One-week benchmark
Weekly Benchmark Results
Latest one-week result plus full weekly history across 25 completed rounds. Models have beaten the S&P 500 in 13/25 completed weekly rounds and 49/128 model-round observations. No model has beaten the S&P 500 in the last 1 completed weekly round.
Weekly benchmark
Latest Result And Full Weekly History
Gemini 3.1 Pro led the latest weekly round at 0.16%, compared with 0.93% for the S&P 500. Grok 4.3 leads the full weekly history with a CapitalBench Score of -2.1.
2026-07-02 close to 2026-07-09 close
CapitalBench Score
Score calculation Main Benchmark Scale
CapitalBench Score compares each model portfolio with the best eligible asset in hindsight for the same weekly window. Max possible is always 100.
Latest round
Latest Round CapitalBench Score
CapitalBench Score compares each portfolio with the best eligible asset in hindsight for this exact weekly window. Max possible is 100.
Max possible S&P 500 Model portfolios
Max possible USO · score 100
100.0 4.84%
S&P 500 Benchmark reference
19.2 0.93%
Gemini 3.1 Pro Google 3.2 0.16%
Claude Fable 5 Anthropic -2.9 -0.14%
GPT-5.5 OpenAI -4.8 -0.23%
Claude Opus 4.8 Anthropic -13.8 -0.67%
Claude Opus 4.7 Anthropic -15.3 -0.74%
Grok 4.3 xAI -30.9 -1.50%
Full weekly history
Full-History Weekly CapitalBench Score
Full-history scores divide total model return by total max-possible return across every resolved weekly round.
Max possible S&P 500 Model portfolios
Max possible Hindsight best asset · score 100
100.0 216.12%
Grok 4.3 xAI · 25/25 rounds -2.1 -4.63%
Claude Opus 4.7 Anthropic · 25/25 rounds -3.7 -8.00%
GPT-5.5 OpenAI · 25/25 rounds -10.5 -22.68%
Gemini 3.1 Pro Google · 25/25 rounds -13.7 -29.71%
S&P 500 Benchmark reference
1.1 2.30%
Weekly track context
Cumulative Weekly Results
Models have beaten the S&P 500 in 13/25 completed weekly rounds and 49/128 model-round observations. No model has beaten the S&P 500 in the last 1 completed weekly round.
Open full weekly history Weekly history trend
CapitalBench Score By Completed Weekly Round
Max possible is fixed at 100. The chart compares S&P 500, the top model, and the average model score in each completed weekly round.
Max possible Top model Average model S&P 500
Investor readout
Top AI Portfolio Still Lagged The Benchmark
Every model finished below the S&P 500. The common pattern was crowded exposure to AI, technology, software, and semiconductor momentum during a short-window rotation away from those trades.
Top model return 0.16% vs S&P 500 0.93%.
Average model portfolio finished -1.45 pp versus S&P 500.
Healthcare Sector (XLV) 29.2% avg Financials Sector (XLF) 18.3% avg US Low Volatility Equities (SPLV) 16.7% avg S&P 500 (SPY) 9.2% avg
Crude Oil (USO) 4.84% China Equities (MCHI) 4.48% Cybersecurity (CIBR) 3.96%
Healthcare Sector (XLV) -0.96% US Low Volatility Equities (SPLV) -1.60% Consumer Staples Sector (XLP) -2.11%
Official weekly result history
Browse Weekly Official Results
Move backward or forward through completed weekly rounds without leaving the weekly results page.
Weekly result1 of 25
Weekly official result
Weekly result scored Jul 9
Same-window returns, ranked after final prices.
Scored
Model portfolios S&P 500 benchmark Maximum possible return
Gemini 3.1 Pro Claude Fable 5 GPT-5.5 Claude Opus 4.8 Claude Opus 4.7 Grok 4.3 S&P 500
Max
Gemini 3.1 Pro Google Claude Fable 5 Anthropic GPT-5.5 OpenAI Claude Opus 4.8 Anthropic Claude Opus 4.7 Anthropic Grok 4.3 xAI S&P 500 Benchmark
0.93% Max possible USO
4.84% 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 Fable 5 Anthropic
Healthcare (XLV) 30% Financials (XLF) 20% Low Vol (SPLV) 20% Biotechnology (XBI) 15% S&P 500 (SPY) 15%
GPT-5.5 OpenAI
Biotechnology (XBI) 30% Healthcare (XLV) 25% Financials (XLF) 20% Defense (ITA) 15% Low Vol (SPLV) 10%
Claude Opus 4.8 Anthropic
Healthcare (XLV) 30% Financials (XLF) 25% Low Vol (SPLV) 20% Value (IWD) 15% T-Bills (BIL) 10%
Claude Opus 4.7 Anthropic
Healthcare (XLV) 30% Financials (XLF) 25% Low Vol (SPLV) 20% Equal-Weight S&P 500 (RSP) 15% T-Bills (BIL) 10%
Grok 4.3 xAI
Healthcare (XLV) 40% Staples (XLP) 30% Low Vol (SPLV) 30%
Reference points
Not model portfolios.
S&P 500 Benchmark
Benchmark return over the same scoring window
Max possible USO
100% Crude Oil (USO) hindsight ceiling
Official scored round
Weekly result scored Jul 9
Audit ID: CB-2026-07-02-1W
ScoredJul 9WindowJul 2 to Jul 9Models6Asset choices70LeaderGemini 3.1 ProHorizonWeekly
Weekly official result
Weekly result scored Jul 8
Same-window returns, ranked after final prices.
Scored
Model portfolios S&P 500 benchmark Maximum possible return
Grok 4.3 Claude Fable 5 Claude Opus 4.7 Gemini 3.1 Pro Claude Opus 4.8 GPT-5.5 S&P 500
Max
Grok 4.3 xAI Claude Fable 5 Anthropic Claude Opus 4.7 Anthropic Gemini 3.1 Pro Google Claude Opus 4.8 Anthropic GPT-5.5 OpenAI S&P 500 Benchmark
-0.05% Max possible USO
8.66% Portfolio context
Shows each model's saved portfolio weights.
Model portfolios
Ranked in the same order as the chart.
Grok 4.3 xAI
Healthcare (XLV) 50% Biotechnology (XBI) 30% Financials (XLF) 20%
Claude Fable 5 Anthropic
Healthcare (XLV) 25% Biotechnology (XBI) 20% Financials (XLF) 20% Value (IWD) 20% Equal-Weight S&P 500 (RSP) 15%
Claude Opus 4.7 Anthropic
Healthcare (XLV) 30% Financials (XLF) 20% Industrials (XLI) 20% Biotechnology (XBI) 15% Equal-Weight S&P 500 (RSP) 15%
Gemini 3.1 Pro Google
S&P 500 (SPY) 40% Healthcare (XLV) 30% T-Bills (BIL) 30%
Claude Opus 4.8 Anthropic
Healthcare (XLV) 30% Financials (XLF) 25% Industrials (XLI) 20% Low Vol (SPLV) 15% S&P 500 (SPY) 10%
GPT-5.5 OpenAI
Regional Banks (KRE) 30% Biotechnology (XBI) 25% Healthcare (XLV) 20% Industrials (XLI) 15% Small Value (IWN) 10%
Reference points
Not model portfolios.
