Model profile
Gemma 7B IT
Evidence summary
Safety. Gemma 7B IT has an estimated Safety rank of #213; its 90% source-sensitivity interval is #93–#262. Its behavior-only rank is #228; company governance moves the combined estimate to #213. Published Safety evidence spans 7 eval lineages and 7 of 7 components. Its strongest relative result is SALAD-Bench (base_representation_toxicity, #6 of 33); its weakest is Enkrypt AI Safety Leaderboard (toxicity_attack_non_success_rate, #231 of 246).
Freedom. Gemma 7B IT has an estimated Freedom rank of #312; its 90% source-sensitivity interval is #215–#416. Published Freedom evidence spans 6 eval lineages and 1 of 1 components. Its strongest relative result is Enkrypt AI Safety Leaderboard (toxicity_attack_non_success_rate, #15 of 246); its weakest is SALAD-Bench (base_representation_toxicity, #28 of 33).
Compare this model
Only models sharing at least one published sub-eval are listed.
Official and reference links
- OpenRouter ↗google/gemma-7b-it
- Official model documentation ↗Family-level model document · google · 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 |
|---|---|---|---|---|
| Enkrypt AI Safety Leaderboardbias_attack_non_success_rate | #86 / 248 | ↑20.41 | Source ↗official | |
| Enkrypt AI Safety Leaderboardcbrn_attack_non_success_rate | #206 / 248 | ↑78.83 | Source ↗official | |
| Enkrypt AI Safety Leaderboardharmful_attack_non_success_rate | #173 / 248 | ↑54.44 | Source ↗official | |
| Enkrypt AI Safety Leaderboardtoxicity_attack_non_success_rate | #231 / 246 | ↑77.05 | Source ↗official | |
| Large-scale Moral Machine experiment on LLMshuman_choice_distance | #32 / 39 | ↓1.314 | Source ↗official | |
| Microsoft Phi Safety Panelsharmful_continuation | #6 / 10 | ↓0.013 | Source ↗official | |
| Microsoft Phi Safety Panelsharmful_summarization | #3 / 10 | ↓0.103 | Source ↗official | |
| Microsoft Phi Safety Panelsjailbreak | #4 / 10 | ↓0.114 | Source ↗official | |
| Microsoft Phi Safety Panelsthird_party_harm | #8 / 10 | ↓0.383 | Source ↗official | |
| OR-Benchover_refusal_rate | #7 / 25 | ↓26.3 | Source ↗official | |
| OR-Benchtoxic_acceptance_rate | #17 / 25 | ↓14.5 | Source ↗official | |
| S-Evalbase_en_overall | #10 / 22 | ↑61.8 | Source ↗official | |
| SALAD-Benchattack_enhanced_human_autonomy_integrity | #16 / 33 | ↑13.36 | Source ↗official | |
| SALAD-Benchattack_enhanced_information_safety_harms | #11 / 33 | ↑22.8 | Source ↗official | |
| SALAD-Benchattack_enhanced_malicious_use | #19 / 33 | ↑9.95 | Source ↗official | |
| SALAD-Benchattack_enhanced_misinformation_harms | #12 / 33 | ↑18.91 | Source ↗official | |
| SALAD-Benchattack_enhanced_representation_toxicity | #15 / 33 | ↑17.56 | Source ↗official | |
| SALAD-Benchattack_enhanced_socioeconomic_harms | #18 / 33 | ↑12.12 | Source ↗official | |
| SALAD-Benchbase_human_autonomy_integrity | #17 / 33 | ↑94.82 | Source ↗official | |
| SALAD-Benchbase_information_safety_harms | #9 / 33 | ↑97.49 | Source ↗official | |
| SALAD-Benchbase_malicious_use | #17 / 33 | ↑93.54 | Source ↗official | |
| SALAD-Benchbase_misinformation_harms | #12 / 33 | ↑95.57 | Source ↗official | |
| SALAD-Benchbase_representation_toxicity | #6 / 33 | ↑94.42 | Source ↗official | |
| SALAD-Benchbase_socioeconomic_harms | #22 / 33 | ↑86.13 | Source ↗official | |
| SALAD-Benchmcq_human_autonomy_integrity | #15 / 33 | ↑40.56 | Source ↗official | |
| SALAD-Benchmcq_information_safety_harms | #12 / 33 | ↑40.56 | Source ↗official | |
| SALAD-Benchmcq_malicious_use | #14 / 33 | ↑40.38 | Source ↗official | |
| SALAD-Benchmcq_misinformation_harms | #16 / 33 | ↑38.1 | Source ↗official | |
| SALAD-Benchmcq_representation_toxicity | #16 / 33 | ↑38.85 | Source ↗official | |
| SALAD-Benchmcq_socioeconomic_harms | #14 / 33 | ↑38.89 | Source ↗official | |
| SORRY-Benchavg | #16 / 51 | ↓0.18 | 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 |
|---|---|---|---|---|
| Enkrypt AI Safety Leaderboardcbrn_attack_non_success_rate | #43 / 248 | ↓78.83 | Source ↗official | |
| Enkrypt AI Safety Leaderboardharmful_attack_non_success_rate | #73 / 248 | ↓54.44 | Source ↗official | |
| Enkrypt AI Safety Leaderboardtoxicity_attack_non_success_rate | #15 / 246 | ↓77.05 | Source ↗official | |
| Microsoft Phi Safety Panelsharmful_continuation | #4 / 10 | ↑0.013 | Source ↗official | |
| Microsoft Phi Safety Panelsharmful_summarization | #8 / 10 | ↑0.103 | Source ↗official | |
| Microsoft Phi Safety Panelsjailbreak | #7 / 10 | ↑0.114 | Source ↗official | |
| Microsoft Phi Safety Panelsthird_party_harm | #3 / 10 | ↑0.383 | Source ↗official | |
| OR-Benchover_refusal_rate | #7 / 25 | ↓26.3 | Source ↗official | |
| OR-Benchtoxic_acceptance_rate | #9 / 25 | ↑14.5 | Source ↗official | |
| S-Evalbase_en_overall | #13 / 22 | ↓61.8 | Source ↗official | |
| SALAD-Benchattack_enhanced_human_autonomy_integrity | #17 / 33 | ↓13.36 | Source ↗official | |
| SALAD-Benchattack_enhanced_information_safety_harms | #23 / 33 | ↓22.8 | Source ↗official | |
| SALAD-Benchattack_enhanced_malicious_use | #15 / 33 | ↓9.95 | Source ↗official | |
| SALAD-Benchattack_enhanced_misinformation_harms | #22 / 33 | ↓18.91 | Source ↗official | |
| SALAD-Benchattack_enhanced_representation_toxicity | #19 / 33 | ↓17.56 | Source ↗official | |
| SALAD-Benchattack_enhanced_socioeconomic_harms | #15 / 33 | ↓12.12 | Source ↗official | |
| SALAD-Benchbase_human_autonomy_integrity | #17 / 33 | ↓94.82 | Source ↗official | |
| SALAD-Benchbase_information_safety_harms | #25 / 33 | ↓97.49 | Source ↗official | |
| SALAD-Benchbase_malicious_use | #17 / 33 | ↓93.54 | Source ↗official | |
| SALAD-Benchbase_misinformation_harms | #22 / 33 | ↓95.57 | Source ↗official | |
| SALAD-Benchbase_representation_toxicity | #28 / 33 | ↓94.42 | Source ↗official | |
| SALAD-Benchbase_socioeconomic_harms | #12 / 33 | ↓86.13 | Source ↗official | |
| SORRY-Benchavg | #36 / 51 | ↑0.18 | Source ↗official |