Poolsidereports that Laguna XS 2.1, its coding model, improves its multilingual coding benchmarkA standard public test set for comparing AI models — the shared scoreboards behind every "model X beats model Y" claim.Full definition → score (SWE-benchThe standard benchmark for AI coding agents: real GitHub issues from real repositories, scored by whether the agent's patch passes the project's own tests.Full definition → Multilingual) by 5.4 points to 63.1%, while retaining XS.2's architecture. The model has 33 billion parameters in total, with 3 billion active at each text-generation step.
The release also supplies versions that store model weights at reduced numerical precision for machines with tighter memory budgets. It follows the XS.2 release, making it an incremental coding-model upgrade with more deployment choices. The reported benchmark improvement comes from Poolside's own evaluation setup.
Terms in this piece · Glossary
benchmark — A standard public test set for comparing AI models — the shared scoreboards behind every "model X beats model Y" claim.
SWE-bench — The standard benchmark for AI coding agents: real GitHub issues from real repositories, scored by whether the agent's patch passes the project's own tests.
quantization — Shrinking a model by storing its numbers less precisely — like rounding — so it runs faster and fits on smaller hardware, at a small quality cost.
context window — The maximum amount of text a model can consider at once — its working memory for the current conversation or task.
