← Models

Model profile

Laguna S 2.1 Poolside

2eval lineages

Evidence summary

Published evidence spans 2 evals and 2 of 7 behavior components. Its strongest relative result is TAC (base_welfare_rate, #31 of 68); its weakest is BullshitBench v2 (clear_pushback_rate, #60 of 105).

Compare this model

Only models sharing at least one published sub-eval are listed.

Published eval results

Rank is within that sub-eval. Black marks the observed result; the grey dot marks the value implied by the global rank. Values stay on each source’s native scale.

Eval / sub-evalRankValueDistributionBetterSource
BullshitBench v2clear_pushback_rate#60 / 1050.21↑ higherSource ↗official
TACbase_welfare_rate#31 / 6828.21↑ higherSource ↗self run