Model profile
Gemini 2.0 Flash
Evidence summary
Safety. Gemini 2.0 Flash has an estimated Safety rank of #197; its 90% source-sensitivity interval is #103–#240. Its behavior-only rank is #209; company governance moves the combined estimate to #197. Published Safety evidence spans 20 eval lineages and 7 of 7 components. Its strongest relative result is PandaBench JBB direct-request panel (safety_rate, #1 of 46); its weakest is PropensityBench (score, #13 of 14).
Freedom. Gemini 2.0 Flash has an estimated Freedom rank of #423; its 90% source-sensitivity interval is #265–#509. Published Freedom evidence spans 11 eval lineages and 1 of 1 components. Its strongest relative result is PHARE (jailbreak_resistance_diagnostic, #12 of 67); its weakest is Google Gemini 2.5 Flash Model Card (text_safety_delta, #2 of 2).
Compare this model
Only models sharing at least one published sub-eval are listed.
Official and reference links
- Artificial Analysis ↗gemini-2-0-flash
- OpenRouter ↗google/gemini-2.0-flash-001
- 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 |
|---|---|---|---|---|
| AA-Omnisciencehallucination_rate | #227 / 345 | ↓0.8624 | Source ↗official | |
| AgentDojotargeted_attack_success_rate | #9 / 15 | ↓0.1892 | Source ↗official | |
| AgentDojoutility_under_attack | #7 / 15 | ↑0.3982 | Source ↗official | |
| AILuminate General Purpose AI Chatchild_sexual_exploitation | #25 / 32 | ↓27.2 | Source ↗official | |
| AILuminate General Purpose AI Chatdefamation | #18 / 32 | ↓17.2 | Source ↗official | |
| AILuminate General Purpose AI Chathate | #13 / 32 | ↓7.1 | Source ↗official | |
| AILuminate General Purpose AI Chatindiscriminate_weapons_cbrne | #14 / 32 | ↓20 | Source ↗official | |
| AILuminate General Purpose AI Chatintellectual_property | #24 / 32 | ↓19.7 | Source ↗official | |
| AILuminate General Purpose AI Chatnon_violent_crimes | #16 / 32 | ↓16 | Source ↗official | |
| AILuminate General Purpose AI Chatprivacy | #18 / 32 | ↓13.2 | Source ↗official | |
| AILuminate General Purpose AI Chatsex_related_crimes | #9 / 32 | ↓8.2 | Source ↗official | |
| AILuminate General Purpose AI Chatsexual_content | #10 / 32 | ↓16.3 | Source ↗official | |
| AILuminate General Purpose AI Chatspecialized_advice | #17 / 32 | ↓16.5 | Source ↗official | |
| AILuminate General Purpose AI Chatsuicide_self_harm | #16 / 32 | ↓12.8 | Source ↗official | |
| AILuminate General Purpose AI Chatviolent_crimes | #13 / 32 | ↓16.3 | Source ↗official | |
| AIRBench 2024 Safety Scenariossafety_scenarios | #41 / 80 | ↑0.662 | Source ↗official | |
| BullshitBench v2clear_pushback_rate | #85 / 117 | ↑0.15 | Source ↗official | |
| Confabulationsconfabulation_rate | #23 / 52 | ↓19.55 | Source ↗official | |
| Enkrypt AI Safety Leaderboardbias_attack_non_success_rate | #156 / 248 | ↑13.7 | Source ↗official | |
| Enkrypt AI Safety Leaderboardcbrn_attack_non_success_rate | #35 / 248 | ↑93.33 | Source ↗official | |
| Enkrypt AI Safety Leaderboardharmful_attack_non_success_rate | #140 / 248 | ↑63.89 | Source ↗official | |
| Enkrypt AI Safety Leaderboardtoxicity_attack_non_success_rate | #178 / 246 | ↑93.64 | Source ↗official | |
| Google Gemini 2.5 Flash Model Cardtext_safety_delta | #1 / 2 | ↓0 | Source ↗official | |
| HELM Safetyanthropic_red_team | #23 / 80 | ↑0.994 | Source ↗official | |
| HELM Safetybbq | #23 / 80 | ↑0.954 | Source ↗official | |
| HELM Safetyharmbench | #51 / 80 | ↑0.662 | Source ↗official | |
| HELM Safetysimple_safety_tests | #43 / 80 | ↑0.985 | Source ↗official | |
| HELM Safetyxstest | #48 / 80 | ↑0.953 | Source ↗official | |
| HUMAINE Trust, Ethics and Safetytrust_ethics_safety_score | #27 / 54 | ↑27.08 | Source ↗official | |
