LLM Reference

Gemini 3 Pro

Released
2025-12-11
Last refreshed
2026-06-15
Status
Researched 182d ago
ProprietaryCommercial use: conditionalMultimodalCodingRAGAgentsLong contextVisionClassificationJSON / Tool use

Gemini 3 Pro is worth evaluating for coding, rag, and agents when its provider route and context window match the workload.

Use it for

  • Teams evaluating coding, rag, and agents
  • Workloads that can use a 1m context window
  • Buyers comparing 2 tracked provider routes

Do not use it for

  • Workloads where another current model has stronger sourced task evidence
Specifications
Family
Gemini 3
Released
2025-12-11
Context
1m
Architecture
Decoder Only
Knowledge cutoff
2025-01
Specialization
general
Openness
Proprietary
License
ProprietaryCommercial use: conditional
Training
Pretrained
Created by

Pioneering artificial intelligence research.

London, United Kingdom
Founded 2014
Website
Pricing
Output / 1M
$5.00
Input / 1M
$1.25

Cheapest of 2 routes · GCP Vertex AI

About

Google DeepMind's most advanced reasoning Gemini model. Part of the Gemini 3 series with frontier-class intelligence, multimodal understanding, and 1M token context window.

Gemini 3 Pro is a proprietary model in the Gemini 3 family. The structured metadata tracks a 1m-token context window, multimodal input, function calling, tool use, and code execution. This page tracks provider routes through Replicate API and GCP Vertex AI, with the cheapest tracked route listed at $1.25 input and $5 output per 1M tokens. Headline tracked benchmarks include SWE-bench Pro 42.5, Massive Multi-discipline Multimodal Understanding 81.0, and BFCL 72.5.

Top use-case fit: coding, agents, and build tasks

Coding

Q/$ D

2 relevant benchmarks in the decision map.

RAG

Included by capability and metadata signals in the decision map.

Agents

Q/$ C

1 relevant benchmark in the decision map.

Provider price ladder

Compare all 2

Compare API pricing across 2 providers for input and output tokens, batch, and cached reads when available.

ProviderInput / 1MOutput / 1MRoute
GCP Vertex AI$1.25$5.00
Serverless
Replicate API$2.00$12.00
Serverless

Available via routers & gateways(13)

Capabilities

VisionMultimodalFunction CallingTool UseCode Execution

Benchmark peer barsfor Coding

Benchmark scores(8)

Scores are benchmark-specific and are direction-aware: the same numeric gap can mean very different outcomes across suites. Use the leaderboard context and this model's provider route to decide whether the winning margin is meaningful for your workload.
BenchmarkScoreVersionSource
SWE-bench Pro42.5https://labs.scale.com/leaderboard/swe_bench_pro_public
Massive Multi-discipline Multimodal Understanding81.0https://mmmu-benchmark.github.io/
BFCL72.5v4https://gorilla.cs.berkeley.edu/leaderboard.html
MMLU PRO91.8https://deepmind.google/technologies/gemini/pro/
Chatbot Arena1486.0https://arena.ai/leaderboard
MMMU Pro81.0official Google DeepMind model card, Thinking High, no toolshttps://deepmind.google/models/model-cards/gemini-3-1-pro/
Google-Proof Q&A91.9https://deepmind.google/technologies/gemini/pro/
SWE-bench Verified76.2https://deepmind.google/technologies/gemini/pro/

Migration checks

Compare Gemini 3 Pro with other models

Frequently asked questions

What is the context window of Gemini 3 Pro?

Gemini 3 Pro has a context window of 1m tokens.

How much does Gemini 3 Pro cost?

Gemini 3 Pro pricing ranges from $1.25/1M to $2/1M input tokens depending on the provider.

When was Gemini 3 Pro released?

Gemini 3 Pro was released on 2025-12-11.

Which providers offer Gemini 3 Pro?

Gemini 3 Pro is available from 2 providers: Replicate API, GCP Vertex AI.

What benchmarks has Gemini 3 Pro been tested on?

Gemini 3 Pro has been evaluated on 8 benchmarks, including SWE-bench Pro, Massive Multi-discipline Multimodal Understanding, BFCL, MMLU PRO, Chatbot Arena.