Benchmark RadarAI BENCHMARK PROFILE
The Complexity Ceiling Benchmark
Complexity Ceiling Benchmark evaluates sequential reasoning decay with depth scaling across grounded spatial state-tracking, symbolic pointer manipulation, and transitive relational inference.
- Released
- 2026-06-28
- Readiness
- Paper only
- Primary field
- General AI
Why it matters
It quantifies reasoning degradation with step count, which could inform model development for long-horizon tasks.
Motivation
We introduce the Complexity Ceiling Benchmark (CCB), a controlled evaluation of how language-model reasoning decays as the number of required sequential steps grows.
Primary resources
Benchmark Radar records only publicly supported details and links back to primary sources for verification.