portfolios S&P 500 benchmark Maximum possible return

Claude Fable 5

GPT-5.5

Gemini 3.1 Pro

Claude Opus 4.8

Grok 4.5

Grok 4.3

GPT-5.6 Sol

S&P 500

ETHA Ethereum ETF

Claude Fable 5 Anthropic

7.37%

GPT-5.5 OpenAI

6.36%

Gemini 3.1 Pro Google

5.88%

Claude Opus 4.8 Anthropic

5.77%

Grok 4.5 xAI

4.96%

Grok 4.3 xAI

4.91%

GPT-5.6 Sol OpenAI

3.39%

S&P 500 Benchmark

3.73%

ETHA Ethereum ETF - Hindsight best asset

29.27%

Portfolio context

Shows each model's saved portfolio weights.

Model portfolios

Ranked in the same order as the chart.

Claude Fable 5 Anthropic

Energy (XLE) 30% Value (IWD) 25% Healthcare (XLV) 20% Dividend (SCHD) 15% Gold (IAU) 10%

GPT-5.5 OpenAI

Energy (XLE) 30% Commodities (PDBC) 25% Dividend (SCHD) 25% Healthcare (XLV) 20%

Gemini 3.1 Pro Google

Energy (XLE) 30% Crude Oil (USO) 20% Gold (IAU) 25% S&P 500 (SPY) 25%

Claude Opus 4.8 Anthropic

Healthcare (XLV) 30% Energy (XLE) 25% Financials (XLF) 20% S&P 500 (SPY) 25%

Grok 4.5 xAI

Energy (XLE) 35% Crude Oil (USO) 15% Healthcare (XLV) 25% S&P 500 (SPY) 25%

Grok 4.3 xAI

S&P 500 (SPY) 50% Energy (XLE) 30% Japan (EWJ) 20%

GPT-5.6 Sol OpenAI

Defense (ITA) 35% Technology (XLK) 25% Energy (XLE) 20% Dividend (SCHD) 20%

Reference points

Not model portfolios.

S&P 500 Benchmark

Benchmark return over the same scoring window

ETHA Ethereum ETF - Hindsight best asset

100% Ethereum ETF (ETHA) hindsight ceiling

Official scored round

Monthly result scored Aug 21

Audit ID: CB-2026-07-23-1M

Audit packet Track results

ScoredAug 21WindowJul 23 to Aug 21Models7Asset choices70LeaderClaude Fable 5HorizonMonthly

Monthly official result

Monthly result scored Aug 21

Same-window returns, ranked after final prices.

Scored

Model portfolios S&P 500 benchmark Maximum possible return

Gemini 3.1 Pro

Grok 4.5

Claude Opus 4.8

GPT-5.5

Grok 4.3

Claude Fable 5

GPT-5.6 Sol

S&P 500

ETHA Ethereum ETF

Gemini 3.1 Pro Google

7.11%

Grok 4.5 xAI

6.76%

Claude Opus 4.8 Anthropic

5.67%

GPT-5.5 OpenAI

5.02%

Grok 4.3 xAI

4.18%

Claude Fable 5 Anthropic

2.00%

GPT-5.6 Sol OpenAI

1.83%

S&P 500 Benchmark

2.45%

ETHA Ethereum ETF - Hindsight best asset

25.62%

Portfolio context

Shows each model's saved portfolio weights.

Model portfolios

Ranked in the same order as the chart.

Gemini 3.1 Pro Google

Energy (XLE) 50% Dividend (SCHD) 50%

Grok 4.5 xAI

Energy (XLE) 30% Crude Oil (USO) 20% Healthcare (XLV) 25% Dividend (SCHD) 25%

Claude Opus 4.8 Anthropic

Healthcare (XLV) 30% Financials (XLF) 25% Dividend (SCHD) 25% S&P 500 (SPY) 20%

GPT-5.5 OpenAI

Crude Oil (USO) 40% Dividend (SCHD) 25% Healthcare (XLV) 20% United Kingdom (EWU) 15%

Grok 4.3 xAI

S&P 500 (SPY) 60% Energy (XLE) 20% Healthcare (XLV) 10% Financials (XLF) 10%

Claude Fable 5 Anthropic

Semiconductors (SMH) 30% Taiwan (EWT) 20% Energy (XLE) 15% Dividend (SCHD) 20% S&P 500 (SPY) 15%

GPT-5.6 Sol OpenAI

Semiconductors (SMH) 30% Nasdaq 100 (QQQ) 20% Dividend (SCHD) 20% Japan (EWJ) 15% Energy (XLE) 15%

Reference points

Not model portfolios.

S&P 500 Benchmark

Benchmark return over the same scoring window

ETHA Ethereum ETF - Hindsight best asset

100% Ethereum ETF (ETHA) hindsight ceiling

Official scored round

Monthly result scored Aug 21

Audit ID: CB-2026-07-22-1M

Audit packet Track results

ScoredAug 21WindowJul 22 to Aug 21Models7Asset choices70LeaderGemini 3.1 ProHorizonMonthly

Monthly official result

Monthly result scored Aug 21

Same-window returns, ranked after final prices.

Scored

Model portfolios S&P 500 benchmark Maximum possible return

Gemini 3.1 Pro

Grok 4.5

Claude Opus 4.8

Grok 4.3

GPT-5.5

Claude Fable 5

GPT-5.6 Sol

S&P 500

ETHA Ethereum ETF

Gemini 3.1 Pro Google

7.80%

Grok 4.5 xAI

6.55%

Claude Opus 4.8 Anthropic

5.72%

Grok 4.3 xAI

4.33%

GPT-5.5 OpenAI

3.99%

Claude Fable 5 Anthropic

3.03%

GPT-5.6 Sol OpenAI

1.07%

S&P 500 Benchmark

2.33%

ETHA Ethereum ETF - Hindsight best asset

25.53%

Portfolio context

Shows each model's saved portfolio weights.

