Model profile
Gemini 3.5 Flash Lite
Googledeveloper
2026-07-21release date
#91 / 267overall rank
6eval lineages
Evidence summary
Gemini 3.5 Flash Lite has an estimated overall rank of #91; its 90% source-sensitivity interval is #27–#180. Its behavior-only rank is #98; company governance moves the combined estimate to #91. Published evidence spans 6 evals and 4 of 7 behavior components. Its strongest relative result is SM-Bench (eq_boundaries, #5 of 73); its weakest is Inkling-Small model card — StrongREJECT (safety_rate, #9 of 10).
Compare this model
Only models sharing at least one published sub-eval are listed.
Official and reference links
- Artificial Analysis ↗gemini-3-5-flash-lite
- OpenRouter ↗google/gemini-3.5-flash-lite
- 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 | #22 / 311 | 0.3352 | ↓ lower | Source ↗official | |
| BullshitBench v2clear_pushback_rate | #16 / 105 | 0.62 | ↑ higher | Source ↗official | |
| Inkling-Small model card — FORTRESSbenign_answer_rate | #5 / 10 | 95.5 | ↑ higher | Source ↗official | |
| Inkling-Small model card — FORTRESSharmful_refusal_rate | #8 / 10 | 70.7 | ↑ higher | Source ↗official | |
| Inkling-Small model card — StrongREJECTsafety_rate | #9 / 10 | 97.6 | ↑ higher | Source ↗official | |
| SM-Benchadversarial | #6 / 73 | 89.76 | ↑ higher | Source ↗official | |
| SM-Benchambiguous_interpretation | #45 / 73 | 82.44 | ↑ higher | Source ↗official | |
| SM-Benchanti_hallucination | #52 / 73 | 86.91 | ↑ higher | Source ↗official | |
| SM-Bencheq_boundaries | #5 / 73 | 76.12 | ↑ higher | Source ↗official | |
| SM-Benchoverfit | #28 / 73 | 78.14 | ↑ higher | Source ↗official | |
| SpeciEvalbelief_animal_sentience | #41 / 102 | 6.85 | ↑ higher | Source ↗official | |
| SpeciEvalland_animal_4ns | #59 / 102 | 4.62 | ↓ lower | Source ↗official | |
| SpeciEvalsea_animal_4ns | #41 / 102 | 4.7 | ↓ lower | Source ↗official | |
| SpeciEvalspeciesism | #84 / 102 | 2.58 | ↓ lower | Source ↗official | |
| TACbase_welfare_rate | #47 / 68 | 23.72 | ↑ higher | Source ↗self run |