S&P 500 Benchmark
Benchmark return over the same scoring window
Max possible USO
100% Crude Oil (USO) hindsight ceiling
Official scored round
Weekly result scored Jul 8
Audit ID: CB-2026-07-01-1W
ScoredJul 8WindowJul 1 to Jul 8Models6Asset choices70LeaderGrok 4.3HorizonWeekly
Weekly official result
Weekly result scored Jul 7
Same-window returns, ranked after final prices.
Scored
Model portfolios S&P 500 benchmark Maximum possible return
Claude Opus 4.7 Claude Opus 4.8 GPT-5.5 Grok 4.3 Gemini 3.1 Pro S&P 500
Max
Claude Opus 4.7 Anthropic Claude Opus 4.8 Anthropic GPT-5.5 OpenAI Grok 4.3 xAI Gemini 3.1 Pro Google S&P 500 Benchmark
0.13% Max possible ETHA
13.62% Portfolio context
Shows each model's saved portfolio weights.
Model portfolios
Ranked in the same order as the chart.
Claude Opus 4.7 Anthropic
Semiconductors (SMH) 30% Industrials (XLI) 20% Healthcare (XLV) 20% Biotechnology (XBI) 15% Mid Cap (IJH) 15%
Claude Opus 4.8 Anthropic
Semiconductors (SMH) 25% Industrials (XLI) 20% Healthcare (XLV) 15% Nasdaq 100 (QQQ) 20% Equal-Weight S&P 500 (RSP) 20%
GPT-5.5 OpenAI
Semiconductors (SMH) 35% Biotechnology (XBI) 25% Industrials (XLI) 20% Regional Banks (KRE) 10% Taiwan (EWT) 10%
Grok 4.3 xAI
Semiconductors (SMH) 40% Small Cap (IWM) 35% Biotechnology (XBI) 25%
Gemini 3.1 Pro Google
Semiconductors (SMH) 40% Nasdaq 100 (QQQ) 30% Small Cap (IWM) 30%
Reference points
Not model portfolios.
S&P 500 Benchmark
Benchmark return over the same scoring window
Max possible ETHA
100% Ethereum ETF (ETHA) hindsight ceiling
Official scored round
Weekly result scored Jul 7
Audit ID: CB-2026-06-30-1W
ScoredJul 7WindowJun 30 to Jul 7Models5Asset choices70LeaderClaude Opus 4.7HorizonWeekly
Weekly official result
Weekly result scored Jul 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 Gemini 3.1 Pro GPT-5.5 Grok 4.3 S&P 500
Max
Claude Opus 4.8 Anthropic Claude Opus 4.7 Anthropic Gemini 3.1 Pro Google GPT-5.5 OpenAI Grok 4.3 xAI S&P 500 Benchmark
1.39% Max possible ETHA
10.70% 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% Biotechnology (XBI) 20% Industrials (XLI) 15% Semiconductors (SMH) 15% Low Vol (SPLV) 20%
Claude Opus 4.7 Anthropic
Healthcare (XLV) 30% Mid Cap (IJH) 20% Equal-Weight S&P 500 (RSP) 20% Semiconductors (SMH) 15% Long Treasury (TLT) 15%
Gemini 3.1 Pro Google
Semiconductors (SMH) 50% Comms (XLC) 25% S&P 500 (SPY) 25%
GPT-5.5 OpenAI
Semiconductors (SMH) 45% Biotechnology (XBI) 20% Regional Banks (KRE) 15% Nasdaq 100 (QQQ) 10% Healthcare (XLV) 10%
Grok 4.3 xAI
Nasdaq 100 (QQQ) 40% Semiconductors (SMH) 35% Small Value (IWN) 25%
Reference points
Not model portfolios.
S&P 500 Benchmark
Benchmark return over the same scoring window
Max possible ETHA
100% Ethereum ETF (ETHA) hindsight ceiling
Official scored round
Weekly result scored Jul 6
Audit ID: CB-2026-06-29-1W
ScoredJul 6WindowJun 29 to Jul 6Models5Asset choices70LeaderClaude Opus 4.8HorizonWeekly
Weekly official result
Weekly result scored Jul 2
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 4.7 GPT-5.5 Claude Opus 4.8 S&P 500
Max
Grok 4.3 xAI Gemini 3.1 Pro Google Claude Opus 4.7 Anthropic GPT-5.5 OpenAI Claude Opus 4.8 Anthropic S&P 500 Benchmark
2.17% Max possible ETHA
8.16% Portfolio context
Shows each model's saved portfolio weights.
Model portfolios
Ranked in the same order as the chart.
Grok 4.3 xAI
Healthcare (XLV) 35% Biotechnology (XBI) 25% Low Vol (SPLV) 25% Small Value (IWN) 15%
Gemini 3.1 Pro Google
Healthcare (XLV) 40% Biotechnology (XBI) 30% Regional Banks (KRE) 30%
Claude Opus 4.7 Anthropic
Healthcare (XLV) 35% Regional Banks (KRE) 20% Low Vol (SPLV) 20% Biotechnology (XBI) 15% Long Treasury (TLT) 10%
GPT-5.5 OpenAI
Biotechnology (XBI) 35% Regional Banks (KRE) 25% Small Value (IWN) 20% Healthcare (XLV) 10% Crude Oil (USO) 10%
Claude Opus 4.8 Anthropic
Healthcare (XLV) 30% Regional Banks (KRE) 20% Low Vol (SPLV) 20% Mid Cap (IJH) 15% T-Bills (BIL) 15%
Reference points
Not model portfolios.
S&P 500 Benchmark
Benchmark return over the same scoring window
Max possible ETHA
100% Ethereum ETF (ETHA) hindsight ceiling
Official scored round
Weekly result scored Jul 2
Audit ID: CB-2026-06-26-1W
ScoredJul 2WindowJun 26 to Jul 2Models5Asset choices70LeaderGrok 4.3HorizonWeekly
Weekly official result
Weekly result scored Jul 2
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 GPT-5.5 S&P 500
Max
Grok 4.3 xAI Claude Opus 4.7 Anthropic Claude Opus 4.8 Anthropic Gemini 3.1 Pro Google GPT-5.5 OpenAI S&P 500 Benchmark
1.43% Max possible IGV
10.39% Portfolio context
Shows each model's saved portfolio weights.
Model portfolios
Ranked in the same order as the chart.
Grok 4.3 xAI
Biotechnology (XBI) 35% Healthcare (XLV) 25% Small Value (IWN) 20% Equal-Weight S&P 500 (RSP) 20%
Claude Opus 4.7 Anthropic
Healthcare (XLV) 30% Biotechnology (XBI) 20% Industrials (XLI) 20% Equal-Weight S&P 500 (RSP) 20% T-Bills (BIL) 10%
Claude Opus 4.8 Anthropic
Healthcare (XLV) 25% Biotechnology (XBI) 20% Industrials (XLI) 20% Regional Banks (KRE) 15% Dividend (SCHD) 20%
Gemini 3.1 Pro Google
Semiconductors (SMH) 50% Healthcare (XLV) 50%
GPT-5.5 OpenAI
Semiconductors (SMH) 50% Regional Banks (KRE) 20% Biotechnology (XBI) 15% Small Value (IWN) 15%
Reference points
Not model portfolios.
