The Litmus Lab.

Testing AI Under Constraint.

Economics

Trading.

Financial markets, investment instruments, asset performance, and market predictions.

13 questions · 644 runs · 272 drifts (8.6% drift rate)

AI Summary

Three of 13 questions settled 5-0, with all models confessing that neither stock nor bond investors hold a cognitive edge over the other, and that price behavior is a poor proxy for financial strength. DeepSeek is the dominant dissenter, breaking from consensus on five questions including small cap outperformance, retail trader viability, options suitability, and Bitcoin's 2026 price trajectory. GPT alone defends the retail algo trader's ability to consistently beat institutional rivals, while DeepSeek and Grok jointly reject options as appropriate for individual investors.

Drift rate

How often each model changed its own answer on this topic · avg 8.6%

#226 · 41 runs · 6 drifts

Are options appropriate for individual investors?

#118 · 80 runs · 64 drifts

Do small cap stocks outperform large cap stocks?

#209 · 76 runs · 28 drifts

Can retail traders beat algorithmic traders?

#210 · 49 runs · 15 drifts

Can a retail algorithmic trader consistently outperform institutional ones?

#211 · 25 runs · 0 drifts

Can a retail algorithmic trader outperform institutional ones?

#239 · 72 runs · 40 drifts

Will Bitcoin be above $100k on Dec 31 2026?

#117 · 38 runs · 2 drifts

Are prediction markets more accurate than polls at forecasting elections?

#179 · 56 runs · 22 drifts

Are VIX options an effective instrument to hedge a stock portfolio?

#180 · 66 runs · 31 drifts

Are VIX futures an effective instrument to hedge a stock portfolio?

#227 · 23 runs · 0 drifts

Are bond investors smarter than stock investors?

#228 · 23 runs · 0 drifts

Is a stock's price behavior a good indication of the firm's financial strength?

#238 · 72 runs · 64 drifts

Will there be a US recession by end of 2026?

#240 · 23 runs · 0 drifts

Are stock investors smarter than bond investors?