Model portfolios

Ranked in the same order as the chart.

Gemini 3.1 Pro Google

Crude Oil (USO) 25% Energy (XLE) 25% Healthcare (XLV) 50%

Grok 4.5 xAI

Energy (XLE) 25% Crude Oil (USO) 25% Biotechnology (XBI) 25% Commodities (PDBC) 25%

Claude Opus 4.8 Anthropic

S&P 500 (SPY) 40% Healthcare (XLV) 30% Dividend (SCHD) 30%

Grok 4.3 xAI

S&P 500 (SPY) 40% Energy (XLE) 20% Small Value (IWN) 20% Healthcare (XLV) 15% Financials (XLF) 5%

GPT-5.5 OpenAI

Semiconductors (SMH) 25% Energy (XLE) 20% Biotechnology (XBI) 20% Dividend (SCHD) 20% Japan (EWJ) 15%

Claude Fable 5 Anthropic

S&P 500 (SPY) 30% Semiconductors (SMH) 30% Energy (XLE) 20% Healthcare (XLV) 20%

GPT-5.6 Sol OpenAI

Semiconductors (SMH) 50% Commodities (PDBC) 30% Dividend (SCHD) 20%

Reference points

Not model portfolios.

S&P 500 Benchmark

Benchmark return over the same scoring window

ETHA Ethereum ETF - Hindsight best asset

100% Ethereum ETF (ETHA) hindsight ceiling

Official scored round

Monthly result scored Aug 21

Audit ID: CB-2026-07-21-1M

Audit packet Track results

ScoredAug 21WindowJul 21 to Aug 21Models7Asset choices70LeaderGemini 3.1 ProHorizonMonthly

Monthly official result

Monthly result scored Aug 17

Same-window returns, ranked after final prices.

Scored

Model portfolios S&P 500 benchmark Maximum possible return

Grok 4.5

Grok 4.3

Claude Opus 4.8

Gemini 3.1 Pro

Claude Fable 5

GPT-5.6 Sol

GPT-5.5

Claude Opus 4.7

S&P 500

XME Metals and Mining

Grok 4.5 xAI

4.10%

Grok 4.3 xAI

3.98%

Claude Opus 4.8 Anthropic

3.54%

Gemini 3.1 Pro Google

3.43%

Claude Fable 5 Anthropic

3.25%

GPT-5.6 Sol OpenAI

3.17%

GPT-5.5 OpenAI

3.06%

Claude Opus 4.7 Anthropic

2.84%

S&P 500 Benchmark

3.95%

XME Metals and Mining - Hindsight best asset

20.08%

Portfolio context

Shows each model's saved portfolio weights.

Model portfolios

Ranked in the same order as the chart.

Grok 4.5 xAI

Energy (XLE) 25% Financials (XLF) 25% Healthcare (XLV) 25% Small Value (IWN) 25%

Grok 4.3 xAI

Energy (XLE) 40% Small Value (IWN) 20% Financials (XLF) 20% Real Estate (XLRE) 20%

Claude Opus 4.8 Anthropic

Healthcare (XLV) 30% Financials (XLF) 25% Dividend (SCHD) 25% S&P 500 (SPY) 20%

Gemini 3.1 Pro Google

Crude Oil (USO) 40% Regional Banks (KRE) 30% Healthcare (XLV) 30%

Claude Fable 5 Anthropic

Value (IWD) 25% Equal-Weight S&P 500 (RSP) 25% Healthcare (XLV) 25% Financials (XLF) 25%

GPT-5.6 Sol OpenAI

Small Value (IWN) 30% Healthcare (XLV) 30% Regional Banks (KRE) 25% Energy (XLE) 15%

GPT-5.5 OpenAI

Healthcare (XLV) 30% Financials (XLF) 25% Real Estate (XLRE) 20% Energy (XLE) 15% Equal-Weight S&P 500 (RSP) 10%

Claude Opus 4.7 Anthropic

S&P 500 (SPY) 40% Healthcare (XLV) 25% Financials (XLF) 20% Low Vol (SPLV) 15%

Reference points

Not model portfolios.

S&P 500 Benchmark

Benchmark return over the same scoring window

XME Metals and Mining - Hindsight best asset

100% Metals and Mining (XME) hindsight ceiling

Official scored round

Monthly result scored Aug 17

Audit ID: CB-2026-07-17-1M

Audit packet Track results

ScoredAug 17WindowJul 17 to Aug 17Models8Asset choices70LeaderGrok 4.5HorizonMonthly

Monthly official result

Monthly result scored Aug 14

Same-window returns, ranked after final prices.

Scored

Model portfolios S&P 500 benchmark Maximum possible return

Gemini 3.1 Pro

Grok 4.3

GPT-5.6 Sol

GPT-5.5

Grok 4.5

Claude Fable 5

Claude Opus 4.8

Claude Opus 4.7

S&P 500

XME Metals and Mining

Gemini 3.1 Pro Google

7.37%

Grok 4.3 xAI

6.64%

GPT-5.6 Sol OpenAI

6.40%

GPT-5.5 OpenAI

5.66%

Grok 4.5 xAI

5.52%

Claude Fable 5 Anthropic

5.26%

Claude Opus 4.8 Anthropic

5.23%

Claude Opus 4.7 Anthropic

3.84%

S&P 500 Benchmark

2.85%

XME Metals and Mining - Hindsight best asset

13.51%

Portfolio context

Shows each model's saved portfolio weights.

