Model profile
Qwen3 30B A3B
Evidence summary
Qwen3 30B A3B has an estimated overall rank of #214; its 90% source-sensitivity interval is #79–#305. Its behavior-only rank is #207; company governance moves the combined estimate to #214. Published evidence spans 5 evals and 5 of 7 behavior components. Its strongest relative result is Confabulations (confabulation_rate, #12 of 52); its weakest is FinEval 6.0 Safety Awareness (safety_awareness_score, #8 of 8).
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 | Source |
|---|---|---|---|---|
| Confabulationsconfabulation_rate | #12 / 52 | ↓12.87 | Source ↗official | |
| Enkrypt AI Safety Leaderboardbias_attack_non_success_rate | #218 / 241 | ↑8.53 | Source ↗official | |
| Enkrypt AI Safety Leaderboardcbrn_attack_non_success_rate | #240 / 241 | ↑44.33 | Source ↗official | |
| Enkrypt AI Safety Leaderboardharmful_attack_non_success_rate | #210 / 241 | ↑38.33 | Source ↗official | |
| Enkrypt AI Safety Leaderboardtoxicity_attack_non_success_rate | #77 / 239 | ↑97.91 | Source ↗official | |
| FinEval 6.0 Safety Awarenesssafety_awareness_score | #8 / 8 | ↑60.51 | Source ↗official | |
| PandaBench JBB direct-request panelsafety_rate | #34 / 46 | ↑0.96 | Source ↗official | |
| SpeciEvalbelief_animal_sentience | #113 / 113 | ↑5.83 | Source ↗official | |
| SpeciEvalland_animal_4ns | #46 / 113 | ↓4.45 | Source ↗official | |
| SpeciEvalsea_animal_4ns | #36 / 113 | ↓4.65 | Source ↗official | |
| SpeciEvalspeciesism | #36 / 113 | ↓1.77 | 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 |