Only models with substantial code pretraining track entity state through a sequence of operations, and all degrade as the sequence lengthens.

Capability: Tracking state through a long task

Sources

supportsEntity Tracking in Language Models
Only models with substantial code pretraining track entity state through a sequence of operations, and all degrade as the sequence lengthens.

Status: activeLast checked: 2026-09-03Evidence activity

Disagreeing is the most useful thing you can do here. Both sides of every contested claim in this catalog were assembled by the same person, which is its weakest point.

Related claims

Most models claiming long contexts fail well before their advertised length on synthetic retrieval, tracing and aggregation tasks.Losing information in long inputs
On verifiable instructions such as length and format constraints, strong models still fail a meaningful share, and failures grow when several constraints apply at once.Following an unfamiliar procedure