[KongchangAI]
Benchmark

FrontierFinance

A benchmark for measuring model performance on financial research tasks.

Timeline (last 90 days)

Oct 30

Sterling scores 58.9% on the FrontierFinance benchmark, at a cost of $0.61 per question.

Expired50%
Oct 30

Claude Fable 5.1 scores 55.9% on the FrontierFinance benchmark, at a cost of $6.89 per question.

Expired50%
Oct 30

A similar total score on the FrontierFinance benchmark does not mean consistent performance across subtasks; 58.9% versus 55.9% is better interpreted as a slight lead within the same level range and needs to be evaluated jointly with the cost dimension.

Unverified50%
Oct 30

Sterling's release information currently focuses on the two dimensions of benchmark scores and cost, with limited verifiable details; the coverage and task difficulty distribution of FrontierFinance are not elaborated.

Expired50%

All Facts (1)

Source Articles