Samaya AI released FrontierFinance, a new public benchmark for measuring AI Agents in investment workflows, and published evaluation results on July 29, 2026, in Mountain View, Calif. FrontierFinance consists of 220 diverse queries and 11,543 expert-crafted rubrics, covering use cases including Screening & Discovery, Company Research, Sector, Industry & Macro Analysis, Earnings and Events, and Coverage & Catalyst Monitoring. Samaya's proprietary AI system outperformed all evaluated models, including Anthropic Claude Fable 5, Claude Opus 4.8, OpenAI GPT-5.6 Sol, Google Gemini 3.1 Pro, GLM 5.2, and DeepSeek V4 Pro. Samaya (low effort) scored 50.8% accuracy at 4x lower inference cost than Fable 5, and Samaya (high effort) scored 56% accuracy at 2x lower cost than Fable 5. Anthropic's Claude Fable 5 was the best performing frontier model at 49.2%, followed by GPT-5.6 Sol at 46.8% and Claude Opus 4.8 at 45%. Maithra Raghu, CEO and Founder of Samaya AI, stated that investment use cases are uniquely hard for AI because being almost correct is still a loss.