AI benchmark tape
Benchmark Live AI capital allocation same brief, frozen portfolios, real returns AI Positioning Risk-seeking 77.6/100 As of October 28, 2026. Broad risk seeking Model Agreement Mixed 5.7 point dispersion Insight Models missed the monthly oracle asset The hindsight best asset was Ethereum ETF (ETHA) at +152.31%. 0 of 7 models held it, with +0.00% average allocation. Crowded Position Consumer Staples Sector 27.5% 5 models hold XLP Biggest Shift S&P 500 down 56.7 pp vs prior weekly round Open Portfolio Leader Gemini 4 Argon currently leads at 1.4% interim result, not yet scored Latest Weekly Gemini 4 Argon led 0.1% vs S&P -0.6% Full Weekly History Gemini 4 Argon leads score 17.6 across 2/80
Data Prices Nov 3 164/164 audited

One-week rounds

All Available Weekly History

Context across every resolved one-week round. Fair model-vs-model rankings use equal-run comparison sets.

Weekly track

Full-History Weekly Scores

Resolved weekly rounds only.

80 resolved rounds compared0 full-history models ranked14 short-history models separatedNewest included round: CB-2026-10-22-1W
All resolved rounds

Full-History Model Scores

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

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

S&P 500 S&P 500 · 80/80 scored rounds
1.0
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
80 resolved rounds compared0 full-history models ranked14 short-history models separatedNewest included round: CB-2026-10-22-1W
Return context

Average Return Details

Average portfolio return across the same finished rounds.

S&P S&P 500
0.14%
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.
14.24%
Not ranked yet Short-history models

Shown for transparency; not included in the main ranking until they have all 80 completed rounds.

Google
Gemini 4 Argon Google · short history · 2/80 scored rounds
Score (2/80)
17.6
Avg return
1.13%
OpenAI
GPT-5.6 Sol OpenAI · short history · 35/80 scored rounds
Score (35/80)
5.0
Avg return
0.56%
Anthropic
Claude Opus 5 Anthropic · short history · 34/80 scored rounds
Score (34/80)
4.1
Avg return
0.47%
Anthropic
Claude Fable 5 Anthropic · short history · 43/80 scored rounds
Score (43/80)
3.8
Avg return
0.41%
xAI
Grok 4.5 xAI · short history · 53/80 scored rounds
Score (53/80)
2.1
Avg return
0.35%
xAI
Grok 4.3 xAI · short history · 78/80 scored rounds
Score (78/80)
1.0
Avg return
0.15%
OpenAI
GPT-6 Astra OpenAI · short history · 16/80 scored rounds
Score (16/80)
0.5
Avg return
0.16%
xAI
Grok 4.6 xAI · short history · 31/80 scored rounds
Score (31/80)
0.4
Avg return
0.10%
Anthropic
Claude Opus 5 5 Anthropic · short history · 8/80 scored rounds
Score (8/80)
-0.3
Avg return
-0.17%
Anthropic
Claude Opus 4.8 Anthropic · short history · 50/80 scored rounds
Score (50/80)
-1.2
Avg return
-0.12%
Anthropic
Claude Fable 5.1 Anthropic · short history · 17/80 scored rounds
Score (17/80)
-2.1
Avg return
-0.63%
OpenAI
GPT-5.5 OpenAI · short history · 49/80 scored rounds
Score (49/80)
-2.8
Avg return
-0.25%
Google
Gemini 3.1 Pro Google · short history · 78/80 scored rounds
Score (78/80)
-2.8
Avg return
-0.41%
Anthropic
Claude Opus 4.7 Anthropic · short history · 35/80 scored rounds
Score (35/80)
-5.0
Avg return
-0.45%
Short history: models missing resolved rounds are shown but cannot lead the full-history score.
Scope

What This Scorecard Includes

This all-history view can include unequal model histories. Use Benchmark Comparison Sets for the fair headline ranking where every model has the exact same included rounds.

Compare cohorts Comparison sets