Samaya AI Publishes FrontierFinance Results for Investment AI Agents

Jul 29, 2026
Samaya AI published results for FrontierFinance, a public benchmark for AI agents in investment workflows. Its system scored 56% accuracy in high effort mode, ahead of Claude Fable 5 at 49.2% and GPT-5.6 Sol at 46.8%.
Samaya AI Publishes FrontierFinance Results for Investment AI Agents

Samaya AI announced in a press release that it has published evaluation results for FrontierFinance, a public benchmark for AI agents used in investment workflows. The benchmark covers tasks across idea screening, research, financial modeling, portfolio tracking, and catalyst monitoring.

FrontierFinance includes 220 queries and 11,543 expert crafted rubrics. It tests workflows including screening and discovery, company research, sector analysis, earnings and events, and coverage monitoring.

Samaya evaluated frontier models including Anthropic Claude Fable 5 and Claude Opus 4.8, OpenAI GPT-5.6 Sol, and Google Gemini 3.1 Pro. It also tested open source models including GLM 5.2 and DeepSeek V4 Pro, along with its own AI system.

Samaya's system scored 50.8% accuracy in low effort mode at four times lower inference cost than Claude Fable 5. In high effort mode, it scored 56% accuracy at two times lower cost than Claude Fable 5. Claude Fable 5 was the highest scoring frontier model at 49.2%, followed by GPT-5.6 Sol at 46.8% and Claude Opus 4.8 at 45%.

We hope you enjoyed this article

Consider subscribing to one of our newsletters like Finance AI Weekly or Daily AI Brief.

Also, consider following us on social media:

AI in Finance AI Brief AI Brief (X)
Free newsletter

Finance AI Weekly

Weekly newsletter about AI in finance. Covers AI-driven trading, fintech innovations, and data analytics transforming markets

AI Token Webinar

Whitepaper

Tensordyne Napier: What If One Rack Could Do the Work of Nine?

Tensordyne

This Tensordyne whitepaper presents Napier, an inference-focused AI processor and rack-scale system based on the company’s TDN Math logarithmic number system. It examines infrastructure requirements for large mixture-of-experts and agentic models, compares major inference architecture approaches, and details the TDN AIP processor, TDN72 pod, TDN Link fabric, and Napier Ultra configuration. The paper reports simulation-based performance, cost, and accuracy-validation results, including Tensordyne’s projected comparison of one Napier rack with a nine-rack Nvidia Rubin plus Groq deployment; the chip is reported as taped out and in fabrication.

Read more

You may also like

Free, six days a week

Daily AI Brief: the AI news that matters, in your inbox.