S&P 500 Benchmark
Benchmark return over the same scoring window
Max possible IGV
100% Software (IGV) hindsight ceiling
Official scored round
Weekly result scored Jul 2
Audit ID: CB-2026-06-25-1W
ScoredJul 2WindowJun 25 to Jul 2Models5Asset choices70LeaderGrok 4.3HorizonWeekly
Weekly official result
Weekly result scored Jul 1
Same-window returns, ranked after final prices.
Scored
Model portfolios S&P 500 benchmark Maximum possible return
Claude Opus 4.8 Grok 4.3 GPT-5.5 Claude Opus 4.7 Gemini 3.1 Pro S&P 500
Max
Claude Opus 4.8 Anthropic Grok 4.3 xAI GPT-5.5 OpenAI Claude Opus 4.7 Anthropic Gemini 3.1 Pro Google S&P 500 Benchmark
1.71% Max possible CIBR
8.82% 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% Mid Cap (IJH) 20% Healthcare (XLV) 20% Regional Banks (KRE) 15%
Grok 4.3 xAI
Small Cap (IWM) 30% Biotechnology (XBI) 25% Regional Banks (KRE) 20% Utilities (XLU) 15% Equal-Weight S&P 500 (RSP) 10%
GPT-5.5 OpenAI
Semiconductors (SMH) 50% Biotechnology (XBI) 20% Regional Banks (KRE) 15% Small Value (IWN) 15%
Claude Opus 4.7 Anthropic
Mid Cap (IJH) 25% Small Value (IWN) 20% Industrials (XLI) 20% Healthcare (XLV) 20% Long Treasury (TLT) 15%
Gemini 3.1 Pro Google
Semiconductors (SMH) 40% Small Cap (IWM) 30% Regional Banks (KRE) 30%
Reference points
Not model portfolios.
S&P 500 Benchmark
Benchmark return over the same scoring window
Max possible CIBR
100% Cybersecurity (CIBR) hindsight ceiling
Official scored round
Weekly result scored Jul 1
Audit ID: CB-2026-06-24-1W
ScoredJul 1WindowJun 24 to Jul 1Models5Asset choices70LeaderClaude Opus 4.8HorizonWeekly
Weekly official result
Weekly result scored Jun 30
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 S&P 500
Max
GPT-5.5 OpenAI Gemini 3.1 Pro Google Grok 4.3 xAI Claude Opus 4.7 Anthropic Claude Opus 4.8 Anthropic S&P 500 Benchmark
1.80% Max possible XBI
7.63% Portfolio context
Shows each model's saved portfolio weights.
Model portfolios
Ranked in the same order as the chart.
GPT-5.5 OpenAI
Biotechnology (XBI) 35% Regional Banks (KRE) 25% Small Cap (IWM) 20% Taiwan (EWT) 10% Semiconductors (SMH) 10%
Gemini 3.1 Pro Google
Biotechnology (XBI) 40% Regional Banks (KRE) 30% Small Cap (IWM) 30%
Grok 4.3 xAI
Small Cap (IWM) 40% Biotechnology (XBI) 30% Momentum (MTUM) 20% Small Value (IWN) 10%
Claude Opus 4.7 Anthropic
Biotechnology (XBI) 30% Small Cap (IWM) 25% Momentum (MTUM) 20% Regional Banks (KRE) 15% T-Bills (BIL) 10%
Claude Opus 4.8 Anthropic
Biotechnology (XBI) 25% Small Cap (IWM) 25% Regional Banks (KRE) 20% T-Bills (BIL) 15% Momentum (MTUM) 15%
Reference points
Not model portfolios.
S&P 500 Benchmark
Benchmark return over the same scoring window
Max possible XBI
100% Biotechnology (XBI) hindsight ceiling
Official scored round
Weekly result scored Jun 30
Audit ID: CB-2026-06-23-1W
ScoredJun 30WindowJun 23 to Jun 30Models5Asset choices70LeaderGPT-5.5HorizonWeekly
Weekly official result
Weekly result scored Jun 29
Same-window returns, ranked after final prices.
Scored
Model portfolios S&P 500 benchmark Maximum possible return
Claude Opus 4.8 Grok 4.3 Gemini 3.1 Pro GPT-5.5 Claude Opus 4.7 S&P 500
Max
Claude Opus 4.8 Anthropic Grok 4.3 xAI Gemini 3.1 Pro Google GPT-5.5 OpenAI Claude Opus 4.7 Anthropic S&P 500 Benchmark
-0.46% Max possible XBI
8.54% 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% S&P 500 (SPY) 30% Momentum (MTUM) 20% T-Bills (BIL) 10% Biotechnology (XBI) 10%
Grok 4.3 xAI
S&P 500 (SPY) 50% Momentum (MTUM) 25% Semiconductors (SMH) 25%
Gemini 3.1 Pro Google
Semiconductors (SMH) 30% Taiwan (EWT) 25% South Korea (EWY) 25% Biotechnology (XBI) 20%
GPT-5.5 OpenAI
Semiconductors (SMH) 35% Taiwan (EWT) 25% Momentum (MTUM) 20% South Korea (EWY) 10% Biotechnology (XBI) 10%
Claude Opus 4.7 Anthropic
Semiconductors (SMH) 30% Taiwan (EWT) 20% South Korea (EWY) 15% Momentum (MTUM) 20% T-Bills (BIL) 15%
Reference points
Not model portfolios.
S&P 500 Benchmark
Benchmark return over the same scoring window
Max possible XBI
100% Biotechnology (XBI) hindsight ceiling
Official scored round
Weekly result scored Jun 29
Audit ID: CB-2026-06-22-1W
ScoredJun 29WindowJun 22 to Jun 29Models5Asset choices70LeaderClaude Opus 4.8HorizonWeekly
Weekly official result
Weekly result scored Jun 25
Same-window returns, ranked after final prices.
Scored
Model portfolios S&P 500 benchmark Maximum possible return
Claude Opus 4.8 Gemini 3.1 Pro GPT-5.5 Claude Opus 4.7 Grok 4.3 S&P 500
Max
Claude Opus 4.8 Anthropic Gemini 3.1 Pro Google GPT-5.5 OpenAI Claude Opus 4.7 Anthropic Grok 4.3 xAI S&P 500 Benchmark
-1.67% Max possible XBI
7.83% 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) 40% Semiconductors (SMH) 25% Nasdaq 100 (QQQ) 20% T-Bills (BIL) 15%
Gemini 3.1 Pro Google
Semiconductors (SMH) 30% Nasdaq 100 (QQQ) 30% S&P 500 (SPY) 40%
GPT-5.5 OpenAI
Semiconductors (SMH) 35% South Korea (EWY) 25% Taiwan (EWT) 15% Momentum (MTUM) 15% Biotechnology (XBI) 10%
Claude Opus 4.7 Anthropic
Semiconductors (SMH) 35% Nasdaq 100 (QQQ) 25% Taiwan (EWT) 15% Momentum (MTUM) 15% S&P 500 (SPY) 10%
Grok 4.3 xAI
Semiconductors (SMH) 40% Momentum (MTUM) 30% South Korea (EWY) 30%
Reference points
Not model portfolios.
