AI benchmark tape
Benchmark Live AI capital allocation same brief, frozen portfolios, real returns AI Positioning Risk-seeking 75.5/100 As of September 4, 2026. Broad risk seeking Model Agreement Tight 4.0 point dispersion Insight Models found the weekly oracle asset The hindsight best asset was Crude Oil (USO) at +9.45%. 1 of 7 models held it, with +5.00% average allocation. The largest allocation came from Gemini 3.1 Pro at +35.00%. Crowded Position S&P 500 22.2% 9 models hold SPY Biggest Shift Copper up 9.3 pp vs prior monthly round Open Portfolio Leader GPT-5.5 currently leads at 1.2% interim result, not yet scored Latest Monthly Claude Fable 5 led 4.2% vs S&P 0.1% Full Monthly History Grok 4.5 leads score 15.8 across 18/46
Data Prices Sep 4 132/132 audited

One-month rounds

All Available Monthly History

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

Monthly track

Full-History Monthly Scores

Resolved monthly rounds only.

46 resolved rounds compared3 full-history models ranked6 short-history models separatedNewest included round: CB-2026-08-05-1M
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

Grok 4.3
Gemini 3.1 Pro
GPT-5.5
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

Grok 4.3 xAI · 46/46 scored rounds
3.1
Gemini 3.1 Pro Google · 46/46 scored rounds
-0.8
GPT-5.5 OpenAI · 46/46 scored rounds
-6.6
S&P 500 S&P 500 · 46/46 scored rounds
6.2
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
46 resolved rounds compared3 full-history models ranked6 short-history models separatedNewest included round: CB-2026-08-05-1M
Return context

Average Return Details

Average portfolio return across the same finished rounds.

xAI Grok 4.3
0.64%
Google Gemini 3.1 Pro
-0.17%
OpenAI GPT-5.5
-1.35%
S&P S&P 500
1.28%
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.
20.58%
Not ranked yet Short-history models

Shown for transparency; not included in the main ranking until they have all 46 completed rounds.

xAI
Grok 4.5 xAI · short history · 18/46 scored rounds
Score (18/46)
15.8
Avg return
3.66%
OpenAI
GPT-5.6 Sol OpenAI · short history · 16/46 scored rounds
Score (16/46)
11.9
Avg return
2.91%
Anthropic
Claude Fable 5 Anthropic · short history · 24/46 scored rounds
Score (24/46)
10.1
Avg return
2.25%
Anthropic
Claude Opus 5 Anthropic · short history · 8/46 scored rounds
Score (8/46)
9.2
Avg return
2.72%
Anthropic
Claude Opus 4.8 Anthropic · short history · 43/46 scored rounds
Score (43/46)
2.6
Avg return
0.55%
Anthropic
Claude Opus 4.7 Anthropic · short history · 35/46 scored rounds
Score (35/46)
-5.1
Avg return
-0.92%
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