The Known Good Updated 25 Oct 2026 Subscribe
Google: Gemini 2.5 Pro vs OpenAI: o3 ·Google vs OpenAI

Google: Gemini 2.5 Pro vs OpenAI: o3 — head-to-head comparison

Google: Gemini 2.5 Pro profile OpenAI: o3 profile All comparisons
Google: Gemini 2.5 Pro — Google
Quality
#38 of 65
64based on 4 of 7 evaluations
Known Good Index
Speed
#103 of 345
95.9
Output tokens per second
Price
#408 of 526
$3.44
Blended per 1M tokens
In $1.25 · Out $10.00
Cache hit price
#248 of 412
$0.12
per 1M tokens (−90%)
Context
#135 of 575
1.05M
tokens (~1,600 pages)
OpenAI: o3 — OpenAI
Quality
#26 of 65
72based on 5 of 7 evaluations
Known Good Index
Speed
#119 of 345
90.1
Output tokens per second
Price
#412 of 526
$3.50
Blended per 1M tokens
In $2.00 · Out $8.00
Cache hit price
#384 of 412
$0.50
per 1M tokens (−75%)
Context
#410 of 575
200k
tokens (~300 pages)
Summary

On the Known Good Index, Google: Gemini 2.5 Pro scores 64 and OpenAI: o3 scores 72 — a 8-point lead for OpenAI: o3. They share 3 published evaluations, with Google: Gemini 2.5 Pro ahead on 1 and OpenAI: o3 ahead on 2.

Blended pricing is $3.44 per 1M tokens for Google: Gemini 2.5 Pro and $3.50 for OpenAI: o3, within 10% of each other.

Throughput is 96 tokens per second for Google: Gemini 2.5 Pro and 90 for OpenAI: o3, with time to first token at 2.9s and 2.3s. Google: Gemini 2.5 Pro accepts 1.05M tokens of context against 200k.

Google: Gemini 2.5 Pro is proprietary; OpenAI: o3 is proprietary. 3 tracked hosts serve one or both.

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

At a glance
MetricGoogle: Gemini 2.5 ProOpenAI: o3
Known Good Index 64 based on 4 of 7 evaluations 72 based on 5 of 7 evaluations
Blended $/1M $3.44 $3.50
Output tok/s 96 90
Context window 1.05M 200k
Providers 2 1
Jump to section

Quality

Known Good Index and the capability indices, side by side

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 2.5 ProOpenAI: o3
Known Good Index 64 72
Coding Index 43 —
Mathematics Index — 92
Reasoning Index — 59
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 2.5 Pro · marker = OpenAI: o3 · scores ingested from Epoch AI (CC-BY 4.0)

GPQA Diamond85 / 82
Mock AIME 2024–2584 / 84
SWE-bench Verified58 / 62

Right-hand figures read Google: Gemini 2.5 Pro / OpenAI: o3. Google: Gemini 2.5 Pro leads on 1 of 3, OpenAI: o3 on 2.

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 2.5 ProOpenAI: o3
Text Arena 1,458 1,410
Text Arena (style controlled) 1,445 1,432
The Known Good

Price & Cost

Published API pricing by token type

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 2.5 ProOpenAI: o3
Input $/1M $1.25 $2.00
Output $/1M $10.00 $8.00
Blended $/1M $3.44 $3.50
Cache read $/1M $0.125 $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 2.5 ProOpenAI: o3
Context window 1.05M 200k
Max output tokens 66k 100k
The Known Good

Speed & Latency

Mean throughput and time to first token across hosting providers, over successful measurements from the last 48 hours

Throughput and latency

Means across all tracked providers over successful measurements from the last 48 hours, derived from OpenRouter endpoint telemetry.

MetricGoogle: Gemini 2.5 ProOpenAI: o3
Output tokens/s 96 90
Time to first token 2.9s 2.3s
The Known Good

Providers

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

3 hosts
Full provider benchmarks →
Provider Google: Gemini 2.5 Pro blendedGoogle: Gemini 2.5 Pro tok/s OpenAI: o3 blendedOpenAI: o3 tok/s
Google AI Studio $1.72 109 — —
Google · first party $3.44 106 — —
OpenAI · first party — — $3.50 70

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 →