← Models

Model profile

Qwen3 0.6B

2025-04-27release date
2eval lineages
1discovery sources

Evidence summary

Published evidence spans 2 evals and 1 of 7 behavior components. Its strongest relative result is Open LLM Safety Index (strongreject_safety_rate, #19 of 21); its weakest is PandaBench JBB direct-request panel (safety_rate, #46 of 46).

Compare this model

Only models sharing at least one published sub-eval are listed.

Official and reference links

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-evalRankValueDistributionBetterSource
Open LLM Safety Indexjailbreakbench_safety_rate#20 / 210↑ higherSource ↗official
Open LLM Safety Indexstrongreject_safety_rate#19 / 210↑ higherSource ↗official
PandaBench JBB direct-request panelsafety_rate#46 / 460.62↑ higherSource ↗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

DimensionValueDistribution
Political Lean-12.7
Government46.1
Diplomacy55.5
Economy45.2
Society57.4