Google
Google

Gemini 3.1 Pro

google-gemini-3-1-pro

Portfolio pattern High-conviction concentrator Usually expresses views through fewer holdings and a larger top position than peers.
Live portfolios WeeklyMonthly First run 2026-05-10
Live portfolios 23 23 open rounds
Completed rounds 44 scored rounds
Beat S&P 500 29.5% all completed tracks
Portfolio Minus S&P 500 -1.29 pp completed average
Portfolio pattern

How Does This Model Tend To Invest?

Calculated from every official saved portfolio, including open and completed rounds.

Saved portfolios 67
Average holdings 3.6
Average largest position 39.3%
Most common top holding Semiconductors (SMH)
Typical approach High-conviction concentrator

Usually expresses views through fewer holdings and a larger top position than peers.

Based on 67 saved portfolios.
Risk taking 75.3 / 100 0 defensive to 100 aggressive
Typical largest position 39.3% average top holding
Similarity to peers 52.8% closest to GPT-5.6 Sol
Portfolio turnover 57.8% average change between rounds
Compared with other models

Most similar to GPT-5.6 Sol

Average portfolio overlap is 52.8% on matching rounds. It made an unusually different allocation in 25 rounds.

Compare every model's pattern
Overall risk appetite

Growth

Usually favors equities, sectors, or thematic growth exposure.

4.06 / 5 allocation-weighted score
Gemini 3.1 Pro4.06
72.1% high-risk exposure 39.7% technology exposure 8.9% defensive holdings
Most frequently held assets
Semiconductors (SMH)AI and Technology 59.7% held 21.4% avg
Healthcare Sector (XLV)US Sector 29.9% held 8.1% avg
Technology Sector (XLK)US Sector 29.9% held 8.1% avg
S&P 500 (SPY)US Broad Market 28.4% held 10.2% avg
Energy Sector (XLE)US Sector 23.9% held 7.0% avg
Short-Term Treasury Bills (BIL)Cash and Short Duration 23.9% held 5.5% avg
South Korea Equities (EWY)Country Equity 22.4% held 5.4% avg
Average allocation by category
US Sector28.7%
AI and Technology25.8%
US Broad Market10.7%
Country Equity7.2%
Commodities6.4%
Cash and Short Duration5.5%
US Growth and Technology4.0%
Current portfolios

What Is This Model Holding Now?

23 open portfolios across weekly and monthly tests. Completed rounds are excluded.

Weekly4 open portfolios
8 assets
Completed rounds are excluded from this live view.Next scoring target: 2026-07-17
Still in progress

How Are Its Open Portfolios Doing?

Latest available close for live rounds only. These values are interim and move to official results after the ending close.

