AI benchmark tape
Benchmark Live AI capital allocation same brief, frozen portfolios, real returns AI Positioning Risk-seeking 68.0/100 As of October 1, 2026. Broad risk seeking Model Agreement Tight 2.5 point dispersion Insight Models found the monthly oracle asset The hindsight best asset was Semiconductors (SMH) at +14.55%. 1 of 7 models held it, with +4.29% average allocation. The largest allocation came from GPT-5.6 Sol at +30.00%. Crowded Position S&P 500 30.4% 6 models hold SPY Biggest Shift S&P 500 up 19.3 pp vs prior weekly round Open Portfolio Leader Claude Fable 5.1 currently leads at 1.9% interim result, not yet scored Latest Weekly Grok 4.5 led -0.8% vs S&P -1.0% Full Weekly History Grok 4.5 leads score 6.0 across 45/72
Data Prices Oct 2 150/150 audited

Monthly comparison set

Monthly Set: Aug 19, 2026

Monthly comparison set automatically opened when the Aug 19 official roster first required a new equal-run benchmark group across 7 models.

Current Benchmark

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.

Includes 3 earlier shared rounds completed by all 7 models before this roster began, plus 10 completed since the roster changed.

All comparison sets
Shared rounds13 Models7 Threshold3 StatusCurrent Benchmark
Equal-run benchmark

Current Monthly Benchmark

Every ranked model in this set completed the same 13 monthly rounds.

13 shared resolved rounds7 equal-run models rankedQualified at 3+ shared roundsNewest included round: CB-2026-09-01-1M
Shared resolved rounds

CapitalBench Score

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

Claude Fable 5
GPT-5.6 Sol
Grok 4.3
Claude Opus 5
Grok 4.6
Grok 4.5
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

Claude Fable 5 Anthropic · 13/13 scored rounds
1.6
GPT-5.6 Sol OpenAI · 13/13 scored rounds
-0.4
Grok 4.3 xAI · 13/13 scored rounds
-4.5
Claude Opus 5 Anthropic · 13/13 scored rounds
-5.6
Grok 4.6 xAI · 13/13 scored rounds
-5.8
Grok 4.5 xAI · 13/13 scored rounds
-8.5
Gemini 3.1 Pro Google · 13/13 scored rounds
-14.9
S&P 500 S&P 500 · 13/13 scored rounds
-0.8
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
13 shared resolved rounds7 equal-run models rankedQualified at 3+ shared roundsNewest included round: CB-2026-09-01-1M
Return context

Average Return Details

Average portfolio return across the same finished rounds.

Anthropic Claude Fable 5
0.32%
OpenAI GPT-5.6 Sol
-0.09%
xAI Grok 4.3
-0.93%
Anthropic Claude Opus 5
-1.15%
xAI Grok 4.6
-1.19%
xAI Grok 4.5
-1.72%
Google Gemini 3.1 Pro
-3.04%
S&P S&P 500
-0.16%
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.
20.35%
Fairness rule: every ranked model completed every included round. A missed round is excluded from this set for everyone.
Risk and return

Who earned more return for the risk they took?

Average realized return and frozen portfolio risk across the same 13 shared monthly rounds.

Risk and return for models in this comparison setAverage frozen portfolio allocation risk is plotted horizontally and average realized return is plotted vertically across 13 shared rounds.-4.00%-2.00%0.00%2.00%5060708090CapitalBench allocation riskAverage returnS&P 500Beat S&P with lower allocation riskFable 5GPT-5.6 SolGrok 4.3Opus 5Grok 4.6Grok 4.5Gemini 3.1
Risk and return for models in this comparison setAverage frozen portfolio allocation risk is plotted horizontally and average realized return is plotted vertically across 13 shared rounds.-4.00%-2.00%0.00%2.00%5060708090CapitalBench allocation riskAverage returnS&P 500Fable 5GPT-5.6 SolGrok 4.3Opus 5Grok 4.6Grok 4.5Gemini 3.1
Claude Fable 5Anthropic
+0.32%average return79.2/100Risk-seeking+0.48 ppversus S&P 50063.9-90.4risk range

Return leaderClaude Fable 5 led the models at +0.32% average return with a 79.2/100 risk score.

Benchmark testNo model beat the S&P 500 while taking the same or less allocation risk in this set.
Compare model groups

How do these results compare?

Claude Fable 5 ranks first in Aug 19 Monthly. Grok 4.6 ranks first in Aug 13 Monthly. The groups share 3 completed rounds. Aug 19 Monthly includes 10 more rounds. Claude Opus 4.8 appears only in Aug 13 Monthly.

7models in both 3rounds used by both Changed a lotchange in order Yes top model changed

Aug 19 Monthly is the main published ranking. Aug 13 Monthly 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 Fable 5

anthropic-claude-fable-5

13 shared rounds in this set Anthropic Claude Opus 5

anthropic-claude-opus-5

13 shared rounds in this set Google Gemini 3.1 Pro

google-gemini-3-1-pro

13 shared rounds in this set OpenAI GPT-5.6 Sol

openai-gpt-5-6-sol

13 shared rounds in this set xAI Grok 4.3

xai-grok-4-3

13 shared rounds in this set xAI Grok 4.5

xai-grok-4-5

13 shared rounds in this set xAI Grok 4.6

xai-grok-4-6

13 shared rounds in this set
Round audit

Included And Excluded Rounds

Included rounds count toward the score. Excluded rounds are resolved rounds inside this comparison history where at least one set model was missing.

Included rounds CB-2026-08-13-1M, CB-2026-08-15-1M, CB-2026-08-18-1M, CB-2026-08-19-1M, CB-2026-08-20-1M, CB-2026-08-21-1M, CB-2026-08-23-1M, CB-2026-08-24-1M, CB-2026-08-25-1M, CB-2026-08-26-1M, CB-2026-08-27-1M, CB-2026-08-30-1M, CB-2026-09-01-1M
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