Terminal-Bench 2.1

Measures an agent’s ability to turn incomplete, distributed insurance evidence into an auditable underwriting decision while respecting authority and policy constraints.

Measures how well AI agents can turn fragmented plant-floor, engineering, and supplier evidence into safe, technically defensible decisions and actions.

Tests whether AI agents can reconcile revenue systems, enforce hard commercial controls, and carry a decision through to the correct business state.

Scores how agents gather evidence, perform financial analysis, follow compliance constraints, and complete required state updates in a simulated environment.

Evaluates AI agents on economically valuable professional work and verifiable workplace deliverables.

A benchmark to measure and evolve with the frontier of agent work: real terminal environments, real software engineering tasks, and a rolling task set that is revised as agents catch up to it.

The next frontier benchmark for agent work. A harder, more domain-diverse successor to Terminal-Bench 2.1 — built in the open, task by task, under continuous adversarial review.

Long-horizon professional workflows with verifiable outcomes across 55 sub-industries. 147 public tasks of a 1,500+ task corpus, sourced and validated by 300+ industry experts.

Measures code quality degradation in AI-assisted codebases. Tracks checkpoint solve rates, erosion (code bloat), and verbosity under realistic repo conditions.

Evaluates whether AI systems improve from prior experience across sequential, stateful tasks, measuring real in-context learning, not just raw capability.