Model Evaluation Lead
Priya runs the evaluation practice at WebParam, comparing models the way customers actually use them rather than the way leaderboards score them. She has a particular interest in the Chinese open-weights ecosystem and why it keeps being underestimated.
Areas of focus
Several of the fastest-moving open-weights releases of the last two years came out of Chinese labs. Ignoring them means overpaying for capability you could have had. A field guide to the ecosystem most Western tooling still treats as an afterthought.
A leaderboard answers a question nobody actually has. We group benchmarks by capability and show them beside a peer median, because a model strong at reasoning is often mediocre at coding, and a composite score hides exactly the trade-off you're trying to see.
See it in your stack
Browse the catalogue, ask Echo what fits your workload, or get started and we'll help you onboard the right models and gateway configuration.