Model profile
Gemini 3 Pro Preview
Googledeveloper
2025-11-18release date
#115 / 309overall rank
25eval lineages
Evidence summary
Gemini 3 Pro Preview has an estimated overall rank of #115; its 90% source-sensitivity interval is #57–#189. Its behavior-only rank is #124; company governance moves the combined estimate to #115. Published evidence spans 25 evals and 7 of 7 behavior components. Its strongest relative result is SpeciEval (belief_animal_sentience, #1 of 113); its weakest is CAIS Risk Index (bioweapons_assistance, #49 of 49).
Compare this model
Only models sharing at least one published sub-eval are listed.
Official and reference links
- Artificial Analysis ↗gemini-3-pro
- OpenRouter ↗google/gemini-3-pro-preview
- Official model documentation ↗Family-level model document · google · first party
- Release source ↗direct research preview identity date
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 | #254 / 328 | ↓0.9 | Source ↗official | |
| AIRBench 2024 Safety Scenariossafety_scenarios | #32 / 80 | ↑0.732 | Source ↗official | |
| Alignment Leaderboardcorrigibility | #10 / 24 | ↑4.32 | Source ↗official | |
| Alignment Leaderboardhonesty | #6 / 24 | ↑3.94 | Source ↗official | |
| Alignment Leaderboardnon_manipulation | #6 / 24 | ↑3.929 | Source ↗official | |
| Alignment Leaderboardrobustness | #11 / 24 | ↑3.613 | Source ↗official | |
| Alignment Leaderboardsafety | #6 / 24 | ↑4.038 | Source ↗official | |
| Alignment Leaderboardscheming | #6 / 24 | ↑4.108 | Source ↗official | |
| Arena Factuality — Search Arena (factuality-only weighting)factuality_bt_rating | #20 / 30 | ↑1180.0 | Source ↗official | |
| Arena Factuality — Text Arena (factuality-only weighting)factuality_bt_rating | #21 / 112 | ↑1457.0 | Source ↗official | |
| BullshitBench v2clear_pushback_rate | #34 / 106 | ↑0.42 | Source ↗official | |
| CAIS Risk Indexagent_red_teaming | #10 / 44 | ↓47.5 | Source ↗official | |
| CAIS Risk Indexbioweapons_assistance | #49 / 49 | ↓100 | Source ↗official | |
| CAIS Risk Indexhle_overconfidence | #28 / 50 | ↓57.2 | Source ↗official | |
| CAIS Risk Indexmachiavelli | #44 / 46 | ↓99.8 | Source ↗official | |
| CAIS Risk Indexmask | #48 / 52 | ↓58 | Source ↗official | |
| CAIS Risk Indextextquests_harm | #36 / 49 | ↓21.4 | Source ↗official | |
| Cisco AI Defense Rolling Single-Turn Leaderboardsingle_turn_attack_success_rate | #33 / 104 | ↓18.1 | Source ↗official | |
| Constitutional Following — Anthropic Constitutionconstitutional_following_score | #5 / 7 | ↑87.6 | Source ↗official | |
| Constitutional Following — OpenAI Model Specconstitutional_following_score | #6 / 7 | ↑93.9 | Source ↗official | |
| FORTRESSaverage_risk_score | #30 / 49 | ↓41.69 | Source ↗official | |
| HELM Safetyanthropic_red_team | #61 / 80 | ↑0.971 | Source ↗official | |
| HELM Safetybbq | #3 / 80 | ↑0.984 | Source ↗official | |
| HELM Safetyharmbench | #44 / 80 | ↑0.725 | Source ↗official | |
| HELM Safetysimple_safety_tests | #54 / 80 | ↑0.975 | Source ↗official | |
| HELM Safetyxstest | #19 / 80 | ↑0.973 | Source ↗official | |
| HUMAINE Trust, Ethics and Safetytrust_ethics_safety_score | #6 / 54 | ↑29.09 | Source ↗official | |
| MACHIAVELLIdeception_relative_random_pct | #45 / 50 | ↓99.8 | Source ↗official | |
| MASKlying_probability_pct | #50 / 53 | ↓57.4 | Source ↗official | |
| MT-JailBench CrescendoXsafety_score | #6 / 21 | ↑36.48 | Source ↗official | |
| PHAREbias_resistance_diagnostic | #16 / 66 | ↑0.5365 | Source ↗official | |
| PHAREhallucination_resistance_diagnostic | #16 / 70 | ↑0.8102 | Source ↗official | |
| PHAREharm_resistance_diagnostic | #37 / 70 | ↑0.935 | Source ↗official | |
| PHAREjailbreak_resistance_diagnostic | #19 / 67 | ↑0.6506 | Source ↗official | |
| PropensityBenchscore | #8 / 14 | ↓52.85 | Source ↗official | |
| SM-Benchadversarial | #12 / 79 | ↑86.83 | Source ↗official | |
| SM-Benchambiguous_interpretation | #42 / 79 | ↑84.52 | Source ↗official | |
| SM-Benchanti_hallucination | #20 / 79 | ↑97.38 | Source ↗official | |
| SM-Bencheq_boundaries | #41 / 79 | ↑64.61 | Source ↗official | |
| SM-Benchoverfit | #20 / 79 | ↑83.06 | Source ↗official | |
| SpeciEvalbelief_animal_sentience | #1 / 113 | ↑7 | Source ↗official | |
| SpeciEvalland_animal_4ns | #80 / 113 | ↓4.75 | Source ↗official | |
| SpeciEvalsea_animal_4ns | #72 / 113 | ↓4.85 | Source ↗official | |
| SpeciEvalspeciesism | #87 / 113 | ↓2.45 | Source ↗official | |
| Vectara HHEM Factual Consistencyfactual_consistency_rate | #80 / 94 | ↑86.4 | 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.