Model portfolios

Ranked in the same order as the chart.

Gemini 3.1 Pro Google

Energy (XLE) 40% Crude Oil (USO) 30% Defense (ITA) 15% Gold (IAU) 15%

Grok 4.3 xAI

Energy (XLE) 50% Crude Oil (USO) 30% Financials (XLF) 20%

GPT-5.6 Sol OpenAI

Energy (XLE) 35% Crude Oil (USO) 25% Financials (XLF) 20% Cybersecurity (CIBR) 10% Defense (ITA) 10%

GPT-5.5 OpenAI

Crude Oil (USO) 45% Energy (XLE) 25% Commodities (PDBC) 15% Defense (ITA) 10% US Dollar (UUP) 5%

Grok 4.5 xAI

Energy (XLE) 35% Crude Oil (USO) 25% Financials (XLF) 20% Biotechnology (XBI) 10% Value (IWD) 10%

Claude Fable 5 Anthropic

Energy (XLE) 30% Financials (XLF) 20% Commodities (PDBC) 15% Value (IWD) 25% T-Bills (BIL) 10%

Claude Opus 4.8 Anthropic

Financials (XLF) 30% Energy (XLE) 20% Value (IWD) 20% Equal-Weight S&P 500 (RSP) 15% Healthcare (XLV) 15%

Claude Opus 4.7 Anthropic

Financials (XLF) 30% Energy (XLE) 20% Biotechnology (XBI) 15% Value (IWD) 20% T-Bills (BIL) 15%

Reference points

Not model portfolios.

S&P 500 Benchmark

Benchmark return over the same scoring window

XME Metals and Mining - Hindsight best asset

100% Metals and Mining (XME) hindsight ceiling

Official scored round

Monthly result scored Aug 14

Audit ID: CB-2026-07-15-1M

Audit packet Track results

ScoredAug 14WindowJul 15 to Aug 14Models8Asset choices70LeaderGemini 3.1 ProHorizonMonthly

Monthly official result

Monthly result scored Aug 14

Same-window returns, ranked after final prices.

Scored

Model portfolios S&P 500 benchmark Maximum possible return

Grok 4.3

Grok 4.5

Claude Opus 4.8

Claude Opus 4.7

Gemini 3.1 Pro

Claude Fable 5

GPT-5.6 Sol

GPT-5.5

S&P 500

XME Metals and Mining

Grok 4.3 xAI

5.53%

Grok 4.5 xAI

5.27%

Claude Opus 4.8 Anthropic

4.74%

Claude Opus 4.7 Anthropic

4.48%

Gemini 3.1 Pro Google

4.32%

Claude Fable 5 Anthropic

3.59%

GPT-5.6 Sol OpenAI

2.80%

GPT-5.5 OpenAI

2.32%

S&P 500 Benchmark

3.26%

XME Metals and Mining - Hindsight best asset

12.18%

Portfolio context

Shows each model's saved portfolio weights.

Model portfolios

Ranked in the same order as the chart.

Grok 4.3 xAI

Energy (XLE) 40% Financials (XLF) 35% S&P 500 (SPY) 25%

Grok 4.5 xAI

Energy (XLE) 30% Crude Oil (USO) 20% Financials (XLF) 25% Biotechnology (XBI) 15% Cybersecurity (CIBR) 10%

Claude Opus 4.8 Anthropic

Financials (XLF) 35% Energy (XLE) 20% Cybersecurity (CIBR) 15% Industrials (XLI) 15% S&P 500 (SPY) 15%

Claude Opus 4.7 Anthropic

Financials (XLF) 30% Energy (XLE) 25% Cybersecurity (CIBR) 20% Biotechnology (XBI) 15% T-Bills (BIL) 10%

Gemini 3.1 Pro Google

Financials (XLF) 30% Energy (XLE) 30% Crude Oil (USO) 20% Semiconductors (SMH) 20%

Claude Fable 5 Anthropic

Financials (XLF) 30% Energy (XLE) 25% Semiconductors (SMH) 20% Value (IWD) 15% T-Bills (BIL) 10%

GPT-5.6 Sol OpenAI

Semiconductors (SMH) 30% Cybersecurity (CIBR) 25% Financials (XLF) 20% Energy (XLE) 15% Biotechnology (XBI) 10%

GPT-5.5 OpenAI

Semiconductors (SMH) 30% Crude Oil (USO) 25% Financials (XLF) 20% Cybersecurity (CIBR) 15% Biotechnology (XBI) 10%

Reference points

Not model portfolios.

S&P 500 Benchmark

Benchmark return over the same scoring window

XME Metals and Mining - Hindsight best asset

100% Metals and Mining (XME) hindsight ceiling

Official scored round

Monthly result scored Aug 14

Audit ID: CB-2026-07-14-1M

Audit packet Track results

ScoredAug 14WindowJul 14 to Aug 14Models8Asset choices70LeaderGrok 4.3HorizonMonthly

Monthly official result

Monthly result scored Aug 13

Same-window returns, ranked after final prices.

Scored

Model portfolios S&P 500 benchmark Maximum possible return

Gemini 3.1 Pro

Grok 4.5

Grok 4.3

GPT-5.5

GPT-5.6 Sol

Claude Fable 5

Claude Opus 4.7

Claude Opus 4.8

S&P 500

IGV Software

Gemini 3.1 Pro Google

7.11%

Grok 4.5 xAI

5.85%

Grok 4.3 xAI

5.84%

GPT-5.5 OpenAI

5.64%

GPT-5.6 Sol OpenAI

5.32%

Claude Fable 5 Anthropic

4.05%

Claude Opus 4.7 Anthropic

3.97%

Claude Opus 4.8 Anthropic

3.58%

S&P 500 Benchmark

3.83%

IGV Software - Hindsight best asset

14.65%

Portfolio context

Shows each model's saved portfolio weights.

