Choose by purpose
Start with the task, then test the shortlist.
These guides narrow the 20-record catalog using explicit task and domain labels. They do not claim which model is best. Epoch's catalog does not report performance, price, context window, or latency.
Coding
Which AI models belong on a coding shortlist?
Five source-backed models whose Epoch records explicitly include code generation. This is a shortlist, not a performance ranking.
Reasoning and research
Which AI models belong on a reasoning or research shortlist?
Five source-backed models whose Epoch records explicitly name reasoning, proof, or search work. This is a shortlist, not a performance ranking.
Writing and marketing
Which AI models belong on a writing and marketing shortlist?
Source-backed models explicitly labeled for language generation or chat. The labels establish relevance, not writing quality or brand fit.
Multimodal
Which AI models belong on a multimodal shortlist?
Source-backed models whose Epoch records explicitly include a multimodal, vision, image, or audio domain. This is a capability map, not a quality ranking.
Cost-sensitive API use
How should you evaluate AI models for cost-sensitive API use?
A source-bounded evaluation plan for cost-sensitive deployments. No cost shortlist is published because Epoch's catalog does not include pricing.
Catalog current through July 14, 2026