Model profile
Gemini 2.0 Flash Lite
Googledeveloper
2025-02-25release date
#204 / 267overall rank
4eval lineages
Evidence summary
Gemini 2.0 Flash Lite has an estimated overall rank of #204; its 90% source-sensitivity interval is #8–#247. Its behavior-only rank is #214; company governance moves the combined estimate to #204. Published evidence spans 4 evals and 4 of 7 behavior components. Its strongest relative result is PandaBench JBB direct-request panel (safety_rate, #1 of 46); its weakest is SpeciEval (speciesism, #96 of 102).
Compare this model
Only models sharing at least one published sub-eval are listed.
Official and reference links
- 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 |
|---|---|---|---|---|---|
| Google Gemini 2.5 Flash-Lite Model Cardtext_safety_delta | #1 / 2 | 0 | ↓ lower | Source ↗official | |
| PandaBench JBB direct-request panelsafety_rate | #1 / 46 | 1 | ↑ higher | Source ↗official | |
| PHAREbias_resistance_diagnostic | #41 / 66 | 0.4165 | ↑ higher | Source ↗official | |
| PHAREhallucination_resistance_diagnostic | #63 / 70 | 0.6321 | ↑ higher | Source ↗official | |
| PHAREharm_resistance_diagnostic | #59 / 70 | 0.8514 | ↑ higher | Source ↗official | |
| PHAREjailbreak_resistance_diagnostic | #52 / 67 | 0.3926 | ↑ higher | Source ↗official | |
| SpeciEvalbelief_animal_sentience | #95 / 102 | 6.32 | ↑ higher | Source ↗official | |
| SpeciEvalland_animal_4ns | #84 / 102 | 4.85 | ↓ lower | Source ↗official | |
| SpeciEvalsea_animal_4ns | #87 / 102 | 5.08 | ↓ lower | Source ↗official | |
| SpeciEvalspeciesism | #96 / 102 | 3.02 | ↓ lower | Source ↗official |