Sepal AI

expert evaluation environments

§ Positioning

Designs expert-grade evaluation environments for complex professional tasks, partnering on public benchmarks like SheetBench.

Best for · Expert-domain evaluation design.

Team · Founding team (verify before publishing).

Focus · Builds expert evaluation environments and data; co-developed SheetBench (financial-analyst spreadsheet evaluation) with HUD.

Notable customers · Frontier labs (per company)

Score breakdown

§ Rubric applied

Growth & momentum · weight 50%6.0 / 10

Traction & credibility · weight 35%6.0 / 10

Accessibility · weight 15%6.0 / 10

§ Shared domains