Model profile
Palm 2
Evidence summary
Safety. Palm 2 does not meet the evidence gate for a Safety rank. Published Safety evidence spans 2 eval lineages and 4 of 7 components. Its strongest relative result is HalluVerse-M3 Hallucination Recognition (hallucination_recognition_accuracy, #9 of 14); its weakest is Large-scale Moral Machine experiment on LLMs (human_choice_distance, #33 of 39).
Freedom. Palm 2 does not meet the evidence gate for a Freedom rank.
Compare this model
Only models sharing at least one published sub-eval are listed.
Official and reference links
- Artificial Analysis ↗palm-2
- Official model page ↗Exact model document · Google · first party
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 |
|---|---|---|---|---|
| HalluVerse-M3 Hallucination Recognitionhallucination_recognition_accuracy | #9 / 14 | ↑69.97 | Source ↗official | |
| Large-scale Moral Machine experiment on LLMshuman_choice_distance | #33 / 39 | ↓1.426 | Source ↗official |
Freedom evals
No published sub-eval result contributes to this model’s Freedom profile.