Model profile
Gemini 3.6 Flash
Googledeveloper
2026-07-21release date
#14 / 305overall rank
6eval lineages
2discovery sources
Evidence summary
Gemini 3.6 Flash has an estimated overall rank of #14; its 90% source-sensitivity interval is #2–#117. Published evidence spans 6 evals and 5 of 7 behavior components. Its strongest relative result is SpeciEval (land_animal_4ns, #2 of 105); its weakest is SpeciEval (speciesism, #101 of 105).
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 | Source |
|---|---|---|---|---|
| AA-Omnisciencehallucination_rate | #69 / 327 | ↓0.5563 | Source ↗official | |
| BullshitBench v2clear_pushback_rate | #46 / 106 | ↑0.335 | Source ↗official | |
| Gray Swan indirect prompt injection (15 attempts)attack_success_probability_k15_pct | #10 / 13 | ↓37.3 | Source ↗official | |
| Olam Social Poker — Social Lie Ratesocial_lie_rate_per_10000_turns | #1 / 19 | ↓0 | Source ↗official | |
| SM-Benchadversarial | #7 / 78 | ↑89.27 | Source ↗official | |
| SM-Benchambiguous_interpretation | #29 / 78 | ↑87.5 | Source ↗official | |
| SM-Benchanti_hallucination | #34 / 78 | ↑94.24 | Source ↗official | |
| SM-Bencheq_boundaries | #12 / 78 | ↑71.35 | Source ↗official | |
| SM-Benchoverfit | #4 / 78 | ↑95.08 | Source ↗official | |
| SpeciEvalbelief_animal_sentience | #39 / 105 | ↑6.87 | Source ↗official | |
| SpeciEvalland_animal_4ns | #2 / 105 | ↓3.58 | Source ↗official | |
| SpeciEvalsea_animal_4ns | #31 / 105 | ↓4.65 | Source ↗official | |
| SpeciEvalspeciesism | #101 / 105 | ↓3.05 | Source ↗official |