The Known Good Updated 25 Jul 2026
Google: Gemini 3.1 Pro Preview vs OpenAI: o3 ·Google vs OpenAI

Google: Gemini 3.1 Pro Preview vs OpenAI: o3 — head-to-head comparison

Google: Gemini 3.1 Pro Preview profile OpenAI: o3 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)
OpenAI: o3 — OpenAI
Quality
#28 of 61
67based on 4 of 6 evaluations
Known Good Index
Speed
#70 of 316
88.5
Output tokens per second
Price
#269 of 340
$3.50
Blended per 1M tokens
In $2.00 · Out $8.00
Cache hit price
#175 of 206
$0.50
per 1M tokens (−75%)
Context
#203 of 345
200k
tokens (~300 pages)
Summary

On the Known Good Index, Google: Gemini 3.1 Pro Preview scores 96 and OpenAI: o3 scores 67 — a 29-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 OpenAI: o3 ahead on 0.

Blended pricing is $4.50 per 1M tokens for Google: Gemini 3.1 Pro Preview and $3.50 for OpenAI: o3 — OpenAI: o3 is about 1.3× cheaper.

Throughput is 104 tokens per second for Google: Gemini 3.1 Pro Preview and 88 for OpenAI: o3, with time to first token at 2.9s and 2.7s. Google: Gemini 3.1 Pro Preview accepts 1.05M tokens of context against 200k.

Google: Gemini 3.1 Pro Preview is proprietary; OpenAI: o3 is proprietary. 3 tracked hosts serve one or both.

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

At a glance
MetricGoogle: Gemini 3.1 Pro PreviewOpenAI: o3
Known Good Index 96 based on 4 of 6 evaluations 67 based on 4 of 6 evaluations
Blended $/1M $4.50 $3.50
Output tok/s 104 88
Context window 1.05M 200k
Providers 2 1
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 PreviewOpenAI: o3
Known Good Index 96 67
Mathematics Index 96 92
Science Index 99 84
Reasoning Index 100 62
Agentic Index 88 60
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 = OpenAI: o3 · scores ingested from Epoch AI (CC-BY 4.0)

GPQA Diamond94 / 82
MATH / AIME96 / 84
Humanity's Last Exam46 / 20

Right-hand figures read Google: Gemini 3.1 Pro Preview / OpenAI: o3. Google: Gemini 3.1 Pro Preview leads on 3 of 3, OpenAI: o3 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 PreviewOpenAI: o3
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 PreviewOpenAI: o3
Input $/1M $2.00 $2.00
Output $/1M $12.00 $8.00
Blended $/1M $4.50 $3.50
Cache read $/1M $0.200 $0.500
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 PreviewOpenAI: o3
Context window 1.05M 200k
Max output tokens 66k 100k
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 PreviewOpenAI: o3
Output tokens/s 104 88
Time to first token 2.9s 2.7s
The Known Good

Providers

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

3 hosts
Full provider benchmarks →
Provider Google: Gemini 3.1 Pro Preview blendedGoogle: Gemini 3.1 Pro Preview tok/s OpenAI: o3 blendedOpenAI: o3 tok/s
Google AI Studio $2.25 163 — —
Google · first party $2.25 99 — —
OpenAI · first party — — $3.50 72

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 →