Weekly live
Portfolio
-0.60%
S&P 500
+0.38%
Portfolio Minus S&P 500
-0.98 pp
3 open tests
Monthly live
Portfolio
-1.39%
S&P 500
+1.46%
Portfolio Minus S&P 500
-2.85 pp
18 open tests
See all 21 open round returns
CB-2026-07-14-1M monthly / close 2026-07-15 Portfolio -0.15% S&P 500 +0.40% Portfolio Minus S&P 500 -0.55 pp CB-2026-07-13-1M monthly / close 2026-07-15 Portfolio +1.18% S&P 500 +0.75% Portfolio Minus S&P 500 +0.42 pp CB-2026-07-10-1M monthly / close 2026-07-15 Portfolio -4.31% S&P 500 -0.02% Portfolio Minus S&P 500 -4.30 pp CB-2026-07-09-1M monthly / close 2026-07-15 Portfolio -0.39% S&P 500 +0.41% Portfolio Minus S&P 500 -0.80 pp CB-2026-07-08-1M monthly / close 2026-07-15 Portfolio +1.52% S&P 500 +1.26% Portfolio Minus S&P 500 +0.26 pp CB-2026-07-07-1M monthly / close 2026-07-15 Portfolio +0.49% S&P 500 +0.95% Portfolio Minus S&P 500 -0.45 pp CB-2026-07-06-1M monthly / close 2026-07-15 Portfolio -0.99% S&P 500 +0.47% Portfolio Minus S&P 500 -1.46 pp CB-2026-07-02-1M monthly / close 2026-07-15 Portfolio +0.23% S&P 500 +1.35% Portfolio Minus S&P 500 -1.12 pp CB-2026-07-01-1M monthly / close 2026-07-15 Portfolio +1.00% S&P 500 +1.21% Portfolio Minus S&P 500 -0.21 pp CB-2026-06-30-1M monthly / close 2026-07-15 Portfolio -4.51% S&P 500 +1.08% Portfolio Minus S&P 500 -5.59 pp CB-2026-06-29-1M monthly / close 2026-07-15 Portfolio -2.12% S&P 500 +1.86% Portfolio Minus S&P 500 -3.99 pp CB-2026-06-26-1M monthly / close 2026-07-15 Portfolio -0.36% S&P 500 +3.54% Portfolio Minus S&P 500 -3.90 pp CB-2026-06-25-1M monthly / close 2026-07-15 Portfolio -3.99% S&P 500 +2.79% Portfolio Minus S&P 500 -6.78 pp CB-2026-06-24-1M monthly / close 2026-07-15 Portfolio -0.95% S&P 500 +2.94% Portfolio Minus S&P 500 -3.89 pp CB-2026-06-23-1M monthly / close 2026-07-15 Portfolio +1.74% S&P 500 +2.89% Portfolio Minus S&P 500 -1.15 pp CB-2026-06-22-1M monthly / close 2026-07-15 Portfolio +0.16% S&P 500 +1.40% Portfolio Minus S&P 500 -1.24 pp CB-2026-07-14-1W weekly / close 2026-07-15 Portfolio +0.03% S&P 500 +0.40% Portfolio Minus S&P 500 -0.37 pp CB-2026-07-13-1W weekly / close 2026-07-15 Portfolio +1.51% S&P 500 +0.75% Portfolio Minus S&P 500 +0.76 pp CB-2026-06-18-1M monthly / close 2026-07-15 Portfolio -5.94% S&P 500 +1.08% Portfolio Minus S&P 500 -7.02 pp CB-2026-07-10-1W weekly / close 2026-07-15 Portfolio -3.35% S&P 500 -0.02% Portfolio Minus S&P 500 -3.33 pp CB-2026-06-17-1M monthly / close 2026-07-15 Portfolio -7.70% S&P 500 +1.87% Portfolio Minus S&P 500 -9.57 pp
Completed results

How Has This Model Performed?

Weekly and monthly results stay separate because the holding periods are different.

Weekly record

3 wins / 29 completed

Avg return -0.98%
S&P 500 +0.13%
Avg Portfolio Minus S&P 500 -1.10 pp
Hit rate 34.5%
Avg rank 3.4
Best round CB-2026-05-27-1W
Monthly record

3 wins / 15 completed

Avg return -1.88%
S&P 500 -0.24%
Avg Portfolio Minus S&P 500 -1.64 pp
Hit rate 20.0%
Avg rank 3.3
Best round CB-2026-05-24-1M
Round by round

When Did It Beat The S&P 500?

Bars to the right beat the S&P 500. Bars to the left trailed it.

