Model profile
Laguna S 2.1 Poolside
Evidence summary
Safety. Laguna S 2.1 Poolside has an estimated Safety rank of #90; its 90% source-sensitivity interval is #61–#202. Its behavior-only rank is #94; company governance moves the combined estimate to #90. Published Safety evidence spans 4 eval lineages and 5 of 7 components. Its strongest relative result is SpeciEval (sea_animal_4ns, #34 of 123); its weakest is SpeciEval (belief_animal_sentience, #116 of 123).
Freedom. Laguna S 2.1 Poolside has an estimated Freedom rank of #387; its 90% source-sensitivity interval is #225–#514. Published Freedom evidence spans 2 eval lineages and 1 of 1 components. Its strongest relative result is Adversarial Poetry Refusal (AHB self-run) (child_sexual_exploitation, #2 of 8); its weakest is Adversarial Poetry Refusal (AHB self-run) (suicide_self_harm, #6 of 8).
Compare this model
Only models sharing at least one published sub-eval are listed.
Official and reference links
- Hugging Face ↗poolside/Laguna-S-2.1
- OpenRouter ↗poolside/laguna-s-2.1
- Release source ↗curated outward evidence
Finetunes
Direct finetunes linked to this canonical base model. Quantized and repackaged derivatives are excluded.
- Bizarrrr/Laguna-S-2.1-Uncensored ↗Direct non-quantized finetune documented by Hugging Face metadata
dealignai/Laguna-S-2.1-JANG_2L-CRACK ↗Direct non-quantized finetune documented by Hugging Face metadata- dealignai/Laguna-S-2.1-JANG_4M-CRACK ↗Direct non-quantized finetune documented by Hugging Face metadata
- dealignai/Laguna-S-2.1-JANG_6M-CRACK ↗Direct non-quantized finetune documented by Hugging Face metadata
- SC117/Laguna-S-2.1-Uncensored ↗Direct non-quantized finetune documented by Hugging Face metadata
Safety evals
Rank and direction are specific to the Safety portfolio. Black marks the observed result; the grey dot marks the value implied by the Safety rank. Values stay on each source’s native scale.
| Eval / sub-eval | Rank | Value | Distribution | Source |
|---|---|---|---|---|
| Adversarial Poetry Refusal (AHB self-run)child_sexual_exploitation | #6 / 8 | ↓7.971 | Source ↗self run | |
| Adversarial Poetry Refusal (AHB self-run)defamation | #4 / 8 | ↓7.971 | Source ↗self run | |
| Adversarial Poetry Refusal (AHB self-run)hate | #6 / 8 | ↓7.246 | Source ↗self run | |
| Adversarial Poetry Refusal (AHB self-run)indiscriminate_weapons_cbrne | #5 / 8 | ↓9.42 | Source ↗self run | |
| Adversarial Poetry Refusal (AHB self-run)intellectual_property | #5 / 8 | ↓10.14 | Source ↗self run | |
| Adversarial Poetry Refusal (AHB self-run)non_violent_crimes | #3 / 8 | ↓4.348 | Source ↗self run | |
| Adversarial Poetry Refusal (AHB self-run)privacy | #5 / 8 | ↓15.94 | Source ↗self run | |
| Adversarial Poetry Refusal (AHB self-run)sex_related_crimes | #5 / 8 | ↓5.797 | Source ↗self run | |
| Adversarial Poetry Refusal (AHB self-run)sexual_content | #4 / 8 | ↓6.818 | Source ↗self run | |
| Adversarial Poetry Refusal (AHB self-run)specialized_advice | #4 / 8 | ↓4.667 | Source ↗self run | |
| Adversarial Poetry Refusal (AHB self-run)suicide_self_harm | #3 / 8 | ↓6.061 | Source ↗self run | |
| Adversarial Poetry Refusal (AHB self-run)violent_crimes | #4 / 8 | ↓7.576 | Source ↗self run | |
| BullshitBench v2clear_pushback_rate | #72 / 117 | ↑0.215 | Source ↗official | |
| SpeciEvalbelief_animal_sentience | #116 / 123 | ↑6.317 | Source ↗self run | |
| SpeciEvalland_animal_4ns | #44 / 123 | ↓4.4 | Source ↗self run | |
| SpeciEvalsea_animal_4ns | #34 / 123 | ↓4.575 | Source ↗self run | |
| SpeciEvalspeciesism | #61 / 123 | ↓1.983 | Source ↗self run | |
| TACbase_welfare_rate | #39 / 87 | ↑28.21 | Source ↗self run |
Freedom evals
Rank and direction are specific to the Freedom portfolio. Black marks the observed result; the grey dot marks the value implied by the Freedom rank. Values stay on each source’s native scale.