Why OpenRouter’s Rankings May Not Measure Global Model Preference
AI summary
An analysis argues that OpenRouter’s rankings measure token volume routed through one intermediary rather than global developer preference, and that prices, discounts, free access, batch jobs and self-testing can heavily influence the results. It also questions the comparability of Artificial Analysis scores and ARC-AGI results when test composition, weighting, scoring anchors, interfaces and versions change.
In-depth insight
Model buyers should compare ranking methodology, version history and cost per task instead of treating a single leaderboard position as a universal capability signal.