‹ PublicAI Index
The LLM benchmark aggregator.
Laguna XS.2
Other
Strongest in Science (#104 of 122), weakest in Professional (#189 of 194). Above par in 0 of 10 scopes. Among the models it meets almost everywhere, it finishes behind Claude Opus 5 and Claude Fable 5.1 and ahead of Mercury 2.5 and Command R+.
§ 1 · Profile
What it is good at
Bars run from 50 — the average of the models each source lists — so right of the line is above par. The middle column is the gap to whoever leads that scope.
Reasoning43.2−22.2#152/1951/5
Science35.4−28.1#104/1221/1
Knowledge43.7−18.8#166/1971/3
Academic knowledge34.8−29.1#111/1231/1
Coding39.5−26.7#171/1791/6
Agentic coding38.8−28.1#164/1731/5
Professional36.7−25.7#189/1941/2
Finance37.5−24.9#147/1621/1
Medical31.1−35.4#147/1491/1
Legal36.3−29.6#162/1731/1
§ 2 · Head to head
What it beats, and what beats it
The same models turn up scope after scope. Counted once: where both were placed, who finished higher. Bars run right for Laguna XS.2, left for the other.
§ 3 · Sources
Where the numbers come from
1 publication, 11 figures. Every one links to the page it was read from.
Vals · Legal Research Bench 0.96%Vals · LegalBench 71.03%Vals · Finance Agent 15.6%Vals · CorpFin 56.33%Vals · TaxEval 58.95%Vals · MedCode 21.25%Vals · MedScribe 61.43%Vals · SWE-bench Verified 55.2% (Mini-SWE-agent)Vals · Vibe Code Bench 5.21% (OpenHands)Vals · GPQA Diamond 55.05%Vals · MMLU Pro 69.05%
Badge
[](https://publicai.io/model-index/m/laguna-xs-2)