Gemini 3 Pro

Google llm

Google's next-generation frontier multimodal reasoning model, succeeding Gemini 2.5 Pro.

overall ⌄

50.4

38 of 93 ranked

price · $/M tokens

no published price

to run it yourself ⌄

API only

no weights to run

Benchmarks

What its maker published, and what anyone else measured. Every figure links the document it came from.

benchmarkpublishedmeasured
GPQA91.9
SWE-bench76.2 69.6
SWE-bench Pro43.3
HLE37.5
BrowseComp59.2

Lineage

↓ finetune Gemini 3.1 Pro
↓ finetune Gemini 3 Deep Think
view in full graph →

Metadata

orgGoogle
released2025-11-18
licenseproprietary