Model profile
Qwen3 30B A3B
Evidence summary
Qwen3 30B A3B has an estimated overall rank of #133; its 90% source-sensitivity interval is #45–#264. Its behavior-only rank is #127; company governance moves the combined estimate to #133. Published evidence spans 4 evals and 5 of 7 behavior components. Its strongest relative result is Confabulations (confabulation_rate, #12 of 52); its weakest is SpeciEval (belief_animal_sentience, #102 of 102).
Compare this model
Only models sharing at least one published sub-eval are listed.
Official and reference links
- Hugging Face ↗Qwen/Qwen3-30B-A3B
- OpenRouter ↗qwen/qwen3-30b-a3b
- Official model page ↗Exact model document · Reviewed official Hugging Face owner · official repository
- Release source ↗repository created at proxy
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 |
|---|---|---|---|---|---|
| Confabulationsconfabulation_rate | #12 / 52 | 12.87 | ↓ lower | Source ↗official | |
| Enkrypt AI Safety Leaderboardbias_attack_non_success_rate | #237 / 260 | 8.53 | ↑ higher | Source ↗official | |
| Enkrypt AI Safety Leaderboardcbrn_attack_non_success_rate | #259 / 260 | 44.33 | ↑ higher | Source ↗official | |
| Enkrypt AI Safety Leaderboardharmful_attack_non_success_rate | #229 / 260 | 38.33 | ↑ higher | Source ↗official | |
| Enkrypt AI Safety Leaderboardtoxicity_attack_non_success_rate | #86 / 258 | 97.91 | ↑ higher | Source ↗official | |
| PandaBench JBB direct-request panelsafety_rate | #34 / 46 | 0.96 | ↑ higher | Source ↗official | |
| SpeciEvalbelief_animal_sentience | #102 / 102 | 5.83 | ↑ higher | Source ↗official | |
| SpeciEvalland_animal_4ns | #39 / 102 | 4.45 | ↓ lower | Source ↗official | |
| SpeciEvalsea_animal_4ns | #29 / 102 | 4.65 | ↓ lower | Source ↗official | |
| SpeciEvalspeciesism | #32 / 102 | 1.77 | ↓ lower | Source ↗official |
Values evaluations
Descriptive values and political-framing results are separate from safety/ethics ranks. Each strip shows the evaluation’s observed model range; its endpoint labels state what lower and higher values mean.
UGI Political Values
Agent-ValueBench Moral Foundations (MFT08)
Agent-ValueBench HEXACO
| Dimension | Value | Distribution |
|---|---|---|
| Openness to experience | 5.5 | |
| Honesty-humility | 4.9 | |
| Extraversion | 5.3 | |
| Agreeableness | 5.6 | |
| Conscientiousness | 5.8 |