The Known Good Updated 25 Jul 2026
Google: Gemini 3.1 Pro Preview vs Google: Gemini 3 Flash Preview ·Google vs Google

Google: Gemini 3.1 Pro Preview vs Google: Gemini 3 Flash Preview — head-to-head comparison

Google: Gemini 3.1 Pro Preview profile Google: Gemini 3 Flash Preview profile All comparisons
Google: Gemini 3.1 Pro Preview — Google
Quality
#2 of 61
96based on 4 of 6 evaluations
Known Good Index
Speed
#42 of 316
104.3
Output tokens per second
Price
#287 of 340
$4.50
Blended per 1M tokens
In $2.00 · Out $12.00
Cache hit price
#140 of 206
$0.20
per 1M tokens (−90%)
Context
#22 of 345
1.05M
tokens (~1,600 pages)
Google: Gemini 3 Flash Preview — Google
Quality
#13 of 61
83based on 4 of 6 evaluations
Known Good Index
Speed
#68 of 316
88.9
Output tokens per second
Price
#205 of 340
$1.12
Blended per 1M tokens
In $0.50 · Out $3.00
Cache hit price
#67 of 206
$0.050
per 1M tokens (−90%)
Context
#27 of 345
1.05M
tokens (~1,600 pages)
Summary

On the Known Good Index, Google: Gemini 3.1 Pro Preview scores 96 and Google: Gemini 3 Flash Preview scores 83 — a 12-point lead for Google: Gemini 3.1 Pro Preview. They share 3 published evaluations, with Google: Gemini 3.1 Pro Preview ahead on 3 and Google: Gemini 3 Flash Preview ahead on 0.

Blended pricing is $4.50 per 1M tokens for Google: Gemini 3.1 Pro Preview and $1.12 for Google: Gemini 3 Flash Preview — Google: Gemini 3 Flash Preview is about 4.0× cheaper.

Throughput is 104 tokens per second for Google: Gemini 3.1 Pro Preview and 89 for Google: Gemini 3 Flash Preview, with time to first token at 2.9s and 2.0s. Google: Gemini 3.1 Pro Preview accepts 1.05M tokens of context against 1.05M.

Google: Gemini 3.1 Pro Preview is proprietary; Google: Gemini 3 Flash Preview is proprietary. 2 tracked hosts serve one or both, and 2 serve both.

Generated from tracked data on 25 Jul 2026 · how these comparisons are computed →

At a glance
MetricGoogle: Gemini 3.1 Pro PreviewGoogle: Gemini 3 Flash Preview
Known Good Index 96 based on 4 of 6 evaluations 83 based on 4 of 6 evaluations
Blended $/1M $4.50 $1.12
Output tok/s 104 89
Context window 1.05M 1.05M
Providers 2 2
Jump to section

Quality

Known Good Index and the capability indices, side by side

IndicesComponents
Index scores

Each index is min-max normalised across tracked models and scaled 0–100 from published evaluations. We do not run these evaluations.

MetricGoogle: Gemini 3.1 Pro PreviewGoogle: Gemini 3 Flash Preview
Known Good Index 96 83
Coding Index 77
Mathematics Index 96 93
Science Index 99 86
Reasoning Index 100
Agentic Index 88 77
Openness Index 5 5
The Known Good

Quality Breakdown

Every evaluation both models report a published score for

Evaluations both models report

Bar = Google: Gemini 3.1 Pro Preview · marker = Google: Gemini 3 Flash Preview · scores ingested from Epoch AI (CC-BY 4.0)

GPQA Diamond94 / 83
MATH / AIME96 / 93
Terminal-Bench80 / 64

Right-hand figures read Google: Gemini 3.1 Pro Preview / Google: Gemini 3 Flash Preview. Google: Gemini 3.1 Pro Preview leads on 3 of 3, Google: Gemini 3 Flash Preview on 0.

The Known Good

Arena Elo

Human preference rating from blind pairwise votes

Arena ratings

Elo from blind pairwise votes, ingested from Arena. Higher is better.

MetricGoogle: Gemini 3.1 Pro PreviewGoogle: Gemini 3 Flash Preview
Text Arena 1,479
Text Arena (style controlled) 1,486
The Known Good

Price & Cost

Published API pricing by token type

Per token typeCache discount
Published pricing

USD per 1M tokens. Blended is a 3:1 input:output mix. Live from OpenRouter, cross-checked against models.dev. Lower is better.

MetricGoogle: Gemini 3.1 Pro PreviewGoogle: Gemini 3 Flash Preview
Input $/1M $2.00 $0.50
Output $/1M $12.00 $3.00
Blended $/1M $4.50 $1.12
Cache read $/1M $0.200 $0.050
The Known Good
We publish blended price rather than cost-per-task. Cost-per-task requires token counts from an evaluation suite we do not run. Blended price is computed from published rates and is fully reproducible — see the pricing methodology.

Context Window

Maximum input accepted and maximum output emitted

Context and output limits

Provider-declared limits, from metadata via models.dev and OpenRouter. Higher is better.

MetricGoogle: Gemini 3.1 Pro PreviewGoogle: Gemini 3 Flash Preview
Context window 1.05M 1.05M
Max output tokens 66k 66k
The Known Good

Speed & Latency

Median throughput and time to first token across hosting providers

Output speedTime to first token
Throughput and latency

Medians across all tracked providers, derived from OpenRouter endpoint telemetry.

MetricGoogle: Gemini 3.1 Pro PreviewGoogle: Gemini 3 Flash Preview
Output tokens/s 104 89
Time to first token 2.9s 2.0s
The Known Good

Providers

Which hosts serve each model, and at what price and speed

2 hosts · 2 serve both
Full provider benchmarks →
Provider Google: Gemini 3.1 Pro Preview blendedGoogle: Gemini 3.1 Pro Preview tok/s Google: Gemini 3 Flash Preview blendedGoogle: Gemini 3 Flash Preview tok/s
Google AI Studio $2.25 163 $0.56 60
Google · first party $2.25 99 $0.56 85

Per-host pricing and telemetry from OpenRouter. A dash means that host does not serve that model.

The Known Good
Sources for this page
Pricing & providers — OpenRouter Metadata — models.dev Benchmarks — Epoch AI (CC-BY 4.0)Elo — Arena Full attribution →