Model

Gemini 3 Pro

CLOSED

Google · Gemini 3 family · released Nov 18, 2025

Google's frontier reasoning/agentic-coding flagship; sparse MoE, natively multimodal, 1M context; >200k-token prompts bill at $4/$18 per M.

ReasoningCodingVisionFunction callingTool useAgentic

2353.3

Elo · rank #28

Parameters

Undisclosed

Active params

Undisclosed

Context

1M tokens

Architecture

Sparse Mixture-of-Experts Transformer (natively multimodal)

License

Proprietary (Google API Terms)

Languages

—

API price (in/out)

$2 / $12

Modalities

text · vision · audio · video

Benchmark results

Bar shows position within the tracked field; marker = field best

AIMEMath95.0%#18

best: GPT-5.2 · 100.0%

ARC-AGI-2Reasoning31.1%#16

best: GPT-5.6 · 92.5%

Arena EloHuman preference1501#2

best: Claude Fable 5 · 1505

CharXivVision81.4%#7

best: Muse Spark 1.1 (xhigh) · 88.4%

FACTS GroundingKnowledge70.5%#9

best: Gemini 2.5 Flash-Lite (Thinking) · 86.8%

GPQA DiamondReasoning91.9%#17

best: GPT-5.6 · 94.6%

Humanity's Last ExamReasoning37.5%#29

best: Claude Sonnet 5 · 57.4%

LiveCodeBench ProCoding2439#2

best: Gemini 3.1 Pro · 2887

LiveCodeBenchCoding86.4%#19

best: DeepSeek-V4-Pro (Think Max) · 93.5%

MMMLUKnowledge91.8%#2

best: Gemini 3.1 Pro · 92.6%

MMMU-ProVision81.0%#7

best: Claude Opus 4.7 · 85.5%

SWE-bench VerifiedCoding76.2%#39

best: Claude Fable 5 · 95.0%

τ²-Bench AirlineAgents73.0%#3

best: Trinity-Large-Thinking · 88.0%

τ²-Bench RetailAgents85.3%#6

best: Claude Sonnet 4.6 · 91.7%

τ²-Bench TelecomAgents98.0%#8

best: Claude Opus 4.6 · 99.3%

Terminal-Bench 2.0Coding54.2%#42

best: GPT-5.6 · 88.8%

Run it locally

Closed weights — available via API only. No local deployment.

Input / M tok

Output / M tok

$12

Gemini 3 family

Elo progression across releases

Gemini 3 ProNov 20252353.3 Gemini 3 FlashDec 20252346.9

Resources

DOCSai.google.dev/gemini-api/docs/gemini-3 APIAvailable via Google API

API price $2/$12 · each benchmark row carries its own source badge (see methodology)