AI benchmark tape
Benchmark Live AI capital allocation same brief, frozen portfolios, real returns AI Positioning Risk-seeking 60.1/100 As of July 29, 2026. Selective risk taking Model Agreement Tight 4.1 point dispersion Insight Models missed the weekly oracle asset The hindsight best asset was Software (IGV) at +7.13%. 0 of 7 models held it, with +0.00% average allocation. Crowded Position Healthcare Sector 16.4% 9 models hold XLV Biggest Shift Equal-Weight S&P 500 down 15.6 pp vs prior weekly round Open Portfolio Leader Claude Opus 5 currently leads at -0.1% interim result, not yet scored Latest Weekly Grok 4.3 led 0.4% vs S&P 0.5% Full Weekly History GPT-5.6 Sol leads score 2.8 across 9/38
Data Prices Jul 29 86/86 audited

Weekly comparison set

Weekly Set: May 24, 2026

Original weekly comparison set for the first four CapitalBench models.

Qualified Comparison Set

Fairness Scope

Every ranked model in this set is scored only on rounds that all 4 listed models completed. If one model misses a resolved round, that round is excluded from this set for everyone.

All comparison sets
Shared rounds35 Models4 Threshold6 StatusQualified Comparison Set
Equal-run benchmark

Weekly Qualified Comparison Set

Every ranked model in this set completed the same 35 weekly rounds.

35 shared resolved rounds4 equal-run models rankedQualified at 6+ shared roundsNewest included round: CB-2026-07-20-1W
Shared resolved rounds

CapitalBench Score

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

Grok 4.3
Claude Opus 4.7
GPT-5.5
Gemini 3.1 Pro
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 · 35/35 scored rounds
1.4
Claude Opus 4.7 Anthropic · 35/35 scored rounds
-5.0
GPT-5.5 OpenAI · 35/35 scored rounds
-6.4
Gemini 3.1 Pro Google · 35/35 scored rounds
-7.0
S&P 500 S&P 500 · 35/35 scored rounds
-0.4
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
35 shared resolved rounds4 equal-run models rankedQualified at 6+ shared roundsNewest included round: CB-2026-07-20-1W
Return context

Average Return Details

Average portfolio return across the same finished rounds.

xAI Grok 4.3
0.13%
Anthropic Claude Opus 4.7
-0.45%
OpenAI GPT-5.5
-0.57%
Google Gemini 3.1 Pro
-0.63%
S&P S&P 500
-0.04%
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.
8.95%
Excluded for fairness: CB-2026-07-21-1W missing anthropic-claude-opus-4-7; CB-2026-07-22-1W missing anthropic-claude-opus-4-7; CB-2026-07-23-1W missing anthropic-claude-opus-4-7 Fairness rule: every ranked model completed every included round. A missed round is excluded from this set for everyone.
Compare model groups

How do these results compare?

Grok 4.3 ranks first in both groups. The groups share 6 completed rounds. May 24 Weekly includes 29 more rounds. Grok 4.5, Claude Fable 5, GPT-5.6 Sol, Claude Opus 4.8 appear only in Jul 10 Weekly.

4models in both 6rounds used by both Changed a lotchange in order No top model changed

Jul 10 Weekly is the main published ranking. May 24 Weekly also has enough rounds, so compare them to see whether the results hold across different model groups.

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 Opus 4.7

anthropic-claude-opus-4-7

35 shared rounds in this set Google Gemini 3.1 Pro

google-gemini-3-1-pro

35 shared rounds in this set OpenAI GPT-5.5

openai-gpt-5-5

35 shared rounds in this set xAI Grok 4.3

xai-grok-4-3

35 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.

Included rounds CB-2026-05-24-1W, CB-2026-05-27-1W, CB-2026-05-28-1W, CB-2026-05-29-1W, CB-2026-06-01-1W, CB-2026-06-02-1W, CB-2026-06-03-1W, CB-2026-06-05-1W, CB-2026-06-08-1W, CB-2026-06-09-1W, CB-2026-06-12-1W, CB-2026-06-13-1W, CB-2026-06-15-1W, CB-2026-06-16-1W, CB-2026-06-17-1W, CB-2026-06-18-1W, CB-2026-06-22-1W, CB-2026-06-23-1W, CB-2026-06-24-1W, CB-2026-06-25-1W, CB-2026-06-26-1W, CB-2026-06-29-1W, CB-2026-06-30-1W, CB-2026-07-01-1W, CB-2026-07-02-1W, CB-2026-07-06-1W, CB-2026-07-07-1W, CB-2026-07-08-1W, CB-2026-07-09-1W, CB-2026-07-10-1W, CB-2026-07-13-1W, CB-2026-07-14-1W, CB-2026-07-15-1W, CB-2026-07-17-1W, CB-2026-07-20-1W
Excluded for fairness
3 resolved candidate rounds CB-2026-07-21-1W missing anthropic-claude-opus-4-7; CB-2026-07-22-1W missing anthropic-claude-opus-4-7; CB-2026-07-23-1W missing anthropic-claude-opus-4-7
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