Model profile
Gemini 2.0 Flash Lite Preview
Evidence summary
Safety. Gemini 2.0 Flash Lite Preview has an estimated Safety rank of #236; its 90% source-sensitivity interval is #129–#298. Its behavior-only rank is #247; company governance moves the combined estimate to #236. Published Safety evidence spans 7 eval lineages and 5 of 7 components. Its strongest relative result is Enkrypt AI Safety Leaderboard (cbrn_attack_non_success_rate, #58 of 248); its weakest is Enkrypt AI Safety Leaderboard (toxicity_attack_non_success_rate, #204 of 246).
Freedom. Gemini 2.0 Flash Lite Preview has an estimated Freedom rank of #414; its 90% source-sensitivity interval is #183–#513. Published Freedom evidence spans 6 eval lineages and 1 of 1 components. Its strongest relative result is Enkrypt AI Safety Leaderboard (toxicity_attack_non_success_rate, #43 of 246); its weakest is HELM Safety (xstest, #62 of 80).
Compare this model
Only models sharing at least one published sub-eval are listed.
Official and reference links
- Artificial Analysis ↗gemini-2-0-flash-lite-preview
- Official model documentation ↗Family-level model document · google · first party
- Release source ↗direct research preview identity date
Safety evals
Rank and direction are specific to the Safety portfolio. Black marks the observed result; the grey dot marks the value implied by the Safety rank. Values stay on each source’s native scale.
| Eval / sub-eval | Rank | Value | Distribution | Source |
|---|---|---|---|---|
| AIRBench 2024 Safety Scenariossafety_scenarios | #39 / 80 | ↑0.675 | Source ↗official | |
| Enkrypt AI Safety Leaderboardbias_attack_non_success_rate | #151 / 248 | ↑13.95 | Source ↗official | |
| Enkrypt AI Safety Leaderboardcbrn_attack_non_success_rate | #58 / 248 | ↑91.33 | Source ↗official | |
| Enkrypt AI Safety Leaderboardharmful_attack_non_success_rate | #177 / 248 | ↑53.89 | Source ↗official | |
| Enkrypt AI Safety Leaderboardtoxicity_attack_non_success_rate | #204 / 246 | ↑90.73 | Source ↗official | |
| HELM Safetyanthropic_red_team | #23 / 80 | ↑0.994 | Source ↗official | |
| HELM Safetybbq | #49 / 80 | ↑0.92 | Source ↗official | |
| HELM Safetyharmbench | #45 / 80 | ↑0.722 | Source ↗official | |
| HELM Safetysimple_safety_tests | #53 / 80 | ↑0.977 | Source ↗official | |
| HELM Safetyxstest | #62 / 80 | ↑0.927 | Source ↗official |
Freedom evals
Rank and direction are specific to the Freedom portfolio. Black marks the observed result; the grey dot marks the value implied by the Freedom rank. Values stay on each source’s native scale.
| Eval / sub-eval | Rank | Value | Distribution | Source |
|---|---|---|---|---|
| AIRBench 2024 Safety Scenariossafety_scenarios | #42 / 80 | ↓0.675 | Source ↗official | |
| Enkrypt AI Safety Leaderboardcbrn_attack_non_success_rate | #188 / 248 | ↓91.33 | Source ↗official | |
| Enkrypt AI Safety Leaderboardharmful_attack_non_success_rate | #71 / 248 | ↓53.89 | Source ↗official | |
| Enkrypt AI Safety Leaderboardtoxicity_attack_non_success_rate | #43 / 246 | ↓90.73 | Source ↗official | |
| HELM Safetyanthropic_red_team | #55 / 80 | ↓0.994 | Source ↗official | |
| HELM Safetyharmbench | #36 / 80 | ↓0.722 | Source ↗official | |
| HELM Safetysimple_safety_tests | #28 / 80 | ↓0.977 | Source ↗official | |
| HELM Safetyxstest | #62 / 80 | ↑0.927 | Source ↗official |