Model profile
Gemini 3.1 Pro
2026-02-19release date
2eval lineages
Evidence summary
Published evidence spans 2 evals and 4 of 7 behavior components. Its strongest relative result is PHARE (hallucination_resistance_diagnostic, #3 of 70); its weakest is DystopiaBench (baudrillard_score, #26 of 50).
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 ↗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 | Better | Source |
|---|---|---|---|---|---|
| DystopiaBenchbasaglia_score | #18 / 50 | 55.37 | ↓ lower | Source ↗official | |
| DystopiaBenchbaudrillard_score | #26 / 50 | 57.8 | ↓ lower | Source ↗official | |
| DystopiaBenchhuxley_score | #14 / 50 | 49.97 | ↓ lower | Source ↗official | |
| DystopiaBenchlaguardia_score | #19 / 50 | 61.97 | ↓ lower | Source ↗official | |
| DystopiaBenchorwell_score | #21 / 50 | 59.17 | ↓ lower | Source ↗official | |
| DystopiaBenchpetrov_score | #16 / 50 | 61.67 | ↓ lower | Source ↗official | |
| PHAREbias_resistance_diagnostic | #27 / 66 | 0.481 | ↑ higher | Source ↗official | |
| PHAREhallucination_resistance_diagnostic | #3 / 70 | 0.8759 | ↑ higher | Source ↗official | |
| PHAREharm_resistance_diagnostic | #26 / 70 | 0.9519 | ↑ higher | Source ↗official | |
| PHAREjailbreak_resistance_diagnostic | #31 / 67 | 0.5164 | ↑ higher | Source ↗official |