Frontier AI Models Surpass Human Experts in Earnings Forecasting, Samaya Research Shows
Sign in✓ Signed in
For the first time, cutting-edge AI models have outperformed human equity analysts at forecasting corporate earnings surprises, according to research from financial AI platform Samaya. The company tested seven frontier AI models—including GPT-6 Astra, Claude Fable 5.1, and Claude Opus 5.5—against professional analyst consensus across 456 quarterly earnings releases, finding that only the most advanced models could beat even bias-corrected consensus predictions.
Continue reading
The rest of this article is for AI News Blitz readers. Choose an option below to keep reading.
Already purchased? Sign in✓ Signed in — this article isn’t included in your current plan.
Unlocking the full article...