CB-2026-05-10-1Mmonthly / rank 1 of 4 +2.42 pp CB-2026-05-17-1Mmonthly / rank 3 of 4 -5.23 pp CB-2026-05-24-1Mmonthly / rank 3 of 4 +6.53 pp CB-2026-05-24-1Wweekly / rank 4 of 4 +1.34 pp CB-2026-05-27-1Wweekly / rank 2 of 4 +4.06 pp CB-2026-05-28-1Mmonthly / rank 4 of 5 +2.45 pp CB-2026-05-28-1Wweekly / rank 1 of 5 +3.60 pp CB-2026-06-01-1Mmonthly / rank 5 of 5 -3.10 pp CB-2026-05-29-1Mmonthly / rank 5 of 5 -2.75 pp CB-2026-06-01-1Wweekly / rank 4 of 5 -5.08 pp CB-2026-05-29-1Wweekly / rank 4 of 5 -3.12 pp CB-2026-06-02-1Mmonthly / rank 2 of 5 -0.04 pp CB-2026-06-02-1Wweekly / rank 5 of 5 -9.10 pp CB-2026-06-03-1Mmonthly / rank 4 of 5 -6.03 pp CB-2026-06-03-1Wweekly / rank 4 of 5 -7.21 pp CB-2026-06-05-1Mmonthly / rank 3 of 5 -0.16 pp CB-2026-06-05-1Wweekly / rank 4 of 5 -0.45 pp CB-2026-06-08-1Mmonthly / rank 4 of 5 -0.44 pp CB-2026-06-08-1Wweekly / rank 5 of 5 -3.47 pp CB-2026-06-09-1Mmonthly / rank 6 of 6 -2.06 pp CB-2026-06-09-1Wweekly / rank 2 of 6 -1.34 pp CB-2026-06-12-1Mmonthly / rank 3 of 6 -1.35 pp CB-2026-06-12-1Wweekly / rank 3 of 6 +0.23 pp CB-2026-06-13-1Mmonthly / rank 1 of 5 -1.04 pp CB-2026-06-13-1Wweekly / rank 6 of 6 +0.42 pp CB-2026-06-15-1Mmonthly / rank 1 of 5 -4.80 pp CB-2026-06-15-1Wweekly / rank 4 of 5 +3.33 pp CB-2026-06-16-1Mmonthly / rank 4 of 5 -9.03 pp CB-2026-06-16-1Wweekly / rank 4 of 5 -0.26 pp CB-2026-06-17-1Wweekly / rank 5 of 5 -0.97 pp CB-2026-06-18-1Wweekly / rank 2 of 5 -1.00 pp CB-2026-06-22-1Wweekly / rank 3 of 5 -3.24 pp CB-2026-06-23-1Wweekly / rank 2 of 5 +2.49 pp CB-2026-06-24-1Wweekly / rank 5 of 5 -0.45 pp CB-2026-06-25-1Wweekly / rank 4 of 5 -2.32 pp CB-2026-06-26-1Wweekly / rank 2 of 5 -0.40 pp CB-2026-06-29-1Wweekly / rank 3 of 5 -2.69 pp CB-2026-06-30-1Wweekly / rank 5 of 5 -6.19 pp CB-2026-07-01-1Wweekly / rank 4 of 6 +0.56 pp CB-2026-07-02-1Wweekly / rank 1 of 6 -0.77 pp CB-2026-07-06-1Wweekly / rank 5 of 6 -3.45 pp CB-2026-07-07-1Wweekly / rank 2 of 6 +3.12 pp CB-2026-07-08-1Wweekly / rank 1 of 7 +3.36 pp CB-2026-07-09-1Wweekly / rank 2 of 7 -3.04 pp
Ranking context

Where Does It Rank Against Comparable Models?

Each group uses only rounds completed by every included model.

See every comparison group 10
Weekly · Current

Jun 9, 2026 roster

Weekly comparison set that starts when Claude Fable 5 joins the weekly benchmark roster.

Open full set
#2 Rank in set 5.6 CapitalBench Score 5.1% Total return 9 Shared rounds

Current Weekly Benchmark

CapitalBench Score

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

GPT-5.5
Gemini 3.1 Pro This model
Claude Fable 5
Grok 4.3
Claude Opus 4.8
Claude Opus 4.7
S&P 500
Max possible What is this? Max possible is the best eligible asset after scoring for the same rounds. It is a hindsight ceiling, not a model portfolio. hindsight best asset

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

GPT-5.5 OpenAI · 9/9 scored rounds
6.8
Gemini 3.1 Pro Google · 9/9 scored rounds
5.6
Claude Fable 5 Anthropic · 9/9 scored rounds
0.4
Grok 4.3 xAI · 9/9 scored rounds
-0.3
Claude Opus 4.8 Anthropic · 9/9 scored rounds
-1.8
Claude Opus 4.7 Anthropic · 9/9 scored rounds
-4.0
S&P 500 S&P 500 · 9/9 scored rounds
6.6
Max possible Hindsight ceiling, not a model portfolio
What is this? Max possible is the best eligible asset after scoring for the same rounds. It is a hindsight ceiling, not a model portfolio. 100.0
9 shared resolved rounds6 equal-run models rankedQualified at 6+ shared roundsNewest included round: CB-2026-07-09-1W
Return context

Average Return Details

Average portfolio return across the same finished rounds.