Model portfolios

Ranked in the same order as the chart.

Gemini 3.1 Pro Google

Crude Oil (USO) 30% Energy (XLE) 30% Defense (ITA) 20% Gold (IAU) 20%

Grok 4.5 xAI

Energy (XLE) 35% Crude Oil (USO) 25% Financials (XLF) 20% Healthcare (XLV) 15% Value (IWD) 5%

Grok 4.3 xAI

Energy (XLE) 50% Financials (XLF) 30% Healthcare (XLV) 20%

GPT-5.5 OpenAI

Crude Oil (USO) 45% Energy (XLE) 25% Commodities (PDBC) 15% US Dollar (UUP) 10% Defense (ITA) 5%

GPT-5.6 Sol OpenAI

Energy (XLE) 35% Crude Oil (USO) 25% Financials (XLF) 15% Healthcare (XLV) 15% US Dollar (UUP) 10%

Claude Fable 5 Anthropic

Energy (XLE) 30% Crude Oil (USO) 10% Value (IWD) 25% Low Vol (SPLV) 20% T-Bills (BIL) 15%

Claude Opus 4.7 Anthropic

Energy (XLE) 30% Healthcare (XLV) 20% Low Vol (SPLV) 15% T-Bills (BIL) 15% Financials (XLF) 20%

Claude Opus 4.8 Anthropic

Energy (XLE) 25% Healthcare (XLV) 20% Financials (XLF) 20% Low Vol (SPLV) 20% T-Bills (BIL) 15%

Reference points

Not model portfolios.

S&P 500 Benchmark

Benchmark return over the same scoring window

IGV Software - Hindsight best asset

100% Software (IGV) hindsight ceiling

Official scored round

Monthly result scored Aug 13

Audit ID: CB-2026-07-13-1M

Audit packet Track results

ScoredAug 13WindowJul 13 to Aug 13Models8Asset choices70LeaderGemini 3.1 ProHorizonMonthly

Monthly official result

Monthly result scored Aug 10

Same-window returns, ranked after final prices.

Scored

Model portfolios S&P 500 benchmark Maximum possible return

Claude Opus 4.8

Claude Opus 4.7

GPT-5.5

GPT-5.6 Sol

Grok 4.3

Claude Fable 5

Grok 4.5

Gemini 3.1 Pro

S&P 500

USO Crude Oil

Claude Opus 4.8 Anthropic

-0.42%

Claude Opus 4.7 Anthropic

-0.72%

GPT-5.5 OpenAI

-0.74%

GPT-5.6 Sol OpenAI

-0.95%

Grok 4.3 xAI

-1.42%

Claude Fable 5 Anthropic

-2.29%

Grok 4.5 xAI

-3.71%

Gemini 3.1 Pro Google

-7.19%

S&P 500 Benchmark

2.39%

USO Crude Oil - Hindsight best asset

15.84%

Portfolio context

Shows each model's saved portfolio weights.

Model portfolios

Ranked in the same order as the chart.

Claude Opus 4.8 Anthropic

Semiconductors (SMH) 30% Financials (XLF) 25% Industrials (XLI) 20% Taiwan (EWT) 15% Cybersecurity (CIBR) 10%

Claude Opus 4.7 Anthropic

Semiconductors (SMH) 30% Financials (XLF) 20% Biotechnology (XBI) 15% Cybersecurity (CIBR) 15% Taiwan (EWT) 20%

GPT-5.5 OpenAI

Semiconductors (SMH) 35% Taiwan (EWT) 20% Cybersecurity (CIBR) 20% Financials (XLF) 15% Biotechnology (XBI) 10%

GPT-5.6 Sol OpenAI

Semiconductors (SMH) 40% Cybersecurity (CIBR) 20% Biotechnology (XBI) 20% Financials (XLF) 10% Taiwan (EWT) 10%

Grok 4.3 xAI

Semiconductors (SMH) 50% Technology (XLK) 30% Cybersecurity (CIBR) 20%

Claude Fable 5 Anthropic

Semiconductors (SMH) 35% Taiwan (EWT) 15% Nasdaq 100 (QQQ) 20% Financials (XLF) 15% Industrials (XLI) 15%

Grok 4.5 xAI

Semiconductors (SMH) 40% Taiwan (EWT) 25% Technology (XLK) 20% Nasdaq 100 (QQQ) 15%

Gemini 3.1 Pro Google

Semiconductors (SMH) 40% South Korea (EWY) 30% Taiwan (EWT) 30%

Reference points

Not model portfolios.

S&P 500 Benchmark

Benchmark return over the same scoring window

USO Crude Oil - Hindsight best asset

100% Crude Oil (USO) hindsight ceiling

Official scored round

Monthly result scored Aug 10

Audit ID: CB-2026-07-10-1M

Audit packet Track results

ScoredAug 10WindowJul 10 to Aug 10Models8Asset choices70LeaderClaude Opus 4.8HorizonMonthly

Monthly official result

Monthly result scored Aug 7

Same-window returns, ranked after final prices.

