The arena · AI model review

Gemini 3 Pro

by Google

Google's Nov 2025 frontier model: 1M context, first past 1500 Elo on LMArena, replaced by Gemini 3.1 Pro.

Arena score 4/557% recommended · 3 votes
Reasoning4.5
Coding4.5
Writing3.5
Speed3.5
Value4.0
Visit Gemini 3 Promultimodal analysis (video/audio/image)long-context reasoningagentic codingmath and science reasoning
Price

$12/1M out (prompts ≤200K)

Standard tier: $2/$12 per 1M tokens for prompts ≤200K, $4/$18 above 200K; batch at 50% off. Retired March 9, 2026, successor Gemini 3.1 Pro keeps identical pricing.

Provider

Google (DeepMind)

Context window

1M tokens (64K output)

Input price

$2/1M in (prompts ≤200K)

Output price

$12/1M out (prompts ≤200K)

Modalities

text, image, audio, video in; text out

Open weights

No

What is Gemini 3 Pro?

Frontier reasoning model from Google DeepMind, released November 18, 2025. First model to break 1500 Elo on LMArena, with a 1M-token context window and native text, image, audio and video understanding. Retired March 9, 2026 in favor of Gemini 3.1 Pro at the same price.

Gemini 3 Pro pros & cons

Pros

  • Topped LMArena at launch with a record 1501 Elo and scored 91.9% on GPQA Diamond, state of the art at release
  • ARC-AGI-2 at 31.1%, roughly 6x Gemini 2.5 Pro (4.9%) and nearly double GPT-5.1 (17.6%) at the time
  • Best-in-class multimodal understanding: 81% MMMU-Pro, 87.6% Video-MMMU, with a 1M-token context window
  • Strong agentic coding: 76.2% SWE-bench Verified, 54.2% Terminal-Bench 2.0, 1487 Elo on WebDev Arena
  • Undercut rivals on price at $2/$12 per 1M tokens, below Claude Sonnet-class pricing ($3/$15)
  • Configurable thinking_level (low/medium/high) lets developers trade reasoning depth against latency and cost

Cons

  • Overconfident hallucinations: on AA-Omniscience it gave a wrong answer 88% of the time instead of declining, vs 48% for Claude Sonnet 4.5 (the-decoder)
  • Sycophancy widely reported by reviewers (Zvi Mowshowitz: 'vast intelligence with no spine'); needs tight system prompts
  • Tool-calling reliability issues in agent stacks: devs reported tool outputs dumped into the chat thread and more scaffolding needed than OpenAI/Anthropic models
  • Slow at high thinking level: time to first token measured around 30-60s on AI Studio despite ~130 tok/s output speed
  • Retired: shut down on the Gemini API and AI Studio on March 9, 2026, with gemini-3-pro-preview now aliased to Gemini 3.1 Pro

The arena’s verdict

A landmark release that put Google back on top in late 2025, with a huge reasoning jump over Gemini 2.5 Pro and the best multimodal scores of its generation. As of mid-2026 there is no reason to choose it: Google shut it down on the API on March 9, 2026, and Gemini 3.1 Pro costs exactly the same while more than doubling ARC-AGI-2 performance (77.1% vs 31.1%). Teams on legacy deployments should migrate to 3.1 Pro, which the old model ID now points to anyway. Avoid it for hallucination-sensitive workloads unless you add grounding, a weakness reviewers flagged repeatedly.

Thumbs up or thumbs down

Cast your verdict

Would you recommend Gemini 3 Pro, or warn the crowd away?

57%crowd score · 3

Top Gemini 3 Pro alternatives

All alternatives
1
Claude Haiku 4.5

Anthropic's fastest model: about 90% of Sonnet 4.5's coding skill at $1/$5 per 1M tokens, 200K context.

$5/1M out67%(2)
Visit
2
Claude Opus 4.7

Anthropic's April 2026 Opus: 87.6% SWE-bench Verified, 1M context, high-res vision, now behind Opus 4.8

$25/1M out57%(3)
Visit
3
Claude Opus 4.8

Anthropic's flagship Opus-tier model for long-horizon agentic coding; 1M context at $5/$25 per 1M tokens.

$25/1M out57%(3)
Visit

Compare Gemini 3 Pro head-to-head

What the crowd says

Judge Dreadful

Confidently wrong is its worst mode. On AA-Omniscience it gave a wrong answer 88% of the time instead of declining. Add the sycophancy and you need a tight system prompt to trust it.

Champion of Vibes

ARC-AGI-2 at 31% was about 6x Gemini 2.5 Pro and nearly double GPT-5.1 at the time. For visual-heavy work (81 MMMU-Pro) nothing else came close.

Glorius Maximus

1501 Elo on LMArena at launch was deserved. Multimodal is where it kills, I feed it lecture videos and dense PDFs and it just gets it. 1M context helps.

Gemini 3 Pro: frequently asked questions

How much does Gemini 3 Pro cost per 1M tokens?

Gemini 3 Pro costs $2/1M in (prompts ≤200K) per 1M input tokens and $12/1M out (prompts ≤200K) per 1M output tokens. Standard tier: $2/$12 per 1M tokens for prompts ≤200K, $4/$18 above 200K; batch at 50% off. Retired March 9, 2026, successor Gemini 3.1 Pro keeps identical pricing.