Gemini 3.1 Pro Preview

Google DeepMind · google/gemini-3-1-pro-preview

ProviderGoogle DeepMind
Familygemini-pro
Typellm-reasoning
Statuspreview
Released2026-02-19
Updated2026-02-19

Reported benchmark scores

These scores carry one collection date for the whole card (2026-04) and a source list rather than a source per score, so they cannot be attributed individually. They are shown as reported and are not verified evidence. Benchmark pages carry the reviewed, dated evidence where it exists.
BenchmarkCatalogue standingScore
GPQA Diamondunassessed94.3
Humanity's Last Examunassessed44.4
Humanity's Last Exam (with tools)unassessed51.4
LegalBenchunassessed87.4
MedQAunassessed96.4
SWE-bench Prounassessed54.2
SWE-bench Verifiedunassessed80.6
Terminal-Bench 2.0unassessed68.5
USAMO 2026unassessed74.4

Data

This card as JSON · Edit on GitHub