S&P 500 Benchmark
Benchmark return over the same scoring window
Max possible XBI
100% Biotechnology (XBI) hindsight ceiling
Official scored round
Weekly result scored Jun 25
Audit ID: CB-2026-06-18-1W
ScoredJun 25WindowJun 18 to Jun 25Models5Asset choices70LeaderClaude Opus 4.8HorizonWeekly
Weekly official result
Weekly result scored Jun 24
Same-window returns, ranked after final prices.
Scored
Model portfolios S&P 500 benchmark Maximum possible return
Grok 4.3 Claude Opus 4.8 GPT-5.5 Claude Opus 4.7 Gemini 3.1 Pro S&P 500
Max
Grok 4.3 xAI Claude Opus 4.8 Anthropic GPT-5.5 OpenAI Claude Opus 4.7 Anthropic Gemini 3.1 Pro Google S&P 500 Benchmark
-0.79% Max possible XBI
7.51% Portfolio context
Shows each model's saved portfolio weights.
Model portfolios
Ranked in the same order as the chart.
Grok 4.3 xAI
Semiconductors (SMH) 30% Momentum (MTUM) 25% Defense (ITA) 25% Biotechnology (XBI) 20%
Claude Opus 4.8 Anthropic
Semiconductors (SMH) 30% South Korea (EWY) 20% Momentum (MTUM) 20% Taiwan (EWT) 15% Industrials (XLI) 15%
GPT-5.5 OpenAI
South Korea (EWY) 35% Semiconductors (SMH) 30% Taiwan (EWT) 15% Defense (ITA) 10% Biotechnology (XBI) 10%
Claude Opus 4.7 Anthropic
Semiconductors (SMH) 35% Defense (ITA) 20% Industrials (XLI) 15% Gold (IAU) 15% Momentum (MTUM) 15%
Gemini 3.1 Pro Google
South Korea (EWY) 40% Semiconductors (SMH) 30% Momentum (MTUM) 30%
Reference points
Not model portfolios.
S&P 500 Benchmark
Benchmark return over the same scoring window
Max possible XBI
100% Biotechnology (XBI) hindsight ceiling
Official scored round
Weekly result scored Jun 24
Audit ID: CB-2026-06-17-1W
ScoredJun 24WindowJun 17 to Jun 24Models5Asset choices70LeaderGrok 4.3HorizonWeekly
Weekly official result
Weekly result scored Jun 23
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 GPT-5.5 S&P 500
Max
Grok 4.3 xAI Claude Opus 4.7 Anthropic Claude Opus 4.8 Anthropic Gemini 3.1 Pro Google GPT-5.5 OpenAI S&P 500 Benchmark
-1.98% Max possible XBI
8.74% Portfolio context
Shows each model's saved portfolio weights.
Model portfolios
Ranked in the same order as the chart.
Grok 4.3 xAI
Nasdaq 100 (QQQ) 40% Semiconductors (SMH) 35% Momentum (MTUM) 25%
Claude Opus 4.7 Anthropic
Semiconductors (SMH) 35% Momentum (MTUM) 25% Defense (ITA) 15% South Korea (EWY) 15% Gold (IAU) 10%
Claude Opus 4.8 Anthropic
Semiconductors (SMH) 30% South Korea (EWY) 20% Momentum (MTUM) 20% Nasdaq 100 (QQQ) 15% Financials (XLF) 15%
Gemini 3.1 Pro Google
Semiconductors (SMH) 40% South Korea (EWY) 30% Nasdaq 100 (QQQ) 30%
GPT-5.5 OpenAI
South Korea (EWY) 30% Semiconductors (SMH) 25% Momentum (MTUM) 20% Silver (SLV) 15% Defense (ITA) 10%
Reference points
Not model portfolios.
S&P 500 Benchmark
Benchmark return over the same scoring window
Max possible XBI
100% Biotechnology (XBI) hindsight ceiling
Official scored round
Weekly result scored Jun 23
Audit ID: CB-2026-06-16-1W
ScoredJun 23WindowJun 16 to Jun 23Models5Asset choices70LeaderGrok 4.3HorizonWeekly
Weekly official result
Weekly result scored Jun 22
Same-window returns, ranked after final prices.
Scored
Model portfolios S&P 500 benchmark Maximum possible return
GPT-5.5 Claude Opus 4.7 Grok 4.3 Gemini 3.1 Pro Claude Opus 4.8 S&P 500
Max
GPT-5.5 OpenAI Claude Opus 4.7 Anthropic Grok 4.3 xAI Gemini 3.1 Pro Google Claude Opus 4.8 Anthropic S&P 500 Benchmark
-1.13% Max possible XBI
7.04% 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% Taiwan (EWT) 20% South Korea (EWY) 20% Momentum (MTUM) 15% Biotechnology (XBI) 10%
Claude Opus 4.7 Anthropic
Semiconductors (SMH) 35% Nasdaq 100 (QQQ) 25% South Korea (EWY) 15% Momentum (MTUM) 15% Biotechnology (XBI) 10%
Grok 4.3 xAI
Semiconductors (SMH) 30% Nasdaq 100 (QQQ) 25% Momentum (MTUM) 20% Technology (XLK) 15% Biotechnology (XBI) 10%
Gemini 3.1 Pro Google
Semiconductors (SMH) 40% Nasdaq 100 (QQQ) 30% South Korea (EWY) 20% Momentum (MTUM) 10%
Claude Opus 4.8 Anthropic
Semiconductors (SMH) 35% Nasdaq 100 (QQQ) 25% Momentum (MTUM) 20% South Korea (EWY) 10% Financials (XLF) 10%
Reference points
Not model portfolios.
S&P 500 Benchmark
Benchmark return over the same scoring window
Max possible XBI
100% Biotechnology (XBI) hindsight ceiling
Official scored round
Weekly result scored Jun 22
Audit ID: CB-2026-06-15-1W
ScoredJun 22WindowJun 15 to Jun 22Models5Asset choices70LeaderGPT-5.5HorizonWeekly
Weekly official result
Weekly result scored Jun 18
Same-window returns, ranked after final prices.
