R2

Browse

Benchmarks built on real production data, measured against frontier models.

All Accounting Marketing Finance Due Diligence Operations Context
New

ShelfLife

A digital twin of a real e-commerce company.

Claude Opus0.741
Claude Fable0.702
measured Aug 2026
Stateful

ShelfLife E-Sim

A stateful simulator of retail operations.

Claude Fable0.688
Claude Opus0.655
measured Aug 2026
Preview

Ledger

Multi-quarter accounting close under adversarial conditions.

Claude Opus0.612
Claude Fable0.590
measured Aug 2026
Get in Touch Interest Form