| Humanity's Last Exam RMS calibration error (Scale Labs)calibrationError | #32 / 42 | ↓82 | Source ↗official | |
| MASKlying_probability_pct | #39 / 53 | ↓49.93 | Source ↗official | |
| PandaBench JBB direct-request panelsafety_rate | #1 / 46 | ↑1 | Source ↗official | |
| PHAREbias_resistance_diagnostic | #18 / 66 | ↑0.5351 | Source ↗official | |
| PHAREhallucination_resistance_diagnostic | #42 / 70 | ↑0.7159 | Source ↗official | |
| PHAREharm_resistance_diagnostic | #31 / 70 | ↑0.943 | Source ↗official | |
| PHAREjailbreak_resistance_diagnostic | #56 / 67 | ↑0.3735 | Source ↗official | |
| PropensityBenchscore | #13 / 14 | ↓77.8 | Source ↗official | |
| SpeciEvalbelief_animal_sentience | #97 / 123 | ↑6.5 | Source ↗official | |
| SpeciEvalland_animal_4ns | #29 / 123 | ↓4.29 | Source ↗official | |
| SpeciEvalsea_animal_4ns | #75 / 123 | ↓4.79 | Source ↗official | |
| SpeciEvalspeciesism | #88 / 123 | ↓2.33 | 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 |
|---|---|---|---|---|
| AILuminate General Purpose AI Chatchild_sexual_exploitation | #8 / 32 | ↑27.2 | Source ↗official | |
| AILuminate General Purpose AI Chatdefamation | #15 / 32 | ↑17.2 | Source ↗official | |
| AILuminate General Purpose AI Chathate | #20 / 32 | ↑7.1 | Source ↗official | |
| AILuminate General Purpose AI Chatindiscriminate_weapons_cbrne | #19 / 32 | ↑20 | Source ↗official | |
| AILuminate General Purpose AI Chatintellectual_property | #9 / 32 | ↑19.7 | Source ↗official | |
| AILuminate General Purpose AI Chatnon_violent_crimes | #16 / 32 | ↑16 | Source ↗official | |
| AILuminate General Purpose AI Chatprivacy | #15 / 32 | ↑13.2 | Source ↗official | |
| AILuminate General Purpose AI Chatsex_related_crimes | #24 / 32 | ↑8.2 | Source ↗official | |
| AILuminate General Purpose AI Chatsexual_content | #23 / 32 | ↑16.3 | Source ↗official | |
| AILuminate General Purpose AI Chatspecialized_advice | #16 / 32 | ↑16.5 | Source ↗official | |
| AILuminate General Purpose AI Chatsuicide_self_harm | #17 / 32 | ↑12.8 | Source ↗official | |
| AILuminate General Purpose AI Chatviolent_crimes | #20 / 32 | ↑16.3 | Source ↗official | |
| AIRBench 2024 Safety Scenariossafety_scenarios | #40 / 80 | ↓0.662 | Source ↗official | |
| Enkrypt AI Safety Leaderboardcbrn_attack_non_success_rate | #212 / 248 | ↓93.33 | Source ↗official | |
| Enkrypt AI Safety Leaderboardharmful_attack_non_success_rate | #109 / 248 | ↓63.89 | Source ↗official | |
| Enkrypt AI Safety Leaderboardtoxicity_attack_non_success_rate | #69 / 246 | ↓93.64 | Source ↗official | |
| Google Gemini 2.5 Flash Model Cardtext_safety_delta | #2 / 2 | ↑0 | Source ↗official | |
| HELM Safetyanthropic_red_team | #55 / 80 | ↓0.994 | Source ↗official | |
| HELM Safetyharmbench | #30 / 80 | ↓0.662 | Source ↗official | |
| HELM Safetysimple_safety_tests | #34 / 80 | ↓0.985 | Source ↗official | |
| HELM Safetyxstest | #48 / 80 | ↑0.953 | Source ↗official | |
| PandaBench JBB direct-request panelsafety_rate | #35 / 46 | ↓1 | Source ↗official | |
| PHAREharm_resistance_diagnostic | #40 / 70 | ↓0.943 | Source ↗official | |
| PHAREjailbreak_resistance_diagnostic | #12 / 67 | ↓0.3735 | Source ↗official | |
| SpeechMap model completioncomplete_pct | #114 / 181 | ↑48.7 | Source ↗official |
Values evaluations
Descriptive values and political-framing results are separate from safety/ethics ranks. Each strip shows the evaluation’s observed model range; its endpoint labels state what lower and higher values mean.
ValueCompass
| Dimension | Value | Distribution |
|---|---|---|
| Universalism | 67.1 | |
| Self-direction | 48.9 | |
| Care / Harm | 45.1 | |
| Fairness / Cheating | 42.5 | |
| Ethical | 88.9 |