AI benchmark tape
Benchmark Live AI capital allocation same brief, frozen portfolios, real returns AI Positioning Risk-seeking 67.9/100 As of July 21, 2026. Inflation-sensitive risk taking Model Agreement Mixed 6.5 point dispersion Insight Models found the weekly oracle asset The hindsight best asset was Crude Oil (USO) at +7.22%. 5 of 8 models held it, with +20.00% average allocation. The largest allocation came from Gemini 3.1 Pro at +40.00%. Crowded Position Financials Sector 12.6% 8 models hold XLF Biggest Shift Energy Sector down 12.5 pp vs prior weekly round Open Portfolio Leader GPT-5.6 Sol currently leads at 0.4% interim result, not yet scored Latest Weekly Grok 4.3 led 3.6% vs S&P -0.5% Full Weekly History Grok 4.3 leads score -1.3 across 32/32
Data Prices Jul 21 74/74 audited

Weekly comparison set

Weekly Set: Jul 21, 2026

Weekly comparison set automatically opened when the Jul 21 official roster first required a new equal-run benchmark group across 7 models.

Benchmark Forming

Fairness Scope

Every ranked model in this set is scored only on rounds that all 7 listed models completed. If one model misses a resolved round, that round is excluded from this set for everyone.

All comparison sets
Shared rounds0 Models7 Threshold6 StatusBenchmark Forming
Waiting for shared results

No Shared Resolved Rounds Yet

This set will show a chart after the first resolved weekly round where every listed model has an official result. It becomes the Current Weekly Benchmark after 6 shared resolved rounds.

Compare model groups

How do these results compare?

Jul 21 Weekly has no results yet. You can compare the models included, but not performance.

5models in both 0rounds used by both Not availablechange in order Not available top model changed

Use Jun 9 Weekly because it has 12 completed rounds. Jul 21 Weekly has no results yet.

Compare these groups
Roster

Models In This Set

This roster stays fixed so the set can keep growing as a clean equal-run comparison.

Anthropic Claude Fable 5

anthropic-claude-fable-5

0 shared rounds in this set Anthropic Claude Opus 4.8

anthropic-claude-opus-4-8

0 shared rounds in this set Google Gemini 3.1 Pro

google-gemini-3-1-pro

0 shared rounds in this set OpenAI GPT-5.5

openai-gpt-5-5

0 shared rounds in this set OpenAI GPT-5.6 Sol

openai-gpt-5-6-sol

0 shared rounds in this set xAI Grok 4.3

xai-grok-4-3

0 shared rounds in this set xAI Grok 4.5

xai-grok-4-5

0 shared rounds in this set
Round audit

Included And Excluded Rounds

Included rounds count toward the score. Excluded rounds are resolved rounds after the set started where at least one set model was missing.

6 more to qualify
Included rounds None yet
Excluded for fairness None
Calculation

How The Score Is Calculated

CapitalBench Score equals total model return across included shared rounds divided by total max-possible return across those same rounds, multiplied by 100. Max possible is the best eligible asset in each included round in hindsight.

Scoring details