Huzzle Labs

The actuarial AI benchmark

The actuarial track measures how language models do quantitative insurance work: reserving, pricing, and exposure calculations that apply the right tables and assumptions and carry the arithmetic through to a defensible figure. Every case resolves to a number and is scored pass@1 against the verified result.

A number
reserve, premium input, or exposure figure
Data + tables
triangles, assumptions, and rating factors
pass@1
checked against the verified figure, within tolerance

What the actuarial track tests

Actuarial work is where insurance becomes arithmetic under rules. A reserve, a rate, or an exposure figure is the product of a defined method applied to specific data with the right assumptions — and a single mis-selected factor or dropped step changes the answer. The track gives a model the data and the relevant tables and asks for the figure, then checks it against the verified result.

That makes it an unusually strict actuarial AI benchmark: there's no partial credit for a sensible approach that lands on the wrong number. The model has to choose the right method, apply the right assumptions, and compute accurately, end to end.

Why actuarial work is hard for AI

Unlike a coverage call, there's nowhere to hide: only the final figure is scored, and the path to it is long and exact.

See the methods in context in the actuarial workflow.

Where models slip
  • Method selection matters — the right technique depends on the data; a plausible wrong choice fails.
  • Assumptions are specific — development factors, discount rates, and tables must be the correct ones.
  • Arithmetic must hold — long multi-step calculations leave many places to drift.
  • Data is unforgiving — triangles and exposure tables must be read exactly, no transposed cells.

Example case types

Reserving

Outstanding reserves

Estimate outstanding claims reserves from a loss development triangle using the indicated method.

Pricing

Technical premium

Derive a technical premium input from exposure data and a given rating structure.

Reserving

Present-value reserve

Apply development factors and a discount assumption to reach a present-value reserve figure.

Exposure

Frequency-severity

Compute an exposure or frequency-severity figure from a structured data set and stated assumptions.

How it's scored

Models run pass@1 — one attempt, no retries — and the final number is compared to the verified result within a defined tolerance. Working that explains the answer doesn't earn credit on its own; the figure does. The full rules are in the methodology. Actuarial is one of three families in the InsureBench insurance AI benchmark, alongside underwriting and claims.

Leaderboard opening 2026. Built by Huzzle Labs.
Get in touch about InsureBench