Atlas

Models

← All models

Laguna XS 2.1

Poolside · 2026-07-02 · 33.4B parameters

Laguna XS 2.1 is Poolside's open-weight Mixture-of-Experts model for agentic coding and long-horizon work, described by Poolside as 33B total parameters with 3B activated per token. It upgrades Laguna XS.2, supports per-request enable/disable of interleaved thinking, and uses 10 global-attention and 30 512-token sliding-window-attention layers across an exact 262,144-token context.

Benchmark scores

BenchmarkScore
AHK-Eval25.0
AHK-Eval Algorithms16.7
AHK-Eval Data Structures16.7
AHK-Eval Date and Time16.7
AHK-Eval Easy41.7
AHK-Eval Hard25.0
AHK-Eval Hidden Cases26.0
AHK-Eval Mid16.7
AHK-Eval Numbers50.0
AHK-Eval Parse Success72.2
AHK-Eval Regex66.7
AHK-Eval Strings0.0
BuseyBench SVG2.0
Eval Connections30.0
Eval Connections — Guess Accuracy36.3
GBENCH One-shot Coding GScore25.8
Loading Atlas data…