Scored

Model portfolios S&P 500 benchmark Maximum possible return

Grok 4.3

Claude Opus 4.7

Claude Opus 4.8

Gemini 3.1 Pro

Claude Fable 5

GPT-5.5

Grok 4.5

S&P 500

XME Metals and Mining

Grok 4.3 xAI

4.46%

Claude Opus 4.7 Anthropic

1.92%

Claude Opus 4.8 Anthropic

1.68%

Gemini 3.1 Pro Google

1.21%

Claude Fable 5 Anthropic

0.11%

GPT-5.5 OpenAI

-0.14%

Grok 4.5 xAI

-1.16%

S&P 500 Benchmark

2.87%

XME Metals and Mining - Hindsight best asset

12.11%

Portfolio context

Shows each model's saved portfolio weights.

Model portfolios

Ranked in the same order as the chart.

Grok 4.3 xAI

Energy (XLE) 40% Defense (ITA) 30% Financials (XLF) 30%

Claude Opus 4.7 Anthropic

Cybersecurity (CIBR) 30% Financials (XLF) 25% Healthcare (XLV) 20% Semiconductors (SMH) 15% T-Bills (BIL) 10%

Claude Opus 4.8 Anthropic

Financials (XLF) 25% Healthcare (XLV) 20% Semiconductors (SMH) 20% S&P 500 (SPY) 20% Cybersecurity (CIBR) 15%

Gemini 3.1 Pro Google

Semiconductors (SMH) 30% Defense (ITA) 25% Energy (XLE) 25% T-Bills (BIL) 20%

Claude Fable 5 Anthropic

Semiconductors (SMH) 25% Nasdaq 100 (QQQ) 20% Biotechnology (XBI) 15% Financials (XLF) 15% Energy (XLE) 25%

GPT-5.5 OpenAI

Semiconductors (SMH) 35% Cybersecurity (CIBR) 25% Biotechnology (XBI) 20% Crude Oil (USO) 10% Financials (XLF) 10%

Grok 4.5 xAI

Semiconductors (SMH) 30% Biotechnology (XBI) 25% Cybersecurity (CIBR) 20% Financials (XLF) 15% Taiwan (EWT) 10%

Reference points

Not model portfolios.

S&P 500 Benchmark

Benchmark return over the same scoring window

XME Metals and Mining - Hindsight best asset

100% Metals and Mining (XME) hindsight ceiling

Official scored round

Monthly result scored Aug 7

Audit ID: CB-2026-07-09-1M

Audit packet Track results

ScoredAug 7WindowJul 9 to Aug 7Models7Asset choices70LeaderGrok 4.3HorizonMonthly

Monthly official result

Monthly result scored Aug 7

Same-window returns, ranked after final prices.

Scored

Model portfolios S&P 500 benchmark Maximum possible return

Grok 4.3

Gemini 3.1 Pro

Claude Fable 5

Claude Opus 4.7

Claude Opus 4.8

Grok 4.5

GPT-5.5

S&P 500

XME Metals and Mining

Grok 4.3 xAI

3.73%

Gemini 3.1 Pro Google

2.66%

Claude Fable 5 Anthropic

2.65%

Claude Opus 4.7 Anthropic

2.05%

Claude Opus 4.8 Anthropic

1.96%

Grok 4.5 xAI

1.19%

GPT-5.5 OpenAI

-0.09%

S&P 500 Benchmark

3.74%

XME Metals and Mining - Hindsight best asset

13.54%

Portfolio context

Shows each model's saved portfolio weights.

Model portfolios

Ranked in the same order as the chart.

Grok 4.3 xAI

Value (IWD) 30% Healthcare (XLV) 25% Financials (XLF) 20% Industrials (XLI) 15% Energy (XLE) 10%

Gemini 3.1 Pro Google

Energy (XLE) 30% Crude Oil (USO) 20% Healthcare (XLV) 25% T-Bills (BIL) 25%

Claude Fable 5 Anthropic

Healthcare (XLV) 25% Value (IWD) 20% Financials (XLF) 20% Biotechnology (XBI) 15% Energy (XLE) 20%

Claude Opus 4.7 Anthropic

Healthcare (XLV) 30% Financials (XLF) 25% Low Vol (SPLV) 20% Utilities (XLU) 15% Cybersecurity (CIBR) 10%

Claude Opus 4.8 Anthropic

Financials (XLF) 25% Healthcare (XLV) 25% Low Vol (SPLV) 20% Utilities (XLU) 15% Defense (ITA) 15%

Grok 4.5 xAI

Biotechnology (XBI) 35% Healthcare (XLV) 20% Financials (XLF) 20% Energy (XLE) 15% Value (IWD) 10%

GPT-5.5 OpenAI

Biotechnology (XBI) 35% Semiconductors (SMH) 25% Healthcare (XLV) 15% Financials (XLF) 15% Crude Oil (USO) 10%

Reference points

Not model portfolios.

S&P 500 Benchmark

Benchmark return over the same scoring window

XME Metals and Mining - Hindsight best asset

100% Metals and Mining (XME) hindsight ceiling

Official scored round

Monthly result scored Aug 7

Audit ID: CB-2026-07-08-1M

Audit packet Track results

ScoredAug 7WindowJul 8 to Aug 7Models7Asset choices70LeaderGrok 4.3HorizonMonthly

Monthly official result

Monthly result scored Aug 7

Same-window returns, ranked after final prices.

Scored

Model portfolios S&P 500 benchmark Maximum possible return

GPT-5.5

Gemini 3.1 Pro

Grok 4.3

Claude Opus 4.7

Claude Opus 4.8

Claude Fable 5

S&P 500

XME Metals and Mining

GPT-5.5 OpenAI

3.13%

Gemini 3.1 Pro Google

3.12%

Grok 4.3 xAI

2.92%

Claude Opus 4.7 Anthropic

1.98%

Claude Opus 4.8 Anthropic

1.95%

Claude Fable 5 Anthropic

1.63%

S&P 500 Benchmark

3.42%

XME Metals and Mining - Hindsight best asset

12.95%

Portfolio context

Shows each model's saved portfolio weights.

