Samaya says Sterling beat Claude Fable 5.1 in finance benchmark
BROBROK News · Based on reporting by DiarioBitcoin ·
Samaya AI said its Sterling financial research agent outperformed Claude Fable 5.1 in the FrontierFinance benchmark while costing less per query. The company says the system was tuned for financial research and that the results come from a benchmark it developed itself.
Key points
- Sterling scored 58.9% on FrontierFinance, versus 55.9% for Claude Fable 5.1, according to Samaya.
- Samaya reported a cost of USD 0.61 per query for Sterling, compared with USD 6.89 for Anthropic’s model.
- The company says Sterling plans research, uses financial tools, and hands findings to another model for report writing.
- Sterling is based on Nemotron 3.5 Lightning, with 30 billion parameters in total and 3 billion active.
- Samaya notes the results are self-reported and tied to an internally built benchmark.
Why it matters
The report highlights how specialized agents and tool use can lower the cost of finance research workflows. But because the benchmark was created by Samaya, the comparison should be treated as company-reported rather than independent.
Original headline: “Samaya Sterling supera a Claude Fable 5.1 en investigación financiera por una fracción del costo”
Read the original on DiarioBitcoin
Summary and analysis written by BROBROK News from the original report. Read the full story on the source website. Not investment advice.