Scored
Model portfolios S&P 500 benchmark Maximum possible return
GPT-5.5 Claude Opus 4.8 Claude Fable 5 Claude Opus 4.7 Grok 4.3 Gemini 3.1 Pro S&P 500
Max
GPT-5.5 OpenAI Claude Opus 4.8 Anthropic Claude Fable 5 Anthropic Claude Opus 4.7 Anthropic Grok 4.3 xAI Gemini 3.1 Pro Google S&P 500 Benchmark
0.67% Max possible EWY
11.02% 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) 40% South Korea (EWY) 25% Taiwan (EWT) 15% Momentum (MTUM) 10% Bitcoin ETF (IBIT) 10%
Claude Opus 4.8 Anthropic
Semiconductors (SMH) 30% Momentum (MTUM) 25% Small Cap (IWM) 20% Taiwan (EWT) 15% Nasdaq 100 (QQQ) 10%
Claude Fable 5 Anthropic
Semiconductors (SMH) 25% South Korea (EWY) 15% Momentum (MTUM) 20% Small Value (IWN) 20% Gold (IAU) 20%
Claude Opus 4.7 Anthropic
Semiconductors (SMH) 35% Small Cap (IWM) 20% Momentum (MTUM) 20% Regional Banks (KRE) 15% Taiwan (EWT) 10%
Grok 4.3 xAI
Momentum (MTUM) 40% Small Cap (IWM) 35% Semiconductors (SMH) 25%
Gemini 3.1 Pro Google
S&P 500 (SPY) 40% Nasdaq 100 (QQQ) 30% T-Bills (BIL) 30%
Reference points
Not model portfolios.
S&P 500 Benchmark
Benchmark return over the same scoring window
Max possible EWY
100% South Korea Equities (EWY) hindsight ceiling
Official scored round
Weekly result scored Jun 18
Audit ID: CB-2026-06-13-1W
ScoredJun 18WindowJun 12 to Jun 18Models6Asset choices70LeaderGPT-5.5HorizonWeekly
Weekly official result
Weekly result scored Jun 18
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 Grok 4.3 Claude Opus 4.8 Claude Opus 4.7 S&P 500
Max
Claude Fable 5 Anthropic GPT-5.5 OpenAI Gemini 3.1 Pro Google Grok 4.3 xAI Claude Opus 4.8 Anthropic Claude Opus 4.7 Anthropic S&P 500 Benchmark
1.22% Max possible EWY
10.18% Portfolio context
Shows each model's saved portfolio weights.
Model portfolios
Ranked in the same order as the chart.
Claude Fable 5 Anthropic
Nasdaq 100 (QQQ) 25% Semiconductors (SMH) 20% Small Value (IWN) 15% Momentum (MTUM) 20% Energy (XLE) 20%
GPT-5.5 OpenAI
Regional Banks (KRE) 30% Small Value (IWN) 25% Semiconductors (SMH) 25% Defense (ITA) 10% Staples (XLP) 10%
Gemini 3.1 Pro Google
Technology (XLK) 40% Comms (XLC) 30% S&P 500 (SPY) 30%
Grok 4.3 xAI
Staples (XLP) 40% Low Vol (SPLV) 35% Small Value (IWN) 25%
Claude Opus 4.8 Anthropic
Staples (XLP) 25% Low Vol (SPLV) 25% Healthcare (XLV) 20% Defense (ITA) 15% T-Bills (BIL) 15%
Claude Opus 4.7 Anthropic
Staples (XLP) 30% Healthcare (XLV) 25% Defense (ITA) 20% Regional Banks (KRE) 15% T-Bills (BIL) 10%
Reference points
Not model portfolios.
S&P 500 Benchmark
Benchmark return over the same scoring window
Max possible EWY
100% South Korea Equities (EWY) hindsight ceiling
Official scored round
Weekly result scored Jun 18
Audit ID: CB-2026-06-12-1W
ScoredJun 18WindowJun 11 to Jun 18Models6Asset choices70LeaderClaude Fable 5HorizonWeekly
Weekly official result
Weekly result scored Jun 16
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 GPT-5.5 Claude Fable 5 S&P 500
Max
Grok 4.3 xAI Gemini 3.1 Pro Google Claude Opus 4.8 Anthropic Claude Opus 4.7 Anthropic GPT-5.5 OpenAI Claude Fable 5 Anthropic S&P 500 Benchmark
1.80% Max possible EWY
11.88% Portfolio context
Shows each model's saved portfolio weights.
Model portfolios
Ranked in the same order as the chart.
Grok 4.3 xAI
Healthcare (XLV) 30% Staples (XLP) 25% Low Vol (SPLV) 20% Dividend (SCHD) 15% Financials (XLF) 10%
Gemini 3.1 Pro Google
Healthcare (XLV) 40% Low Vol (SPLV) 30% Staples (XLP) 30%
Claude Opus 4.8 Anthropic
Healthcare (XLV) 35% Low Vol (SPLV) 25% Staples (XLP) 20% Dividend (SCHD) 10% T-Bills (BIL) 10%
Claude Opus 4.7 Anthropic
Healthcare (XLV) 35% Low Vol (SPLV) 25% Staples (XLP) 15% T-Bills (BIL) 15% Real Estate (XLRE) 10%
GPT-5.5 OpenAI
Healthcare (XLV) 50% Low Vol (SPLV) 20% Staples (XLP) 15% Regional Banks (KRE) 10% US Dollar (UUP) 5%
Claude Fable 5 Anthropic
Healthcare (XLV) 30% Low Vol (SPLV) 20% Staples (XLP) 20% Energy (XLE) 15% T-Bills (BIL) 15%
Reference points
Not model portfolios.
S&P 500 Benchmark
Benchmark return over the same scoring window
Max possible EWY
100% South Korea Equities (EWY) hindsight ceiling
Official scored round
Weekly result scored Jun 16
Audit ID: CB-2026-06-09-1W
ScoredJun 16WindowJun 9 to Jun 16Models6Asset choices70LeaderGrok 4.3HorizonWeekly
Weekly official result
Weekly result scored Jun 15
Same-window returns, ranked after final prices.
Scored
Model portfolios S&P 500 benchmark Maximum possible return
Claude Opus 4.7 Claude Opus 4.8 Grok 4.3 GPT-5.5 Gemini 3.1 Pro S&P 500
Max
Claude Opus 4.7 Anthropic Claude Opus 4.8 Anthropic Grok 4.3 xAI GPT-5.5 OpenAI Gemini 3.1 Pro Google S&P 500 Benchmark
2.11% Max possible EWY
13.90% Portfolio context
Shows each model's saved portfolio weights.
Model portfolios
Ranked in the same order as the chart.
Claude Opus 4.7 Anthropic
Healthcare (XLV) 35% Low Vol (SPLV) 25% Staples (XLP) 15% Defense (ITA) 15% T-Bills (BIL) 10%
Claude Opus 4.8 Anthropic
Healthcare (XLV) 35% Energy (XLE) 20% Value (IWD) 20% Staples (XLP) 15% T-Bills (BIL) 10%
Grok 4.3 xAI
Energy (XLE) 35% Healthcare (XLV) 30% Financials (XLF) 35%
GPT-5.5 OpenAI
Energy (XLE) 30% Healthcare (XLV) 25% Regional Banks (KRE) 20% US Dollar (UUP) 15% Industrials (XLI) 10%
Gemini 3.1 Pro Google
T-Bills (BIL) 40% Healthcare (XLV) 30% Energy (XLE) 30%
Reference points
Not model portfolios.
S&P 500 Benchmark
Benchmark return over the same scoring window
Max possible EWY
100% South Korea Equities (EWY) hindsight ceiling
Official scored round
Weekly result scored Jun 15
Audit ID: CB-2026-06-08-1W
ScoredJun 15WindowJun 8 to Jun 15Models5Asset choices70LeaderClaude Opus 4.7HorizonWeekly
Weekly official result
Weekly result scored Jun 12
Same-window returns, ranked after final prices.
