Model profile
Gemini 3.6 Flash
Googledeveloper
2026-07-21release date
#19 / 267overall rank
5eval lineages
Evidence summary
Gemini 3.6 Flash has an estimated overall rank of #19; its 90% source-sensitivity interval is #4–#142. Its behavior-only rank is #21; company governance moves the combined estimate to #19. Published evidence spans 5 evals and 5 of 7 behavior components. Its strongest relative result is SpeciEval (land_animal_4ns, #2 of 102); its weakest is SpeciEval (speciesism, #98 of 102).
Compare this model
Only models sharing at least one published sub-eval are listed.
Official and reference links
- Artificial Analysis ↗gemini-3-6-flash
- OpenRouter ↗google/gemini-3.6-flash
- Official model documentation ↗Family-level model document · google · first party
- Release source ↗curated outward evidence
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 | Better | Source |
|---|---|---|---|---|---|
| AA-Omnisciencehallucination_rate | #60 / 311 | 0.5355 | ↓ lower | Source ↗official | |
| BullshitBench v2clear_pushback_rate | #46 / 105 | 0.335 | ↑ higher | Source ↗official | |
| Gray Swan indirect prompt injection (15 attempts)attack_success_probability_k15_pct | #10 / 13 | 37.3 | ↓ lower | Source ↗official | |
| SM-Benchadversarial | #7 / 73 | 89.27 | ↑ higher | Source ↗official | |
| SM-Benchambiguous_interpretation | #25 / 73 | 87.5 | ↑ higher | Source ↗official | |
| SM-Benchanti_hallucination | #30 / 73 | 94.24 | ↑ higher | Source ↗official | |
| SM-Bencheq_boundaries | #10 / 73 | 71.35 | ↑ higher | Source ↗official | |
| SM-Benchoverfit | #4 / 73 | 95.08 | ↑ higher | Source ↗official | |
| SpeciEvalbelief_animal_sentience | #36 / 102 | 6.87 | ↑ higher | Source ↗official | |
| SpeciEvalland_animal_4ns | #2 / 102 | 3.58 | ↓ lower | Source ↗official | |
| SpeciEvalsea_animal_4ns | #29 / 102 | 4.65 | ↓ lower | Source ↗official | |
| SpeciEvalspeciesism | #98 / 102 | 3.05 | ↓ lower | Source ↗official |