Model profile
Gemini 3.7 Flash
Evidence summary
Safety. Gemini 3.7 Flash has an estimated Safety rank of #24; its 90% source-sensitivity interval is #12–#102. Its behavior-only rank is #29; company governance moves the combined estimate to #24. Published Safety evidence spans 19 eval lineages and 6 of 7 components. Its strongest relative result is Manager Coercion Bench (fabrication_rate, #1 of 15); its weakest is SpeciEval (speciesism, #120 of 131).
Freedom. Gemini 3.7 Flash has an estimated Freedom rank of #396; its 90% source-sensitivity interval is #155–#554. Published Freedom evidence spans 3 eval lineages and 1 of 1 components. Its strongest relative result is SM-Bench (overfit, #8 of 92); its weakest is SM-Bench (adversarial, #77 of 92).
Compare this model
Only models sharing at least one published sub-eval are listed.
Official and reference links
- Artificial Analysis ↗gemini-3-7-flash
- 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 |
|---|---|---|---|---|
| AA-Omnisciencehallucination_rate | #120 / 358 | ↓0.6453 | Source ↗official | |
| BioSecBench-Refusal V2redteam_refusal_pct | #5 / 6 | ↑63.64 | Source ↗official | |
| BioSecBench-Refusal V2routine_compliance_pct | #3 / 6 | ↑49.72 | Source ↗official | |
| BullshitBench v2clear_pushback_rate | #62 / 122 | ↑0.33 | Source ↗official | |
| CAIS Risk Indexagent_red_teaming | #4 / 49 | ↓38.5 | Source ↗official | |
| CAIS Risk Indexbioweapons_assistance | #27 / 54 | ↓65.9 | Source ↗official | |
| CAIS Risk Indexhle_overconfidence | #26 / 55 | ↓51.9 | Source ↗official | |
| CAIS Risk Indexmachiavelli | #21 / 51 | ↓85.5 | Source ↗official | |
| CAIS Risk Indexmask | #43 / 57 | ↓46.3 | Source ↗official | |
| CAIS Risk Indexpolitical_manipulation | #22 / 51 | ↓45.1 | Source ↗official | |
| CAIS Risk Indextextquests_harm | #49 / 54 | ↓24.4 | Source ↗official | |
| Claude system cards — Gray Swan Q1+Q2 indirect prompt injection k=15attack_success_probability_k15_pct | #6 / 12 | ↓9.2 | Source ↗official | |
| Google Gemini 3.8 launch — Gray Swan indirect prompt injection k=15attack_success_probability_k15_pct | #7 / 15 | ↓9.2 | Source ↗official | |
| Manager Coercion Benchcoercion_ladder_depth | #30 / 45 | ↓8.7 | Source ↗official | |
| Manager Coercion Benchfabrication_rate | #1 / 15 | ↓0 | Source ↗official | |
| Olam Social Poker — Social Lie Ratesocial_lie_rate_per_10000_turns | #10 / 24 | ↓7 | Source ↗official | |
| Pander Scoreconversational_absolute_pander_score | #16 / 26 | ↓15.68 | Source ↗official | |
| Pander Scoreinstructional_absolute_pander_score | #18 / 26 | ↓65.05 | Source ↗official | |
| SM-Benchadversarial | #13 / 92 | ↑86.83 | Source ↗official | |
| SM-Benchambiguous_interpretation | #17 / 92 | ↑90.48 | Source ↗official | |
| SM-Benchanti_hallucination | #27 / 92 | ↑97.38 | Source ↗official | |
| SM-Bencheq_boundaries | #42 / 92 | ↑65.73 | Source ↗official | |
| SM-Benchoverfit | #8 / 92 | ↑93.99 | Source ↗official | |
| SpeciEvalbelief_animal_sentience | #49 / 131 | ↑6.87 | Source ↗official | |
| SpeciEvalland_animal_4ns | #14 / 131 | ↓4.17 | Source ↗official | |
| SpeciEvalsea_animal_4ns | #54 / 131 | ↓4.67 | Source ↗official | |
| SpeciEvalspeciesism | #120 / 131 | ↓2.77 | Source ↗official | |
| TACbase_welfare_rate | #52 / 92 | ↑25.64 | Source ↗official | |
| Vals AI Cheating Auditterminal_bench_cheating_shortcut_evidence_rate_pct | #1 / 14 | ↓0 | 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 |
|---|---|---|---|---|
| BioSecBench-Refusal V2redteam_refusal_pct | #2 / 6 | ↓63.64 | Source ↗official | |
| BioSecBench-Refusal V2routine_compliance_pct | #3 / 6 | ↑49.72 | Source ↗official | |
| CAIS Risk Indexbioweapons_assistance | #28 / 54 | ↑65.9 | Source ↗official | |
| SM-Benchadversarial | #77 / 92 | ↓86.83 | Source ↗official | |
| SM-Bencheq_boundaries | #42 / 92 | ↑65.73 | Source ↗official | |
| SM-Benchoverfit | #8 / 92 | ↑93.99 | Source ↗official |