Agent Models

Chooses four OpenRouter models — low, mid, high-main, high-fallback — and writes them into the six places this repo pins a model id.

Standing constraints, not preferences:

Never pick a Grok / xAI model. rank_models.py filters them out entirely.
Prefer alternative labs. OpenAI, Anthropic and Google are eligible but only win a tier when clearly ahead of the best alternative; the point of these harnesses is to get a read on non-frontier-lab models.
Rank on Intelligence Index vs cost per Intelligence Index task, the two axes of the chart of that name on artificialanalysis.ai. This replaced the Agentic Index in September 2026, when AA stopped publishing it per model. The Coding Agent Index (/agents/coding-agents) was considered and passed over: it covers ~19 harness+model pairs, so most candidates are missing from it.

agent-models