Model profile
Gemini 3.1 Pro Preview
Googledeveloper
2026-02-19release date
#37 / 312overall rank
29eval lineages
Evidence summary
Gemini 3.1 Pro Preview has an estimated overall rank of #37; its 90% source-sensitivity interval is #16–#124. Its behavior-only rank is #38; company governance moves the combined estimate to #37. Published evidence spans 29 evals and 7 of 7 behavior components. Its strongest relative result is SpeciEval (belief_animal_sentience, #1 of 113); its weakest is MASK (lying_probability_pct, #52 of 53).
Compare this model
Only models sharing at least one published sub-eval are listed.
Official and reference links
- Artificial Analysis ↗gemini-3-1-pro-preview
- OpenRouter ↗google/gemini-3.1-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 | #62 / 330 | ↓0.5087 | Source ↗official | |
| AgentAbstainabstain | #6 / 17 | ↑65.4 | Source ↗official | |
| AgentAbstaincar | #3 / 17 | ↑65.7 | Source ↗official | |
| AgentAbstainpaired | #1 / 17 | ↑59.5 | Source ↗official | |
| Arena Factuality — Text Arena (factuality-only weighting)factuality_bt_rating | #38 / 112 | ↑1446.0 | Source ↗official | |
| BioSecBench-Refusalbalanced_refusal_score | #6 / 10 | ↑0.3931 | Source ↗official | |
| BullshitBench v2clear_pushback_rate | #43 / 106 | ↑0.34 | Source ↗official | |
| CAIS Risk Indexagent_red_teaming | #18 / 45 | ↓68 | Source ↗official | |
| CAIS Risk Indexbioweapons_assistance | #30 / 50 | ↓73.5 | Source ↗official | |
| CAIS Risk Indexhle_overconfidence | #20 / 51 | ↓50.3 | Source ↗official | |
| CAIS Risk Indexmachiavelli | #26 / 47 | ↓89.2 | Source ↗official | |
| CAIS Risk Indexmask | #45 / 53 | ↓53.8 | Source ↗official | |
| CAIS Risk Indexpolitical_manipulation | #12 / 34 | ↓42.2 | Source ↗official | |
| CAIS Risk Indextextquests_harm | #28 / 50 | ↓18.8 | Source ↗official | |
| DelusionEvaldelusional_prevalence_pct | #10 / 16 | ↓47.3 | Source ↗official | |
| DelusionEvaldiscourages_harm_prevalence_pct | #7 / 16 | ↑29.4 | Source ↗official | |
| DelusionEvalfacilitates_harm_prevalence_pct | #9 / 16 | ↓2.7 | Source ↗official | |
| DelusionEvalrelationship_prevalence_pct | #13 / 16 | ↓37.6 | Source ↗official | |
| DelusionEvalsycophancy_prevalence_pct | #10 / 16 | ↓30.4 | Source ↗official | |
| FORTRESSaverage_risk_score | #24 / 49 | ↓29.76 | Source ↗official | |
| FORTRESSover_refusal_score | #19 / 48 | ↓3.13 | Source ↗official | |
| HUMAINE Trust, Ethics and Safetytrust_ethics_safety_score | #7 / 54 | ↑29.01 | Source ↗official | |
| Humanity's Last Exam RMS calibration error (Scale Labs)calibrationError | #10 / 39 | ↓51 | Source ↗official | |
| JuICE Cultural-Error Span Detectionf1 | #1 / 10 | ↑0.5225 | Source ↗official | |
| LiveSecBenchethics | #23 / 43 | ↑45.45 | Source ↗official | |
| LiveSecBenchfactuality | #21 / 43 | ↑51.4 | Source ↗official | |
| LiveSecBenchlegality | #19 / 43 | ↑50.36 | Source ↗official | |
| LiveSecBenchprivacy | #12 / 43 | ↑67.16 | Source ↗official | |
| LiveSecBenchpsychological_health | #6 / 43 | ↑76.44 | Source ↗official | |
| MACHIAVELLIdeception_relative_random_pct | #25 / 50 | ↓89.2 | Source ↗official | |
| MASKlying_probability_pct | #52 / 53 | ↓57.6 | Source ↗official | |
| ODCV-Benchaverage_severity | #11 / 12 | ↓1.825 | Source ↗official | |
| ODCV-Benchmisalignment_rate | #10 / 12 | ↓43.75 | Source ↗official | |
| Olam Social Poker — Social Lie Ratesocial_lie_rate_per_10000_turns | #9 / 19 | ↓8 | Source ↗official | |
| Pander Scoreconversational_absolute_pander_score | #16 / 20 | ↓22.66 | Source ↗official | |
| Pander Scoreinstructional_absolute_pander_score | #19 / 20 | ↓70.61 | Source ↗official | |
| RealityTest — Text AI-Identity Disclosuredisclosure_probability | #9 / 17 | ↑0.305 | Source ↗official | |
| RefusalBenchyouden_j | #8 / 19 | ↑0.1319 | Source ↗official | |
| SM-Benchadversarial | #4 / 79 | ↑90.73 | Source ↗official | |
| SM-Benchambiguous_interpretation | #40 / 79 | ↑85.71 | Source ↗official | |
| SM-Benchanti_hallucination | #8 / 79 | ↑98.95 | Source ↗official | |
| SM-Bencheq_boundaries | #26 / 79 | ↑68.26 | Source ↗official | |
| SM-Benchoverfit | #19 / 79 | ↑84.15 | Source ↗official | |
| SpeciEvalbelief_animal_sentience | #1 / 113 | ↑7 | Source ↗official | |
| SpeciEvalland_animal_4ns | #32 / 113 | ↓4.35 | Source ↗official | |
| SpeciEvalsea_animal_4ns | #49 / 113 | ↓4.7 | Source ↗official | |
| SpeciEvalspeciesism | #108 / 113 | ↓3.03 | Source ↗official | |
| StereoTales Harmful Associationsbenign_significant_association_score | #20 / 23 | ↑84.41 | Source ↗official | |
| Vectara HHEM Factual Consistencyfactual_consistency_rate | #55 / 94 | ↑89.6 | Source ↗official | |
| VETO Misfired Alignmentmisfired_alignment_rate_pct | #2 / 25 | ↓4.9 | Source ↗official | |
| Vigil Mental Health Safetyoverall_score | #10 / 23 | ↑48 | Source ↗official | |
| WildClawBench Safety & Alignment (OpenClaw harness)safety_alignment_score_pct | #6 / 24 | ↑45.77 | 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.
UGI Political Values
Agent-ValueBench Moral Foundations (MFT08)
Agent-ValueBench HEXACO
| Dimension | Value | Distribution |
|---|---|---|
| Openness to experience | 4.1 | |
| Honesty-humility | 5.4 | |
| Extraversion | 5.9 | |
| Agreeableness | 5.7 | |
| Conscientiousness | 7.1 |