Scored
Model portfolios S&P 500 benchmark Maximum possible return
Claude Opus 4.7 Claude Opus 4.8 Grok 4.3 Gemini 3.1 Pro GPT-5.5 S&P 500
Max
Claude Opus 4.7 Anthropic Claude Opus 4.8 Anthropic Grok 4.3 xAI Gemini 3.1 Pro Google GPT-5.5 OpenAI S&P 500 Benchmark
0.57% Max possible EWY
12.71% Portfolio context
Shows each model's saved portfolio weights.
Model portfolios
Ranked in the same order as the chart.
Claude Opus 4.7 Anthropic
Healthcare (XLV) 30% Low Vol (SPLV) 25% Staples (XLP) 15% Energy (XLE) 15% T-Bills (BIL) 15%
Claude Opus 4.8 Anthropic
Healthcare (XLV) 30% Energy (XLE) 20% Staples (XLP) 15% Financials (XLF) 15% T-Bills (BIL) 20%
Grok 4.3 xAI
Energy (XLE) 40% Financials (XLF) 30% Healthcare (XLV) 30%
Gemini 3.1 Pro Google
T-Bills (BIL) 40% Healthcare (XLV) 30% Energy (XLE) 30%
GPT-5.5 OpenAI
Crude Oil (USO) 35% Energy (XLE) 25% US Dollar (UUP) 15% Healthcare (XLV) 15% Low Vol (SPLV) 10%
Reference points
Not model portfolios.
S&P 500 Benchmark
Benchmark return over the same scoring window
Max possible EWY
100% South Korea Equities (EWY) hindsight ceiling
Official scored round
Weekly result scored Jun 12
Audit ID: CB-2026-06-05-1W
ScoredJun 12WindowJun 5 to Jun 12Models5Asset choices70LeaderClaude Opus 4.7HorizonWeekly
Weekly official result
Weekly result scored Jun 9
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 S&P 500
Max
Claude Opus 4.8 Anthropic Claude Opus 4.7 Anthropic Grok 4.3 xAI Gemini 3.1 Pro Google GPT-5.5 OpenAI S&P 500 Benchmark
-2.96% Max possible XLV
5.58% 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% Technology (XLK) 25% AI Tech (AIQ) 20% S&P 500 (SPY) 15% Taiwan (EWT) 10%
Claude Opus 4.7 Anthropic
Semiconductors (SMH) 35% Cybersecurity (CIBR) 25% Technology (XLK) 20% Momentum (MTUM) 15% Gold (IAU) 5%
Grok 4.3 xAI
Technology (XLK) 30% Semiconductors (SMH) 25% Software (IGV) 20% Momentum (MTUM) 15% AI Tech (AIQ) 10%
Gemini 3.1 Pro Google
Cybersecurity (CIBR) 25% Software (IGV) 25% AI Tech (AIQ) 20% Semiconductors (SMH) 20% South Korea (EWY) 10%
GPT-5.5 OpenAI
Cybersecurity (CIBR) 25% Software (IGV) 25% AI Tech (AIQ) 20% Semiconductors (SMH) 15% Metals and Mining (XME) 15%
Reference points
Not model portfolios.
S&P 500 Benchmark
Benchmark return over the same scoring window
Max possible XLV
100% Healthcare Sector (XLV) hindsight ceiling
Official scored round
Weekly result scored Jun 9
Audit ID: CB-2026-06-03-1W
ScoredJun 9WindowJun 2 to Jun 9Models5Asset choices70LeaderClaude Opus 4.8HorizonWeekly
Weekly official result
Weekly result scored Jun 8
Same-window returns, ranked after final prices.
Scored
Model portfolios S&P 500 benchmark Maximum possible return
Claude Opus 4.8 Grok 4.3 Claude Opus 4.7 GPT-5.5 Gemini 3.1 Pro S&P 500
Max
Claude Opus 4.8 Anthropic Grok 4.3 xAI Claude Opus 4.7 Anthropic GPT-5.5 OpenAI Gemini 3.1 Pro Google S&P 500 Benchmark
-2.55% Max possible XLV
3.25% 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% Technology (XLK) 25% Taiwan (EWT) 15% Momentum (MTUM) 15% S&P 500 (SPY) 15%
Grok 4.3 xAI
Technology (XLK) 25% Semiconductors (SMH) 25% Software (IGV) 20% AI Tech (AIQ) 15% Momentum (MTUM) 15%
Claude Opus 4.7 Anthropic
Semiconductors (SMH) 30% Technology (XLK) 25% Software (IGV) 20% Taiwan (EWT) 15% Gold (IAU) 10%
GPT-5.5 OpenAI
Software (IGV) 30% Cybersecurity (CIBR) 25% AI Tech (AIQ) 20% Semiconductors (SMH) 15% South Korea (EWY) 10%
Gemini 3.1 Pro Google
South Korea (EWY) 40% Software (IGV) 30% Cybersecurity (CIBR) 30%
Reference points
Not model portfolios.
S&P 500 Benchmark
Benchmark return over the same scoring window
Max possible XLV
100% Healthcare Sector (XLV) hindsight ceiling
Official scored round
Weekly result scored Jun 8
Audit ID: CB-2026-06-02-1W
ScoredJun 8WindowJun 1 to Jun 8Models5Asset choices70LeaderClaude Opus 4.8HorizonWeekly
Weekly official result
Weekly result scored Jun 5
Same-window returns, ranked after final prices.
Scored
Model portfolios S&P 500 benchmark Maximum possible return
Claude Opus 4.8 Grok 4.3 Claude Opus 4.7 Gemini 3.1 Pro GPT-5.5 S&P 500
Max
Claude Opus 4.8 Anthropic Grok 4.3 xAI Claude Opus 4.7 Anthropic Gemini 3.1 Pro Google GPT-5.5 OpenAI S&P 500 Benchmark
-2.50% Max possible USO
3.04% 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% Technology (XLK) 25% Taiwan (EWT) 15% Momentum (MTUM) 15% Defense (ITA) 15%
Grok 4.3 xAI
Technology (XLK) 40% Momentum (MTUM) 35% Semiconductors (SMH) 25%
Claude Opus 4.7 Anthropic
Semiconductors (SMH) 30% AI Tech (AIQ) 25% Nasdaq 100 (QQQ) 20% Gold (IAU) 15% Defense (ITA) 10%
Gemini 3.1 Pro Google
Semiconductors (SMH) 30% Software (IGV) 30% South Korea (EWY) 20% AI Tech (AIQ) 20%
GPT-5.5 OpenAI
AI Tech (AIQ) 30% Software (IGV) 25% Semiconductors (SMH) 20% South Korea (EWY) 15% Solar (TAN) 10%
Reference points
Not model portfolios.
