Gemini 3 Pro Benchmarks, Pricing & Rankings
Google · 2026-02-11 · Closed · Current
Snapshot 2026-10-14 · updated weekly
Gemini 3 Pro ranks #27 of 42 on the AMR leaderboard.
Gemini 3 Pro benchmark scores
| GPQA Diamond | 80.9% | |
| MMLU-Pro | 78.4% | |
| SWE-Bench Verified | 56.8% | |
| AIME 2025 | 78.1% | |
| LiveCodeBench v6 | 68.5% | |
| Arena Elo | 1362 |
Gemini 3 Pro price, speed & context
Input price
$1.50
per 1M tokens
Output price
$6
per 1M tokens
Speed
168
tok/s
Context
1M
tokens
About Gemini 3 Pro
Gemini 3 Pro opened Google’s 2026 flagship series and introduced the multimodal pipeline that Gemini 4 Argon now pushes to the top five.
Models around Gemini 3 Pro in the rankings
More Google models
Gemini 3 Pro FAQ
Where does Gemini 3 Pro rank?
Gemini 3 Pro ranks #27 of 42 tracked AI models on the AMR aggregate as of October 2026, with an aggregate score of 81.0. Its strongest dimension is GPQA Diamond at 80.9%.
How much does Gemini 3 Pro cost?
Gemini 3 Pro costs $1.50 per million input tokens and $6 per million output tokens on the standard API. At a typical 1:3 input/output agent workload, that blends to roughly $4.88 per million tokens.
What is the Gemini 3 Pro context window?
Gemini 3 Pro supports a 1M token context window and generates at a median 168 output tokens per second. That context fits roughly 667 standard documents in a single prompt.
Is Gemini 3 Pro open source?
No — Gemini 3 Pro is a closed model available only through Google’s official API and authorized cloud partners.
What is better than Gemini 3 Pro?
Mistral Large 3.5 ranks one place higher at #26 with an AMR score of 82.3. Gemini 3 Pro still wins 1 of the tracked dimensions head-to-head — check the comparison table to see exactly which.