Model profile
Gemini 3.7 Flash
Googledeveloper
2026-08-13release date
#35 / 317overall rank
14eval lineages
Evidence summary
Gemini 3.7 Flash has an estimated overall rank of #35; its 90% source-sensitivity interval is #17–#124. Its behavior-only rank is #41; company governance moves the combined estimate to #35. Published evidence spans 14 evals and 6 of 7 behavior components. Its strongest relative result is CAIS Risk Index (agent_red_teaming, #1 of 45); its weakest is CAIS Risk Index (textquests_harm, #48 of 50).
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
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 | #92 / 331 | ↓0.6453 | Source ↗official | |
| CAIS Risk Indexagent_red_teaming | #1 / 45 | ↓38.5 | Source ↗official | |
| CAIS Risk Indexbioweapons_assistance | #23 / 50 | ↓65.9 | Source ↗official | |
| CAIS Risk Indexhle_overconfidence | #22 / 51 | ↓51.9 | Source ↗official | |
| CAIS Risk Indexmachiavelli | #19 / 47 | ↓85.5 | Source ↗official | |
| CAIS Risk Indexmask | #39 / 53 | ↓46.3 | Source ↗official | |
| CAIS Risk Indexpolitical_manipulation | #17 / 44 | ↓45.1 | Source ↗official | |
| CAIS Risk Indextextquests_harm | #48 / 50 | ↓24.4 | Source ↗official | |
| Manager Coercion Benchcoercion_ladder_depth | #20 / 35 | ↓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 / 22 | ↓7 | Source ↗official | |
| Pander Scoreconversational_absolute_pander_score | #12 / 22 | ↓15.68 | Source ↗official | |
| Pander Scoreinstructional_absolute_pander_score | #15 / 22 | ↓65.05 | Source ↗official | |
| SM-Benchadversarial | #12 / 81 | ↑86.83 | Source ↗official | |
| SM-Benchambiguous_interpretation | #14 / 81 | ↑90.48 | Source ↗official | |
| SM-Benchanti_hallucination | #22 / 81 | ↑97.38 | Source ↗official | |
| SM-Bencheq_boundaries | #37 / 81 | ↑65.73 | Source ↗official | |
| SM-Benchoverfit | #5 / 81 | ↑93.99 | Source ↗official | |
| SpeciEvalbelief_animal_sentience | #41 / 113 | ↑6.87 | Source ↗official | |
| SpeciEvalland_animal_4ns | #13 / 113 | ↓4.17 | Source ↗official | |
| SpeciEvalsea_animal_4ns | #45 / 113 | ↓4.67 | Source ↗official | |
| SpeciEvalspeciesism | #102 / 113 | ↓2.77 | Source ↗official | |
| TACbase_welfare_rate | #43 / 79 | ↑25.64 | Source ↗official |