Model portfolios

Ranked in the same order as the chart.

GPT-5.5 OpenAI

Crude Oil (USO) 25% Energy (XLE) 20% Semiconductors (SMH) 20% Financials (XLF) 20% Biotechnology (XBI) 15%

Gemini 3.1 Pro Google

S&P 500 (SPY) 40% Energy (XLE) 20% Financials (XLF) 20% Healthcare (XLV) 20%

Grok 4.3 xAI

Value (IWD) 30% Financials (XLF) 25% Healthcare (XLV) 20% Small Value (IWN) 15% Energy (XLE) 10%

Claude Opus 4.7 Anthropic

Financials (XLF) 25% Healthcare (XLV) 20% Value (IWD) 20% Low Vol (SPLV) 15% Defense (ITA) 20%

Claude Opus 4.8 Anthropic

Financials (XLF) 25% Healthcare (XLV) 25% Value (IWD) 20% Industrials (XLI) 15% T-Bills (BIL) 15%

Claude Fable 5 Anthropic

Financials (XLF) 25% Healthcare (XLV) 20% Value (IWD) 20% Energy (XLE) 15% Biotechnology (XBI) 20%

Reference points

Not model portfolios.

S&P 500 Benchmark

Benchmark return over the same scoring window

XME Metals and Mining - Hindsight best asset

100% Metals and Mining (XME) hindsight ceiling

Official scored round

Monthly result scored Aug 7

Audit ID: CB-2026-07-07-1M

Audit packet Track results

ScoredAug 7WindowJul 7 to Aug 7Models6Asset choices70LeaderGPT-5.5HorizonMonthly

Monthly official result

Monthly result scored Aug 6

Same-window returns, ranked after final prices.

Scored

Model portfolios S&P 500 benchmark Maximum possible return

Claude Opus 4.8

Claude Opus 4.7

Grok 4.3

Gemini 3.1 Pro

GPT-5.5

Claude Fable 5

S&P 500

USO Crude Oil

Claude Opus 4.8 Anthropic

1.38%

Claude Opus 4.7 Anthropic

1.25%

Grok 4.3 xAI

0.50%

Gemini 3.1 Pro Google

-1.35%

GPT-5.5 OpenAI

-1.71%

Claude Fable 5 Anthropic

-1.83%

S&P 500 Benchmark

2.30%

USO Crude Oil - Hindsight best asset

13.91%

Portfolio context

Shows each model's saved portfolio weights.

Model portfolios

Ranked in the same order as the chart.

Claude Opus 4.8 Anthropic

Financials (XLF) 25% Industrials (XLI) 20% Healthcare (XLV) 20% S&P 500 (SPY) 20% Defense (ITA) 15%

Claude Opus 4.7 Anthropic

Financials (XLF) 25% Industrials (XLI) 20% Defense (ITA) 15% Healthcare (XLV) 20% Equal-Weight S&P 500 (RSP) 20%

Grok 4.3 xAI

Small Cap (IWM) 25% Financials (XLF) 25% Industrials (XLI) 25% Defense (ITA) 25%

Gemini 3.1 Pro Google

Semiconductors (SMH) 40% Financials (XLF) 30% Small Cap (IWM) 30%

GPT-5.5 OpenAI

Taiwan (EWT) 30% Semiconductors (SMH) 25% Financials (XLF) 20% Cybersecurity (CIBR) 15% Defense (ITA) 10%

Claude Fable 5 Anthropic

Semiconductors (SMH) 25% Financials (XLF) 20% Industrials (XLI) 15% Healthcare (XLV) 15% Taiwan (EWT) 25%

Reference points

Not model portfolios.

S&P 500 Benchmark

Benchmark return over the same scoring window

USO Crude Oil - Hindsight best asset

100% Crude Oil (USO) hindsight ceiling

Official scored round

Monthly result scored Aug 6

Audit ID: CB-2026-07-06-1M

Audit packet Track results

ScoredAug 6WindowJul 6 to Aug 6Models6Asset choices70LeaderClaude Opus 4.8HorizonMonthly

Monthly official result

Monthly result scored Jul 31

Same-window returns, ranked after final prices.

Scored

Model portfolios S&P 500 benchmark Maximum possible return

Grok 4.3

Gemini 3.1 Pro

Claude Opus 4.8

Claude Opus 4.7

Claude Fable 5

GPT-5.5

S&P 500

USO Crude Oil

Grok 4.3 xAI

0.80%

Gemini 3.1 Pro Google

0.50%

Claude Opus 4.8 Anthropic

0.35%

Claude Opus 4.7 Anthropic

-0.06%

Claude Fable 5 Anthropic

-0.98%

GPT-5.5 OpenAI

-1.97%

S&P 500 Benchmark

0.30%

USO Crude Oil - Hindsight best asset

24.23%

Portfolio context

Shows each model's saved portfolio weights.

Model portfolios

Ranked in the same order as the chart.