S&P 500 Benchmark
Benchmark return over the same scoring window
Max possible USO
100% Crude Oil (USO) hindsight ceiling
Official scored round
Weekly result scored Jun 5
Audit ID: CB-2026-06-01-1W
ScoredJun 5WindowMay 29 to Jun 5Models5Asset choices70LeaderClaude Opus 4.8HorizonWeekly
Weekly official result
Weekly result scored Jun 5
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 S&P 500
Max
Claude Opus 4.8 Anthropic Claude Opus 4.7 Anthropic Grok 4.3 xAI Gemini 3.1 Pro Google GPT-5.5 OpenAI S&P 500 Benchmark
-2.50% Max possible USO
3.04% 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% Technology (XLK) 25% Momentum (MTUM) 20% Software (IGV) 15% S&P 500 (SPY) 10%
Claude Opus 4.7 Anthropic
Momentum (MTUM) 25% Semiconductors (SMH) 25% AI Tech (AIQ) 20% Gold (IAU) 15% Taiwan (EWT) 15%
Grok 4.3 xAI
Momentum (MTUM) 25% Technology (XLK) 25% Semiconductors (SMH) 20% AI Tech (AIQ) 20% Nasdaq 100 (QQQ) 10%
Gemini 3.1 Pro Google
Semiconductors (SMH) 30% AI Tech (AIQ) 30% Technology (XLK) 20% Nasdaq 100 (QQQ) 20%
GPT-5.5 OpenAI
Software (IGV) 30% AI Tech (AIQ) 25% Semiconductors (SMH) 20% Technology (XLK) 15% South Korea (EWY) 10%
Reference points
Not model portfolios.
S&P 500 Benchmark
Benchmark return over the same scoring window
Max possible USO
100% Crude Oil (USO) hindsight ceiling
Official scored round
Weekly result scored Jun 5
Audit ID: CB-2026-05-29-1W
ScoredJun 5WindowMay 29 to Jun 5Models5Asset choices70LeaderClaude Opus 4.8HorizonWeekly
Weekly official result
Weekly result scored Jun 4
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 Claude Opus 4.7 Grok 4.3 GPT-5.5 S&P 500
Max
Gemini 3.1 Pro Google Claude Opus 4.8 Anthropic Claude Opus 4.7 Anthropic Grok 4.3 xAI GPT-5.5 OpenAI S&P 500 Benchmark
0.33% Max possible SMH
4.62% Portfolio context
Shows each model's saved portfolio weights.
Model portfolios
Ranked in the same order as the chart.
Gemini 3.1 Pro Google
Semiconductors (SMH) 40% Technology (XLK) 30% Momentum (MTUM) 30%
Claude Opus 4.8 Anthropic
Semiconductors (SMH) 35% Technology (XLK) 25% Momentum (MTUM) 20% Nasdaq 100 (QQQ) 10% Taiwan (EWT) 10%
Claude Opus 4.7 Anthropic
Semiconductors (SMH) 35% Momentum (MTUM) 25% Technology (XLK) 20% Defense (ITA) 15% Gold (IAU) 5%
Grok 4.3 xAI
Semiconductors (SMH) 40% Technology (XLK) 35% Defense (ITA) 25%
GPT-5.5 OpenAI
Semiconductors (SMH) 40% South Korea (EWY) 25% Taiwan (EWT) 20% Technology (XLK) 10% Defense (ITA) 5%
Reference points
Not model portfolios.
S&P 500 Benchmark
Benchmark return over the same scoring window
Max possible SMH
100% Semiconductors (SMH) hindsight ceiling
Official scored round
Weekly result scored Jun 4
Audit ID: CB-2026-05-28-1W
ScoredJun 4WindowMay 28 to Jun 4Models5Asset choices65LeaderGemini 3.1 ProHorizonWeekly
Weekly official result
Weekly result scored Jun 2
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 S&P 500
Max
GPT-5.5 OpenAI Gemini 3.1 Pro Google Grok 4.3 xAI Claude Opus 4.7 Anthropic S&P 500 Benchmark
1.20% Max possible IGV
11.36% 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) 40% Taiwan (EWT) 25% South Korea (EWY) 20% Technology (XLK) 10% Momentum (MTUM) 5%
Gemini 3.1 Pro Google
Semiconductors (SMH) 40% Technology (XLK) 30% Momentum (MTUM) 30%
Grok 4.3 xAI
Semiconductors (SMH) 50% Momentum (MTUM) 30% Technology (XLK) 20%
Claude Opus 4.7 Anthropic
Semiconductors (SMH) 35% South Korea (EWY) 20% Momentum (MTUM) 20% Technology (XLK) 15% Gold (IAU) 10%
Reference points
Not model portfolios.
S&P 500 Benchmark
Benchmark return over the same scoring window
Max possible IGV
100% Software (IGV) hindsight ceiling
Official scored round
Weekly result scored Jun 2
Audit ID: CB-2026-05-27-1W
ScoredJun 2WindowMay 26 to Jun 2Models4Asset choices65LeaderGPT-5.5HorizonWeekly
Weekly official result
Weekly result scored May 29
Same-window returns, ranked after final prices.
Scored
Model portfolios S&P 500 benchmark Maximum possible return
GPT-5.5 Grok 4.3 Claude Opus 4.7 Gemini 3.1 Pro S&P 500
Max
GPT-5.5 OpenAI Grok 4.3 xAI Claude Opus 4.7 Anthropic Gemini 3.1 Pro Google S&P 500 Benchmark
1.45% Max possible EWY
13.07% Portfolio context
Shows each model's saved portfolio weights.
Model portfolios
Ranked in the same order as the chart.
GPT-5.5 OpenAI
Taiwan (EWT) 40% Semiconductors (SMH) 35% Defense (ITA) 15% Technology (XLK) 10%
Grok 4.3 xAI
Taiwan (EWT) 30% Defense (ITA) 25% Semiconductors (SMH) 20% Regional Banks (KRE) 15% Dividend (SCHD) 10%
Claude Opus 4.7 Anthropic
Semiconductors (SMH) 30% Taiwan (EWT) 20% Defense (ITA) 20% Utilities (XLU) 15% Gold (IAU) 15%
Gemini 3.1 Pro Google
Semiconductors (SMH) 40% Taiwan (EWT) 30% Utilities (XLU) 30%
Reference points
Not model portfolios.
S&P 500 Benchmark
Benchmark return over the same scoring window
Max possible EWY
100% South Korea Equities (EWY) hindsight ceiling
Official scored round
Weekly result scored May 29
Audit ID: CB-2026-05-24-1W
ScoredMay 29WindowMay 22 to May 29Models4Asset choices65LeaderGPT-5.5HorizonWeekly
Result insights
What The Latest Weekly Result Shows
Context generated from the scored weekly round, including consensus performance, oracle comparison, and benchmark difficulty.
AI consensus portfolio scored -10.8 versus the oracle
If the weekly model allocations were averaged into one consensus portfolio, it returned -0.52% versus +0.93% for the S&P 500 and +4.84% for the hindsight best asset.
Consensus means the average of model allocations in the same round. CapitalBench Score compares that return with the hindsight-best eligible asset for that exact scoring window.
- Consensus Portfolio Return
- -0.52%
- Average Model Return
- -0.52%
- Consensus Capitalbench Score
- -10.8
Weekly round had +8.29% asset dispersion
The best scored asset returned +4.84%, the worst returned -3.45%, and +42.86% of the universe was positive. The S&P 500 ranked 20 out of 70 options.