OpenAI GPT-5.5
0.68%
Google Gemini 3.1 Pro
0.56%
Anthropic Claude Fable 5
0.04%
xAI Grok 4.3
-0.03%
Anthropic Claude Opus 4.8
-0.18%
Anthropic Claude Opus 4.7
-0.40%
S&P S&P 500
0.66%
MAX Max possible What is this? Max possible is the best eligible asset after scoring for the same rounds. It is a hindsight ceiling, not a model portfolio.
10.00%
Excluded for fairness: CB-2026-06-15-1W missing anthropic-claude-fable-5; CB-2026-06-16-1W missing anthropic-claude-fable-5; CB-2026-06-17-1W missing anthropic-claude-fable-5; CB-2026-06-18-1W missing anthropic-claude-fable-5; CB-2026-06-22-1W missing anthropic-claude-fable-5; CB-2026-06-23-1W missing anthropic-claude-fable-5; CB-2026-06-24-1W missing anthropic-claude-fable-5; CB-2026-06-25-1W missing anthropic-claude-fable-5; CB-2026-06-26-1W missing anthropic-claude-fable-5; CB-2026-06-29-1W missing anthropic-claude-fable-5; CB-2026-06-30-1W missing anthropic-claude-fable-5 Fairness rule: every ranked model completed every included round. A missed round is excluded from this set for everyone.
Model-specific findings

What Has CapitalBench Learned About Gemini 3.1 Pro?

Findings tied directly to this model's decisions or completed results.

Model BehaviorAs of Jul 16
Model behavior profiles8 models

Model allocation styles are separating into clear behavior profiles

GPT-5.5 has the highest average risk-taking score at 84.2/100. Gemini 3.1 Pro has the largest average top holding at +39.33%. GPT-5.5 has the lowest measured turnover at +46.08%.

Momentum exposure measures how much of the frozen portfolio went into assets that had already been recent winners before the model made its allocation.

High confidenceMath: deterministicData through Jul 16, 2026
Highest Average Risk Taking Score
84.2/100
Largest Average Top Holding
+39.3%
Lowest Average Turnover
+46.1%
Market EnvironmentAs of Jul 16
Weekly up/down split14 resolved rounds1 model

Gemini 3.1 Pro changes most between weekly up and down environments

The model averaged -4.94% in down environments and +1.91% in up environments, a 6.8 percentage-point gap.

Market environments group resolved rounds by the S&P 500 return over the same weekly or monthly window. Models are compared only on shared rounds; high confidence requires at least six observations and stable leadership.

Medium confidenceMath: deterministicData through Jul 16, 2026
Average Return Gap
+6.84%
Down Average Return
-4.94%
Up Average Return
+1.91%
Market EnvironmentAs of Jul 16
Monthly up/down split10 resolved rounds1 model

Gemini 3.1 Pro changes most between monthly up and down environments

The model averaged -3.87% in down environments and +0.69% in up environments, a 4.6 percentage-point gap.

Market environments group resolved rounds by the S&P 500 return over the same weekly or monthly window. Models are compared only on shared rounds; high confidence requires at least six observations and stable leadership.

Medium confidenceMath: deterministicData through Jul 16, 2026
Average Return Gap
+4.56%
Down Average Return
-3.87%
Up Average Return
+0.69%
Decision history

What Did It Choose In Each Round?

Open a row to see the full portfolio, rationale, and audit files.

Round Track Window Portfolio Result
CB-2026-07-15-1W official-20260715 weekly 2026-07-15 to 2026-07-22 OIL 40.0%ENERGY 30.0%AEROSPACE_DEFENSE 15.0%SEMICONDUCTORS 15.0% Pending
Full portfolio
Crude Oil (USO) 40.0% Energy Sector (XLE) 30.0% Aerospace and Defense (ITA) 15.0% Semiconductors (SMH) 15.0%
Rationale

Allocations focus on the acute geopolitical risks in the Middle East driving oil and defense, balanced with a tactical play on semiconductor earnings.

CB-2026-07-15-1M official-20260715 monthly 2026-07-15 to 2026-08-14 ENERGY 40.0%OIL 30.0%AEROSPACE_DEFENSE 15.0%GOLD 15.0% Pending
Full portfolio
Energy Sector (XLE) 40.0% Crude Oil (USO) 30.0% Aerospace and Defense (ITA) 15.0% Gold (IAU) 15.0%
Rationale

Allocations focus on the immediate impact of the Middle East conflict on oil prices and defense spending, with gold as a safe-haven hedge.

