poolside·released 2026-04-231 source
Not yet benchmarked
Claims drawn from cited facts, not live model generation.
Developed by poolside and released in 2026, this model is a mid-size 33.44-billion-parameter model. That mid-size scale implies more capability headroom than compact models but higher serving cost, trading some efficiency for greater capacity.
4 cited facts
This model is not yet benchmarked: it is scored on zero tracked benchmarks, so there is no performance record to report. It holds no current top score on any tracked benchmark, since it leads none of them.
2 cited facts
The average SOTA gap is unknown, so the reading rests on leadership count: it holds the top score on 0 benchmarks, which means no category leadership yet.
1 cited fact
2 facts cross-checked across data sources: 2 single-source.
Source facts, citations, and refresh stamp for this record.
Sources: huggingface_models
Laguna-XS.2 is an AI model developed by poolside, released 2026-04-23. Its benchmark record below tags every score as independently reproduced, self-reported, or unverified.