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:
More from Finance
Nov 19 Arizona opens criminal investigation into OpenAI over what it calls rogue AI agents in banks Nov 19 Citi tells customers they are on their own if third-party AI agents misuse their accounts Nov 18 Klarna launches an AI concierge that books, shops and drafts emails Nov 18 Singapore sets up sandbox for AI agent payments under new national AI missions for finance Nov 18 Payhawk raises $280 million at a $2 billion valuation to build an AI-agent finance platformFinance AI Weekly
Weekly newsletter about AI in finance. Covers AI-driven trading, fintech innovations, and data analytics transforming markets
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 moreYou may also like
New coding benchmark puts Claude Opus 5.5 on top and opens a 35-point gap that DeepSWE hid
Artificial Analysis Index v5: open-weight models fall 12 points behind
Gemini 4 Carbon tops MathArena's maths ranking, ahead of Claude Fable 5.2 and GPT-6.1 Sol
Epoch AI finds no model meets its employee standard, but Fable 5.2 matches contractors on data center research
Terminal X Reports 88.6% Reviewer Agreement for GPT-6.1 Sol
Daily AI Brief: the AI news that matters, in your inbox.