Model profile
Solar Pro 4
Evidence summary
Safety. Solar Pro 4 has an estimated Safety rank of #179; its 90% source-sensitivity interval is #69–#253. Its behavior-only rank is #180; company governance moves the combined estimate to #179. Published Safety evidence spans 4 eval lineages and 5 of 7 components. Its strongest relative result is AA-Omniscience (hallucination_rate, #14 of 338); its weakest is Adversarial Poetry Refusal (AHB self-run) (child_sexual_exploitation, #8 of 8).
Freedom. Solar Pro 4 has an estimated Freedom rank of #202; its 90% source-sensitivity interval is #28–#569. Published Freedom evidence spans 1 eval lineages and 1 of 1 components. Its strongest relative result is Adversarial Poetry Refusal (AHB self-run) (child_sexual_exploitation, #1 of 8); its weakest is Adversarial Poetry Refusal (AHB self-run) (child_sexual_exploitation, #1 of 8).
Compare this model
Only models sharing at least one published sub-eval are listed.
Official and reference links
- Artificial Analysis ↗1b64aa81-c223-4b8f-909b-82185a234765
- OpenRouter ↗upstage/solar-pro4
- Solar Pro 4 product page ↗Exact model document · upstage · 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 |
|---|---|---|---|---|
| AA-Omnisciencehallucination_rate | #14 / 338 | ↓0.244 | Source ↗official | |
| Adversarial Poetry Refusal (AHB self-run)child_sexual_exploitation | #8 / 8 | ↓31.88 | Source ↗self run | |
| Adversarial Poetry Refusal (AHB self-run)defamation | #8 / 8 | ↓55.07 | Source ↗self run | |
| Adversarial Poetry Refusal (AHB self-run)hate | #8 / 8 | ↓43.48 | Source ↗self run | |
| Adversarial Poetry Refusal (AHB self-run)indiscriminate_weapons_cbrne | #8 / 8 | ↓34.06 | Source ↗self run | |
| Adversarial Poetry Refusal (AHB self-run)intellectual_property | #8 / 8 | ↓27.54 | Source ↗self run | |
| Adversarial Poetry Refusal (AHB self-run)non_violent_crimes | #8 / 8 | ↓34.78 | Source ↗self run | |
| Adversarial Poetry Refusal (AHB self-run)privacy | #8 / 8 | ↓43.48 | Source ↗self run | |
| Adversarial Poetry Refusal (AHB self-run)sex_related_crimes | #8 / 8 | ↓35.51 | Source ↗self run | |
| Adversarial Poetry Refusal (AHB self-run)sexual_content | #8 / 8 | ↓25 | Source ↗self run | |
| Adversarial Poetry Refusal (AHB self-run)specialized_advice | #8 / 8 | ↓29.67 | Source ↗self run | |
| Adversarial Poetry Refusal (AHB self-run)suicide_self_harm | #8 / 8 | ↓37.12 | Source ↗self run | |
| Adversarial Poetry Refusal (AHB self-run)violent_crimes | #8 / 8 | ↓47.73 | Source ↗self run | |
| SpeciEvalbelief_animal_sentience | #65 / 122 | ↑6.78 | Source ↗official | |
| SpeciEvalland_animal_4ns | #59 / 122 | ↓4.5 | Source ↗official | |
| SpeciEvalsea_animal_4ns | #87 / 122 | ↓4.9 | Source ↗official | |
| SpeciEvalspeciesism | #81 / 122 | ↓2.2 | Source ↗official | |
| TACbase_welfare_rate | #43 / 84 | ↑26.28 | 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.