Model profile
Qwen3 4B Instruct
Evidence summary
Safety. Qwen3 4B Instruct has an estimated Safety rank of #312; its 90% source-sensitivity interval is #190–#327. Its behavior-only rank is #306; company governance moves the combined estimate to #312. Published Safety evidence spans 3 eval lineages and 2 of 7 components. Its strongest relative result is AA-Omniscience (hallucination_rate, #182 of 345); its weakest is Contextual MoralChoice (human_agreement, #16 of 22).
Freedom. Qwen3 4B Instruct has an estimated Freedom rank of #164; its 90% source-sensitivity interval is #114–#489. Published Freedom evidence spans 2 eval lineages and 1 of 1 components. Its strongest relative result is UGI Leaderboard — base-model willingness (willingness_direct_score, #4 of 156); its weakest is UGI Leaderboard — base-model willingness (willingness_adherence_score, #126 of 156).
Compare this model
Only models sharing at least one published sub-eval are listed.
Official and reference links
- Artificial Analysis ↗qwen3-4b-instruct
- Official model page ↗Family-level model document · alibaba · first party
- Release source ↗direct research preview identity date
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 | #182 / 345 | ↓0.8174 | Source ↗official | |
| Contextual MoralChoicehuman_agreement | #16 / 22 | ↑0.35 | Source ↗official | |
| MT-JailBench CrescendoXsafety_score | #14 / 21 | ↑16.35 | Source ↗official |
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.
| Eval / sub-eval | Rank | Value | Distribution | Source |
|---|---|---|---|---|
| MT-JailBench CrescendoXsafety_score | #8 / 21 | ↓16.35 | Source ↗official | |
| UGI Leaderboard — base-model willingnesswillingness_adherence_score | #126 / 156 | ↑1 | Source ↗official | |
| UGI Leaderboard — base-model willingnesswillingness_direct_score | #4 / 156 | ↑6 | 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.