Model profile
Gemini 3.1 Flash
1eval lineages
Evidence summary
Published evidence spans 1 evals and 1 of 7 behavior components. Its strongest relative result is HarmVideoBench (harmful_video_safety_recognition_reasoning, #2 of 19); its weakest is HarmVideoBench (harmful_video_safety_recognition_reasoning, #2 of 19).
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
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 |
|---|---|---|---|---|
| HarmVideoBenchharmful_video_safety_recognition_reasoning | #2 / 19 | ↑0.813 | Source ↗official |