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 S&P 500 36.2% 5 models hold SPY Biggest Shift S&P 500 down 56.7 pp vs prior weekly round Open Portfolio Leader Gemini 3.1 Pro currently leads at 0.7% 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

Fair model comparisons

Benchmark Sets

Equal-run rankings for fixed model rosters using only shared completed rounds.

Living equal-run rosters

All Benchmark Sets

Older sets keep accumulating shared rounds. New official rosters are opened automatically only when no existing set already contains the models in that run. Sets qualify at 6 weekly shared rounds or 3 monthly shared rounds.

Compare sets Methodology
Weekly Current Benchmark
Sep 28, 2026 roster

Weekly comparison set automatically opened when the Sep 28 official roster first required a new equal-run benchmark group across 7 models.

6 shared rounds 7 models Met current threshold
Open set
Monthly Current Benchmark
Sep 28, 2026 roster

Monthly comparison set automatically opened when the Sep 28 official roster first required a new equal-run benchmark group across 7 models.

3 shared rounds 7 models Met current threshold
Open set
Weekly Qualified
Sep 4, 2026 roster

Weekly comparison set automatically opened when the Sep 4 official roster first required a new equal-run benchmark group across 7 models.

8 shared rounds 7 models Met 6+ threshold
Open set
Weekly Qualified
Aug 19, 2026 roster

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

14 shared rounds 7 models Met 6+ threshold
Open set
Weekly Qualified
Jul 24, 2026 roster

Weekly comparison set automatically opened when the Jul 24 official roster first required a new equal-run benchmark group across 8 models.

11 shared rounds 8 models Met 6+ threshold
Open set
Weekly Qualified
Jul 21, 2026 roster

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

20 shared rounds 7 models Met 6+ threshold
Open set
Weekly Qualified
Jul 10, 2026 roster

Weekly comparison set automatically opened when the Jul 10 official roster first required a new equal-run benchmark group across 8 models.

6 shared rounds 8 models Met 6+ threshold
Open set
Weekly Qualified
Jul 8, 2026 roster

Weekly comparison set that starts when Grok 4.5 joins the weekly benchmark roster.

8 shared rounds 7 models Met 6+ threshold
Open set
Weekly Qualified
Jun 9, 2026 roster

Weekly comparison set that starts when Claude Fable 5 joins the weekly benchmark roster.

15 shared rounds 6 models Met 6+ threshold
Open set
Weekly Qualified
May 28, 2026 roster

Weekly comparison set that adds Claude Opus 4.8 to the established model roster.

33 shared rounds 5 models Met 6+ threshold
Open set
Weekly Qualified
May 24, 2026 roster

Original weekly comparison set for the first four CapitalBench models.

35 shared rounds 4 models Met 6+ threshold
Open set
Monthly Qualified
Sep 4, 2026 roster

Monthly comparison set automatically opened when the Sep 4 official roster first required a new equal-run benchmark group across 7 models.

8 shared rounds 7 models Met 3+ threshold
Open set
Monthly Qualified
Aug 19, 2026 roster

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

14 shared rounds 7 models Met 3+ threshold
Open set
Monthly Qualified
Aug 13, 2026 roster

Monthly comparison set automatically opened when the Aug 13 official roster first required a new equal-run benchmark group across 8 models.

3 shared rounds 8 models Met 3+ threshold
Open set
Monthly Qualified
Jul 24, 2026 roster

Monthly comparison set automatically opened when the Jul 24 official roster first required a new equal-run benchmark group across 8 models.

11 shared rounds 8 models Met 3+ threshold
Open set
Monthly Qualified
Jul 21, 2026 roster

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

19 shared rounds 7 models Met 3+ threshold
Open set
Monthly Qualified
Jul 10, 2026 roster

Monthly comparison set automatically opened when the Jul 10 official roster first required a new equal-run benchmark group across 8 models.

5 shared rounds 8 models Met 3+ threshold
Open set
Monthly Qualified
Jul 8, 2026 roster

Monthly comparison set that starts when Grok 4.5 joins the monthly benchmark roster.

7 shared rounds 7 models Met 3+ threshold
Open set
Monthly Qualified
Jun 9, 2026 roster

Monthly comparison set that starts when Claude Fable 5 joins the monthly benchmark roster.

13 shared rounds 6 models Met 3+ threshold
Open set
Monthly Qualified
May 28, 2026 roster

Monthly comparison set that adds Claude Opus 4.8 to the established model roster.

32 shared rounds 5 models Met 3+ threshold
Open set
Monthly Qualified
May 10, 2026 roster

Original monthly comparison set for the first four CapitalBench models.

35 shared rounds 4 models Met 3+ threshold
Open set
Weekly Forming
Oct 19, 2026 roster

Weekly comparison set automatically opened when the Oct 19 official roster first required a new equal-run benchmark group across 6 models.

2 shared rounds 6 models 2/6 4 more to qualify
Open set
Weekly Forming
Sep 3, 2026 roster

Weekly comparison set automatically opened when the Sep 3 official roster first required a new equal-run benchmark group across 7 models.

1 shared rounds 7 models 1/6 5 more to qualify
Open set
Weekly Forming
Aug 13, 2026 roster

Weekly comparison set automatically opened when the Aug 13 official roster first required a new equal-run benchmark group across 8 models.

3 shared rounds 8 models 3/6 3 more to qualify
Open set
Monthly Forming
Sep 3, 2026 roster

Monthly comparison set automatically opened when the Sep 3 official roster first required a new equal-run benchmark group across 7 models.

1 shared rounds 7 models 1/3 2 more to qualify
Open set
Monthly Waiting
Oct 19, 2026 roster

Monthly comparison set automatically opened when the Oct 19 official roster first required a new equal-run benchmark group across 6 models.

0 shared rounds 6 models 0/3 3 more to qualify
Open set
Selection rule

How Does a Set Become Current?

Fixed roster A set starts when the model roster changes. Missed rounds excluded If one set model is missing, that round is excluded for everyone. Newest qualified wins The newest qualified weekly or monthly set becomes current automatically.
Cross-set evidence

How do results change between model groups?

Main published results compared with the newest groups that have results.

Weekly Sep 28 Weekly vs Oct 19 Weekly

GPT-6 Astra ranks first in both groups. The groups have no completed rounds in common. Sep 28 Weekly includes 6 more rounds, while Oct 19 Weekly includes 2 more rounds. Gemini 4 Argon appears only in Oct 19 Weekly. Grok 4.3, Gemini 3.1 Pro appear only in Sep 28 Weekly.

5models in both 0rounds used by both Changed a littlechange in order Notop model changed

Use Sep 28 Weekly as the more reliable ranking because it has 6 completed rounds. Oct 19 Weekly has 2 and needs 4 more before it has enough evidence to become the main ranking.

Compare weekly groups
Monthly Sep 28 Monthly vs Sep 4 Monthly

Grok 4.5 ranks first in Sep 28 Monthly. GPT-6 Astra ranks first in Sep 4 Monthly. The groups have no completed rounds in common. Sep 28 Monthly includes 3 more rounds, while Sep 4 Monthly includes 8 more rounds. Claude Opus 5 appears only in Sep 4 Monthly. Claude Opus 5 5 appears only in Sep 28 Monthly.

6models in both 0rounds used by both Changedchange in order Yestop model changed

Sep 28 Monthly is the main published ranking. Sep 4 Monthly also has enough rounds, so compare them to see whether the results hold across different model groups.

Compare monthly groups