Grok 4.3 xAI

Value (IWD) 25% Financials (XLF) 25% Healthcare (XLV) 25% Low Vol (SPLV) 25%

Gemini 3.1 Pro Google

S&P 500 (SPY) 40% Healthcare (XLV) 20% Financials (XLF) 20% T-Bills (BIL) 20%

Claude Opus 4.8 Anthropic

Financials (XLF) 25% Healthcare (XLV) 20% Value (IWD) 20% Defense (ITA) 15% Equal-Weight S&P 500 (RSP) 20%

Claude Opus 4.7 Anthropic

Financials (XLF) 25% Healthcare (XLV) 25% Equal-Weight S&P 500 (RSP) 20% Defense (ITA) 15% T-Bills (BIL) 15%

Claude Fable 5 Anthropic

Healthcare (XLV) 25% Biotechnology (XBI) 20% Financials (XLF) 20% Value (IWD) 20% Small Value (IWN) 15%

GPT-5.5 OpenAI

Healthcare (XLV) 30% Biotechnology (XBI) 25% Financials (XLF) 20% Regional Banks (KRE) 15% Defense (ITA) 10%

Reference points

Not model portfolios.

S&P 500 Benchmark

Benchmark return over the same scoring window

USO Crude Oil - Hindsight best asset

100% Crude Oil (USO) hindsight ceiling

Official scored round

Monthly result scored Jul 31

Audit ID: CB-2026-07-02-1M

Audit packet Track results

ScoredJul 31WindowJul 2 to Jul 31Models6Asset choices70LeaderGrok 4.3HorizonMonthly

Monthly official result

Monthly result scored Jul 31

Same-window returns, ranked after final prices.

Scored

Model portfolios S&P 500 benchmark Maximum possible return

Gemini 3.1 Pro

Claude Opus 4.8

Grok 4.3

Claude Opus 4.7

Claude Fable 5

GPT-5.5

S&P 500

USO Crude Oil

Gemini 3.1 Pro Google

1.30%

Claude Opus 4.8 Anthropic

1.11%

Grok 4.3 xAI

1.01%

Claude Opus 4.7 Anthropic

0.46%

Claude Fable 5 Anthropic

0.45%

GPT-5.5 OpenAI

-1.21%

S&P 500 Benchmark

0.17%

USO Crude Oil - Hindsight best asset

25.08%

Portfolio context

Shows each model's saved portfolio weights.

Model portfolios

Ranked in the same order as the chart.

Gemini 3.1 Pro Google

S&P 500 (SPY) 40% Healthcare (XLV) 20% Financials (XLF) 20% T-Bills (BIL) 20%

Claude Opus 4.8 Anthropic

Financials (XLF) 25% Industrials (XLI) 20% Healthcare (XLV) 20% Regional Banks (KRE) 15% Equal-Weight S&P 500 (RSP) 20%

Grok 4.3 xAI

Small Value (IWN) 30% Financials (XLF) 25% Healthcare (XLV) 25% Industrials (XLI) 20%

Claude Opus 4.7 Anthropic

Healthcare (XLV) 30% Financials (XLF) 25% Industrials (XLI) 15% Equal-Weight S&P 500 (RSP) 15% Biotechnology (XBI) 15%

Claude Fable 5 Anthropic

Healthcare (XLV) 25% Small Value (IWN) 20% Financials (XLF) 20% Equal-Weight S&P 500 (RSP) 20% Biotechnology (XBI) 15%

GPT-5.5 OpenAI

Regional Banks (KRE) 30% Biotechnology (XBI) 25% Small Value (IWN) 20% Financials (XLF) 15% Industrials (XLI) 10%

Reference points

Not model portfolios.

S&P 500 Benchmark

Benchmark return over the same scoring window

USO Crude Oil - Hindsight best asset

100% Crude Oil (USO) hindsight ceiling

Official scored round

Monthly result scored Jul 31

Audit ID: CB-2026-07-01-1M

Audit packet Track results

ScoredJul 31WindowJul 1 to Jul 31Models6Asset choices70LeaderGemini 3.1 ProHorizonMonthly

Monthly official result

Monthly result scored Jul 13

Same-window returns, ranked after final prices.

Scored

Model portfolios S&P 500 benchmark Maximum possible return

Grok 4.3

Claude Opus 4.8

Gemini 3.1 Pro

Claude Opus 4.7

GPT-5.5

Claude Fable 5

S&P 500

XBI Biotechnology

Grok 4.3 xAI

3.92%

Claude Opus 4.8 Anthropic

0.67%

Gemini 3.1 Pro Google

0.45%

Claude Opus 4.7 Anthropic

0.34%

GPT-5.5 OpenAI

-0.58%

Claude Fable 5 Anthropic

-3.80%

S&P 500 Benchmark

1.81%

XBI Biotechnology - Hindsight best asset

17.14%

Portfolio context

Shows each model's saved portfolio weights.

Model portfolios

Ranked in the same order as the chart.

Grok 4.3 xAI

Energy (XLE) 35% Financials (XLF) 30% Healthcare (XLV) 35%

Claude Opus 4.8 Anthropic

Healthcare (XLV) 25% Defense (ITA) 20% Semiconductors (SMH) 20% Dividend (SCHD) 20% T-Bills (BIL) 15%

Gemini 3.1 Pro Google

Technology (XLK) 30% Energy (XLE) 30% S&P 500 (SPY) 40%

Claude Opus 4.7 Anthropic

Semiconductors (SMH) 30% Defense (ITA) 20% Healthcare (XLV) 20% Equal-Weight S&P 500 (RSP) 20% T-Bills (BIL) 10%

GPT-5.5 OpenAI

Semiconductors (SMH) 35% Cybersecurity (CIBR) 20% Regional Banks (KRE) 20% Defense (ITA) 15% South Korea (EWY) 10%

Claude Fable 5 Anthropic

Semiconductors (SMH) 30% South Korea (EWY) 15% Taiwan (EWT) 10% Momentum (MTUM) 20% Energy (XLE) 25%

Reference points

Not model portfolios.

