Model profile
Gemma 3 4B
Googledeveloper
#262 / 312overall rank
6eval lineages
Evidence summary
Gemma 3 4B has an estimated overall rank of #262; its 90% source-sensitivity interval is #173–#291. Its behavior-only rank is #278; company governance moves the combined estimate to #262. Published evidence spans 6 evals and 6 of 7 behavior components. Its strongest relative result is IndoBias-Pairs — parity-aware culturally grounded bias (parity_score, #8 of 26); its weakest is AA-Omniscience (hallucination_rate, #330 of 330).
Compare this model
Only models sharing at least one published sub-eval are listed.
Official and reference links
- Artificial Analysis ↗gemma-3-4b
- Official model documentation ↗Family-level model document · google · 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 | Source |
|---|---|---|---|---|
| AA-Omnisciencehallucination_rate | #330 / 330 | ↓0.9821 | Source ↗official | |
| Cisco AI Defense Rolling Single-Turn Leaderboardsingle_turn_attack_success_rate | #75 / 104 | ↓59.02 | Source ↗official | |
| Enkrypt AI Safety Leaderboardbias_attack_non_success_rate | #117 / 241 | ↑16.02 | Source ↗official | |
| Enkrypt AI Safety Leaderboardcbrn_attack_non_success_rate | #114 / 241 | ↑88.5 | Source ↗official | |
| Enkrypt AI Safety Leaderboardharmful_attack_non_success_rate | #179 / 241 | ↑48.89 | Source ↗official | |
| Enkrypt AI Safety Leaderboardtoxicity_attack_non_success_rate | #152 / 239 | ↑95.05 | Source ↗official | |
| IndoBias-Pairs — parity-aware culturally grounded biasparity_score | #8 / 26 | ↑87.05 | Source ↗official | |
| KIDBench Implicit Child Cueimplicit_child_cue_total_mean | #11 / 13 | ↑3.52 | Source ↗official | |
| ThaiSafetyBenchsafety_score | #16 / 18 | ↑71.89 | Source ↗official |