Anthropic released Opus 4.7 this morning. It’s now available in our agent harness, Felix.

At Rogo, we run dedicated testing to evaluate each model’s performance across core financial workflows. As a model-agnostic business, we dynamically route tasks to the systems that perform best for a given job. This approach enables higher-quality outputs while maintaining token efficiency for our customers.

Our evaluation framework goes beyond measuring raw financial intelligence. We place a strong emphasis on artifact creation, which is central to how financial work is actually consumed. Supported by professionals with deep finance expertise, our internal testing assesses not only correctness but also the structure, clarity, and usability of generated outputs.

In our most recent benchmarks, we focused specifically on artifact generation in PowerPoint and Excel, reflecting the primary formats used in real-world financial analysis and reporting.

In our initial testing, Opus 4.7 shows strong improvements in PowerPoint generation and reflects another strong step forward in artifact creation writ large. We are excited to bring its capabilities into production.