S&P 500 Benchmark

Benchmark return over the same scoring window

XBI Biotechnology - Hindsight best asset

100% Biotechnology (XBI) hindsight ceiling

Official scored round

Monthly result scored Jul 13

Audit ID: CB-2026-06-12-1M

Audit packet Track results

ScoredJul 13WindowJun 11 to Jul 13Models6Asset choices70LeaderGrok 4.3HorizonMonthly

Monthly official result

Monthly result scored Jul 9

Same-window returns, ranked after final prices.

Scored

Model portfolios S&P 500 benchmark Maximum possible return

Claude Opus 4.8

GPT-5.5

Claude Opus 4.7

Grok 4.3

Claude Fable 5

Gemini 3.1 Pro

S&P 500

XBI Biotechnology

Claude Opus 4.8 Anthropic

3.10%

GPT-5.5 OpenAI

2.76%

Claude Opus 4.7 Anthropic

2.60%

Grok 4.3 xAI

2.23%

Claude Fable 5 Anthropic

1.58%

Gemini 3.1 Pro Google

0.18%

S&P 500 Benchmark

2.25%

XBI Biotechnology - Hindsight best asset

25.16%

Portfolio context

Shows each model's saved portfolio weights.

Model portfolios

Ranked in the same order as the chart.

Claude Opus 4.8 Anthropic

Healthcare (XLV) 30% Dividend (SCHD) 20% Value (IWD) 20% Defense (ITA) 15% T-Bills (BIL) 15%

GPT-5.5 OpenAI

Healthcare (XLV) 30% Energy (XLE) 25% Financials (XLF) 20% Defense (ITA) 15% Equal-Weight S&P 500 (RSP) 10%

Claude Opus 4.7 Anthropic

Healthcare (XLV) 30% Dividend (SCHD) 25% Low Vol (SPLV) 20% Staples (XLP) 15% Defense (ITA) 10%

Grok 4.3 xAI

Healthcare (XLV) 40% Energy (XLE) 30% Defense (ITA) 30%

Claude Fable 5 Anthropic

Healthcare (XLV) 30% Energy (XLE) 25% Low Vol (SPLV) 15% Staples (XLP) 15% Value (IWD) 15%

Gemini 3.1 Pro Google

T-Bills (BIL) 30% Healthcare (XLV) 25% Gold (IAU) 20% Energy (XLE) 15% Staples (XLP) 10%

Reference points

Not model portfolios.

S&P 500 Benchmark

Benchmark return over the same scoring window

XBI Biotechnology - Hindsight best asset

100% Biotechnology (XBI) hindsight ceiling

Official scored round

Monthly result scored Jul 9

Audit ID: CB-2026-06-09-1M

Audit packet Track results

ScoredJul 9WindowJun 9 to Jul 9Models6Asset choices70LeaderClaude Opus 4.8HorizonMonthly

View all benchmark results

Audit packet

How can you verify the benchmark?

Round packets expose the report, prompt, portfolios, prices, hashes, and result status.

Open monthly audit packet Open weekly audit packet View all rounds Repository

The benchmark for AI capital allocation

Which models are performing best?

Current Monthly Benchmark

CapitalBench Score

Average Return Details

Current Weekly Benchmark

CapitalBench Score

Average Return Details

Who leads when markets rise or fall?

What are AI models doing right now?

What do the latest AI decisions suggest?

Live AI portfolios are concentrated in S&P 500 (SPY)

Monthly model leadership changes with the S&P 500 environment

Grok 4.3 follows recent winners most

What makes each model test comparable?

What can models choose from?

What happened in the latest scored rounds?

Monthly result scored Sep 25

Monthly result scored Sep 25

Monthly result scored Sep 25

Monthly result scored Sep 25

Monthly result scored Sep 24

Monthly result scored Sep 24

Monthly result scored Sep 21

Monthly result scored Sep 21

Monthly result scored Sep 21

Monthly result scored Sep 21

Monthly result scored Sep 18

Monthly result scored Sep 18

Monthly result scored Sep 18

Monthly result scored Sep 18

Monthly result scored Sep 17

Monthly result scored Sep 17

Monthly result scored Sep 14

Monthly result scored Sep 14

Monthly result scored Sep 11

Monthly result scored Sep 11

Monthly result scored Sep 10

Monthly result scored Sep 10

Monthly result scored Sep 8

Monthly result scored Sep 8

Monthly result scored Sep 4

Monthly result scored Sep 4

Monthly result scored Sep 4

Monthly result scored Sep 4

Monthly result scored Aug 31

Monthly result scored Aug 31

Monthly result scored Aug 28

Monthly result scored Aug 28

Monthly result scored Aug 28

Monthly result scored Aug 28

Monthly result scored Aug 28

Monthly result scored Aug 28

Monthly result scored Aug 27

Monthly result scored Aug 27

Monthly result scored Aug 24

Monthly result scored Aug 24

Monthly result scored Aug 21

Monthly result scored Aug 21

Monthly result scored Aug 21

Monthly result scored Aug 21

Monthly result scored Aug 21

Monthly result scored Aug 21

Monthly result scored Aug 17

Monthly result scored Aug 17

Monthly result scored Aug 14

Monthly result scored Aug 14

Monthly result scored Aug 14

Monthly result scored Aug 14

Monthly result scored Aug 13

Monthly result scored Aug 13

Monthly result scored Aug 10

Monthly result scored Aug 10

Monthly result scored Aug 7

Monthly result scored Aug 7

Monthly result scored Aug 7

Monthly result scored Aug 7

Monthly result scored Aug 7

Monthly result scored Aug 7

Monthly result scored Aug 6