Gemini 3.1 Pro Benchmarks, Pricing & Rankings
Google · 2026-04-21 · Closed · Current
Snapshot 2026-10-14 · updated weekly
Gemini 3.1 Pro ranks #28 of 42 on the AMR leaderboard.
Gemini 3.1 Pro benchmark scores
| GPQA Diamond | 79.8% | |
| MMLU-Pro | 77.6% | |
| SWE-Bench Verified | 55.4% | |
| AIME 2025 | 76.9% | |
| LiveCodeBench v6 | 67.3% | |
| Arena Elo | 1358 |
Gemini 3.1 Pro price, speed & context
Input price
$1.25
per 1M tokens
Output price
$5
per 1M tokens
Speed
172
tok/s
Context
1M
tokens
About Gemini 3.1 Pro
Gemini 3.1 Pro was the value king of the previous generation — $2.00 per million blended tokens — and is still the reference cheap 1M-context closed model.
Models around Gemini 3.1 Pro in the rankings
More Google models
Gemini 3.1 Pro FAQ
Where does Gemini 3.1 Pro rank?
Gemini 3.1 Pro ranks #28 of 42 tracked AI models on the AMR aggregate as of October 2026, with an aggregate score of 80.2. Its strongest dimension is GPQA Diamond at 79.8%.
How much does Gemini 3.1 Pro cost?
Gemini 3.1 Pro costs $1.25 per million input tokens and $5 per million output tokens on the standard API. At a typical 1:3 input/output agent workload, that blends to roughly $4.06 per million tokens.
What is the Gemini 3.1 Pro context window?
Gemini 3.1 Pro supports a 1M token context window and generates at a median 172 output tokens per second. That context fits roughly 667 standard documents in a single prompt.
Is Gemini 3.1 Pro open source?
No — Gemini 3.1 Pro is a closed model available only through Google’s official API and authorized cloud partners.
What is better than Gemini 3.1 Pro?
Gemini 3 Pro ranks one place higher at #27 with an AMR score of 81.0. Gemini 3.1 Pro still wins 0 of the tracked dimensions head-to-head — check the comparison table to see exactly which.