CB-2026-07-14-1W official-20260714 weekly 2026-07-14 to 2026-07-21 OIL 40.0%ENERGY 30.0%FINANCIALS 15.0%SEMICONDUCTORS 15.0% Pending
Full portfolio
Crude Oil (USO) 40.0% Energy Sector (XLE) 30.0% Financials Sector (XLF) 15.0% Semiconductors (SMH) 15.0%
Rationale

Allocating to OIL and ENERGY to capitalize on the Strait of Hormuz blockade. Adding FINANCIALS and SEMICONDUCTORS based on strong recent corporate results.

CB-2026-07-14-1M official-20260714 monthly 2026-07-14 to 2026-08-14 FINANCIALS 30.0%ENERGY 30.0%OIL 20.0%SEMICONDUCTORS 20.0% Pending
Full portfolio
Financials Sector (XLF) 30.0% Energy Sector (XLE) 30.0% Crude Oil (USO) 20.0% Semiconductors (SMH) 20.0%
Rationale

Overweighting financials and semiconductors based on strong recent earnings and revenue data, while heavily allocating to energy and oil to profit from the escalating military situation in the Strait of Hormuz.

CB-2026-07-13-1W official-20260713 weekly 2026-07-13 to 2026-07-20 OIL 50.0%ENERGY 30.0%AEROSPACE_DEFENSE 20.0% Pending
Full portfolio
Crude Oil (USO) 50.0% Energy Sector (XLE) 30.0% Aerospace and Defense (ITA) 20.0%
Rationale

Allocating to oil, energy, and defense to capture the upside from the Strait of Hormuz blockade and rising geopolitical tensions.

CB-2026-07-13-1M official-20260713 monthly 2026-07-13 to 2026-08-13 OIL 30.0%ENERGY 30.0%AEROSPACE_DEFENSE 20.0%GOLD 20.0% Pending
Full portfolio
Crude Oil (USO) 30.0% Energy Sector (XLE) 30.0% Aerospace and Defense (ITA) 20.0% Gold (IAU) 20.0%
Rationale

Overweight oil, energy, defense, and gold to profit from the US-Iran conflict and Strait of Hormuz blockade.

CB-2026-07-10-1W official-20260710 weekly 2026-07-10 to 2026-07-17 SEMICONDUCTORS 40.0%TECHNOLOGY 30.0%TAIWAN 20.0%SOUTH_KOREA 10.0% Pending
Full portfolio
Semiconductors (SMH) 40.0% Technology Sector (XLK) 30.0% Taiwan Equities (EWT) 20.0% South Korea Equities (EWY) 10.0%
Rationale

Overweighting semiconductors and related Asian markets to capture potential upside from TSMC's earnings and ongoing AI hardware demand.

CB-2026-07-10-1M official-20260710 monthly 2026-07-10 to 2026-08-10 SEMICONDUCTORS 40.0%SOUTH_KOREA 30.0%TAIWAN 30.0% Pending
Full portfolio
Semiconductors (SMH) 40.0% South Korea Equities (EWY) 30.0% Taiwan Equities (EWT) 30.0%
Rationale

Allocating to semiconductors, South Korea, and Taiwan based on strong AI demand and positive catalysts from key industry players.

CB-2026-07-09-1W official-20260709 weekly 2026-07-09 to 2026-07-16 SEMICONDUCTORS 40.0%TECHNOLOGY 30.0%FINANCIALS 30.0% -3.04 pp
Full portfolio
Semiconductors (SMH) 40.0% Technology Sector (XLK) 30.0% Financials Sector (XLF) 30.0%
Rationale

Allocated to Semiconductors and Technology for AI-driven momentum and TSMC catalysts, and Financials for upcoming major bank earnings.

CB-2026-07-09-1M official-20260709 monthly 2026-07-09 to 2026-08-07 SEMICONDUCTORS 30.0%AEROSPACE_DEFENSE 25.0%ENERGY 25.0%SHORT_TREASURY 20.0% Pending
Full portfolio
Semiconductors (SMH) 30.0% Aerospace and Defense (ITA) 25.0% Energy Sector (XLE) 25.0% Short-Term Treasury Bills (BIL) 20.0%
Rationale

Allocating to semiconductors for AI growth, aerospace and energy for geopolitical hedges, and short-term treasuries for stability.

Audit and data Public Audit Packets For This Model