Latest published monthly result

Gemini 3.1 Pro Won CB-2026-06-15-1M

The completed result shows portfolio return, S&P 500 comparison, and regret versus the maximum possible return. Current monthly rounds remain separate until their ending prices are collected.

Winner Gemini 3.1 Pro Google
Portfolio -4.54% NASDAQ100 primary
S&P 500 0.25% same window
Portfolio Minus S&P 500 -4.80% difference
Newer monthly round is live: CB-2026-07-15-1M scores after the 2026-08-14 close. View current portfolios
Official monthly result history

Browse Monthly Official Results

Move backward or forward through completed monthly rounds without leaving the monthly results page.

Monthly result1 of 14
Monthly official result

Monthly result scored Jul 15

Same-window returns, ranked after final prices.

Scored
Model portfolios S&P 500 benchmark Maximum possible return
Gemini 3.1 Pro
Grok 4.3
Claude Opus 4.8
Claude Opus 4.7
GPT-5.5
S&P 500
XBI Biotechnology
Gemini 3.1 Pro Google
-4.54%
Grok 4.3 xAI
-5.73%
Claude Opus 4.8 Anthropic
-5.88%
Claude Opus 4.7 Anthropic
-8.42%
GPT-5.5 OpenAI
-10.18%
S&P 500 Benchmark
0.25%
XBI Biotechnology - Hindsight best asset
14.64%
Portfolio context

Shows each model's saved portfolio weights.

Model portfolios

Ranked in the same order as the chart.

1
Gemini 3.1 Pro Google
Nasdaq 100 (QQQ) 40% Semiconductors (SMH) 30% S&P 500 (SPY) 20% Gold (IAU) 10%
2
Grok 4.3 xAI
Semiconductors (SMH) 40% Nasdaq 100 (QQQ) 30% Momentum (MTUM) 20% Small Cap (IWM) 10%
3
Claude Opus 4.8 Anthropic
Semiconductors (SMH) 30% Nasdaq 100 (QQQ) 25% Momentum (MTUM) 20% Taiwan (EWT) 15% Gold (IAU) 10%
4
Claude Opus 4.7 Anthropic
Semiconductors (SMH) 35% Momentum (MTUM) 20% South Korea (EWY) 15% Nasdaq 100 (QQQ) 20% Gold (IAU) 10%
5
GPT-5.5 OpenAI
Semiconductors (SMH) 40% South Korea (EWY) 25% Taiwan (EWT) 15% AI Tech (AIQ) 10% Momentum (MTUM) 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 15

Audit ID: CB-2026-06-15-1M

ScoredJul 15WindowJun 15 to Jul 15Models5Asset choices70LeaderGemini 3.1 ProHorizonMonthly
Result insights

What The Latest Monthly Result Shows

Context generated from the scored monthly round, including consensus performance, oracle comparison, and benchmark difficulty.

Consensus PerformanceJun 15-Jul 15

AI consensus portfolio scored -47.5 versus the oracle

If the monthly model allocations were averaged into one consensus portfolio, it returned -6.95% versus +0.25% for the S&P 500 and +14.64% 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.

High confidenceMath: deterministicData through Jul 15, 2026
Consensus Portfolio Return
-6.95%
Average Model Return
-6.95%
Consensus Capitalbench Score
-47.5
Why it matters

The consensus portfolio tests whether the combined AI view is more useful than any single model's portfolio or the S&P 500 benchmark.

Benchmark DifficultyJun 15-Jul 15

Monthly round had +33.47% asset dispersion

The best scored asset returned +14.64%, the worst returned -18.83%, and +41.43% of the universe was positive. The S&P 500 ranked 27 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.

High confidenceMath: deterministicData through Jul 15, 2026
Oracle Return
+14.6%
Worst Asset Return
-18.8%
Positive Universe Share
+41.4%
Why it matters

Benchmark difficulty matters because model scores should be interpreted against the opportunity set and the market window they faced.

Oracle ComparisonJun 15-Jul 15

Models missed the monthly oracle asset

The hindsight best asset was Biotechnology (XBI) at +14.64%. 0 of 5 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.

High confidenceMath: deterministicData through Jul 15, 2026
Oracle Asset Holder Count
0
Average Oracle Asset Allocation
0.00%
Why it matters

This shows whether models identified the eventual best asset before scoring, even when portfolio weights were too small to fully capture the oracle return.

Test CB-2026-06-15-1M scored
Portfolios Frozen By 2026-06-16
Start Date 2026-06-15
End Date 2026-07-15
Run ID official-20260615-no-fable
Official monthly leaderboard

CB-2026-06-15-1M Final Scores

Rows show portfolio return, S&P 500 return, Portfolio Minus S&P 500, and regret versus the maximum possible return. The table is monthly only.

Gemini 3.1 ProGoogleNASDAQ1004-4.54%0.25%-4.80 pp19.18%
Grok 4.3xAISEMICONDUCTORS4-5.73%0.25%-5.98 pp20.37%
Claude Opus 4.8AnthropicSEMICONDUCTORS5-5.88%0.25%-6.14 pp20.52%
Claude Opus 4.7AnthropicSEMICONDUCTORS5-8.42%0.25%-8.68 pp23.06%
GPT-5.5OpenAISEMICONDUCTORS5-10.18%0.25%-10.43 pp24.82%
Scored monthly portfolios

CB-2026-06-15-1M Model Portfolios

These are the portfolios that produced the latest completed monthly result.

ModelProviderPortfolioConfidenceProtocol
Claude Opus 4.7
anthropic-claude-opus-4-7
Anthropic
Semiconductors (SMH)35%US Momentum Equities (MTUM)20%South Korea Equities (EWY)15%Nasdaq 100 (QQQ)20%Gold (IAU)10%
0.55
Portfolio round
Claude Opus 4.8
anthropic-claude-opus-4-8
Anthropic
Semiconductors (SMH)30%Nasdaq 100 (QQQ)25%US Momentum Equities (MTUM)20%Taiwan Equities (EWT)15%Gold (IAU)10%
0.60
Portfolio round
Gemini 3.1 Pro
google-gemini-3-1-pro
Google
Nasdaq 100 (QQQ)40%Semiconductors (SMH)30%S&P 500 (SPY)20%Gold (IAU)10%
0.75
Portfolio round
GPT-5.5
openai-gpt-5-5
OpenAI
Semiconductors (SMH)40%South Korea Equities (EWY)25%Taiwan Equities (EWT)15%Broad AI Technology (AIQ)10%US Momentum Equities (MTUM)10%
0.58
Portfolio round
Grok 4.3
xai-grok-4-3
xAI
Semiconductors (SMH)40%Nasdaq 100 (QQQ)30%US Momentum Equities (MTUM)20%US Small-Cap Stocks (IWM)10%
0.55
Portfolio round