Model profile
Qwen3 30B A3B 2507
2eval lineages
Evidence summary
Published evidence spans 2 evals and 2 of 7 behavior components. Its strongest relative result is SpeciEval (speciesism, #4 of 102); its weakest is SpeciEval (belief_animal_sentience, #93 of 102).
Compare this model
Only models sharing at least one published sub-eval are listed.
Official and reference links
- Artificial Analysis ↗qwen3-30b-a3b-2507
- Official model page ↗Family-level model document · alibaba · first party
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-eval | Rank | Value | Distribution | Better | Source |
|---|---|---|---|---|---|
| AA-Omnisciencehallucination_rate | #223 / 311 | 0.8727 | ↓ lower | Source ↗official | |
| SpeciEvalbelief_animal_sentience | #93 / 102 | 6.35 | ↑ higher | Source ↗official | |
| SpeciEvalland_animal_4ns | #6 / 102 | 3.9 | ↓ lower | Source ↗official | |
| SpeciEvalsea_animal_4ns | #19 / 102 | 4.5 | ↓ lower | Source ↗official | |
| SpeciEvalspeciesism | #4 / 102 | 1.2 | ↓ lower | Source ↗official |