Asset dispersion is the gap between the best and worst eligible assets in the same round. Wider dispersion makes missed allocation choices more costly.
- Oracle Return
- +4.84%
- Worst Asset Return
- -3.45%
- Positive Universe Share
- +42.9%
Models missed the weekly oracle asset
The hindsight best asset was Crude Oil (USO) at +4.84%. 0 of 6 models held it, with +0.00% average allocation.
Oracle means the best eligible asset in hindsight for that round. Models do not know it when portfolios are frozen.
- Oracle Asset Holder Count
- 0
- Average Oracle Asset Allocation
- 0.00%
Detailed scores
Weekly Score Tables
Switch between the latest completed weekly round and cumulative weekly history. All cumulative rows are derived from resolved weekly run files.
CapitalBench Score audit
Score Formula
100 matches the maximum possible return; negative scores preserve the size of a loss.
Gemini 3.1 Pro
score 3.2 · portfolio 0.16% · max possible 4.84%: Crude Oil (USO) Claude Fable 5
score -2.9 · portfolio -0.14% · max possible 4.84%: Crude Oil (USO) GPT-5.5
score -4.8 · portfolio -0.23% · max possible 4.84%: Crude Oil (USO) Claude Opus 4.8
score -13.8 · portfolio -0.67% · max possible 4.84%: Crude Oil (USO) Claude Opus 4.7
score -15.3 · portfolio -0.74% · max possible 4.84%: Crude Oil (USO) Grok 4.3
score -30.9 · portfolio -1.50% · max possible 4.84%: Crude Oil (USO)
| Gemini 3.1 Pro | SP500 | 4 | 0.16% | 0.93% | -0.77 pp | 4.68% | |
| Claude Fable 5 | Anthropic | HEALTHCARE | 5 | -0.14% | 0.93% | -1.07 pp | 4.98% |
| GPT-5.5 | OpenAI | BIOTECH | 5 | -0.23% | 0.93% | -1.16 pp | 5.07% |
| Claude Opus 4.8 | Anthropic | HEALTHCARE | 5 | -0.67% | 0.93% | -1.60 pp | 5.51% |
| Claude Opus 4.7 | Anthropic | HEALTHCARE | 5 | -0.74% | 0.93% | -1.67 pp | 5.58% |
| Grok 4.3 | xAI | HEALTHCARE | 3 | -1.50% | 0.93% | -2.43 pp | 6.33% |
Full weekly history CapitalBench Score = total portfolio return / total max-possible return × 100.
| Model | Scope | CapitalBench Score | Avg Return | Avg vs S&P | Beat S&P Weeks | Total / Max Possible |
|---|---|---|---|---|---|---|
| Grok 4.3 xAI | 25/25 weekly rounds | -2.1 | -0.19% | -0.28 pp | 12/25 | -4.63% / 216.12% |
| Claude Opus 4.7 Anthropic | 25/25 weekly rounds | -3.7 | -0.32% | -0.41 pp | 10/25 | -8.00% / 216.12% |
| GPT-5.5 OpenAI | 25/25 weekly rounds | -10.5 | -0.91% | -1.00 pp | 7/25 | -22.68% / 216.12% |
| Gemini 3.1 Pro Google | 25/25 weekly rounds | -13.7 | -1.19% | -1.28 pp | 8/25 | -29.71% / 216.12% |
| Claude Fable 5 Anthropic | 5/25 weekly rounds | 16.3 | 1.52% | +0.60 pp | 3/5 | 7.59% / 46.57% |
| S&P 500 Benchmark | 25/25 weekly rounds | 1.1 | 0.09% | 0.00 pp | Benchmark | 2.30% / 216.12% |
| Claude Opus 4.8 Anthropic | 23/25 weekly rounds | -4.5 | -0.38% | -0.36 pp | 9/23 | -8.69% / 191.69% |
Portfolios behind the result
Portfolios Behind The Result
Compact allocation cards first, with the full searchable table below.
Gemini 3.1 Pro Google
S&P 500 (SPY) 40% Healthcare Sector (XLV) 20% Financials Sector (XLF) 20% Short-Term Treasury Bills (BIL) 20%
Claude Fable 5 Anthropic
Healthcare Sector (XLV) 30% Financials Sector (XLF) 20% US Low Volatility Equities (SPLV) 20% Biotechnology (XBI) 15% +1 more
GPT-5.5 OpenAI
Biotechnology (XBI) 30% Healthcare Sector (XLV) 25% Financials Sector (XLF) 20% Aerospace and Defense (ITA) 15% +1 more
Claude Opus 4.8 Anthropic
Healthcare Sector (XLV) 30% Financials Sector (XLF) 25% US Low Volatility Equities (SPLV) 20% US Large-Cap Value (IWD) 15% +1 more
Claude Opus 4.7 Anthropic
Healthcare Sector (XLV) 30% Financials Sector (XLF) 25% US Low Volatility Equities (SPLV) 20% Equal-Weight S&P 500 (RSP) 15% +1 more
Grok 4.3 xAI
Healthcare Sector (XLV) 40% Consumer Staples Sector (XLP) 30% US Low Volatility Equities (SPLV) 30%
| Model | Provider | Portfolio | Confidence | Protocol | |
|---|---|---|---|---|---|
| Gemini 3.1 Pro google-gemini-3-1-pro | S&P 500 (SPY)40%Healthcare Sector (XLV)20%Financials Sector (XLF)20%Short-Term Treasury Bills (BIL)20% | 0.65 | Portfolio round | ||
| Claude Fable 5 anthropic-claude-fable-5 | Anthropic | Healthcare Sector (XLV)30%Financials Sector (XLF)20%US Low Volatility Equities (SPLV)20%Biotechnology (XBI)15%S&P 500 (SPY)15% | 0.50 | Portfolio round | |
| GPT-5.5 openai-gpt-5-5 | OpenAI | Biotechnology (XBI)30%Healthcare Sector (XLV)25%Financials Sector (XLF)20%Aerospace and Defense (ITA)15%US Low Volatility Equities (SPLV)10% | 0.58 | Portfolio round | |
| Claude Opus 4.8 anthropic-claude-opus-4-8 | Anthropic | Healthcare Sector (XLV)30%Financials Sector (XLF)25%US Low Volatility Equities (SPLV)20%US Large-Cap Value (IWD)15%Short-Term Treasury Bills (BIL)10% | 0.55 | Portfolio round | |
| Claude Opus 4.7 anthropic-claude-opus-4-7 | Anthropic | Healthcare Sector (XLV)30%Financials Sector (XLF)25%US Low Volatility Equities (SPLV)20%Equal-Weight S&P 500 (RSP)15%Short-Term Treasury Bills (BIL)10% | 0.55 | Portfolio round | |
| Grok 4.3 xai-grok-4-3 | xAI | Healthcare Sector (XLV)40%Consumer Staples Sector (XLP)30%US Low Volatility Equities (SPLV)30% | 0.55 | Portfolio round |
Current live weekly round CB-2026-07-10-1W Scores after the 2026-07-17 close.
View current portfolios