Benchmark RadarAI BENCHMARK PROFILE
INS-ActBench
INS-ActBench evaluates actuarial capability in LLMs across knowledge, case reasoning, and tool-based practice with 12,050 tasks from public exams.
- Released
- 2026-07-27
- Readiness
- Runnable
- Primary field
- Finance & Economics
Why it matters
Provides a reproducible foundation for assessing professional actuarial assistance, revealing capability gaps in case reasoning and tool use.
Motivation
Large Language Models (LLMs) have shown strong potential in financial reasoning, but existing benchmarks often evaluate domain knowledge, numerical reasoning, long-context understanding, and tool use in separate settings.
Primary resources
Benchmark Radar records only publicly supported details and links back to primary sources for verification.