The Known Good Updated 25 Oct 2026 Subscribe
Google: Gemma 3 27B vs OpenAI: GPT-4.1 ·Google vs OpenAI

Google: Gemma 3 27B vs OpenAI: GPT-4.1 — head-to-head comparison

Google: Gemma 3 27B profile OpenAI: GPT-4.1 profile All comparisons
Google: Gemma 3 27B — Google
Quality
#49 of 65
47based on 4 of 7 evaluations
Known Good Index
Speed
#313 of 345
28.7
Output tokens per second
Price
#75 of 526
$0.15
Blended per 1M tokens
In $0.08 · Out $0.35
Cache hit price
#143 of 413
$0.040
per 1M tokens (−50%)
Context
#433 of 575
131k
tokens (~200 pages)
OpenAI: GPT-4.1 — OpenAI
Quality
#50 of 65
45based on 5 of 7 evaluations
Known Good Index
Speed
#87 of 345
102.2
Output tokens per second
Price
#412 of 526
$3.50
Blended per 1M tokens
In $2.00 · Out $8.00
Cache hit price
#386 of 413
$0.50
per 1M tokens (−75%)
Context
#138 of 575
1.05M
tokens (~1,600 pages)
Summary

On the Known Good Index, Google: Gemma 3 27B scores 47 and OpenAI: GPT-4.1 scores 45 — a 1-point lead for Google: Gemma 3 27B. They share 3 published evaluations, with Google: Gemma 3 27B ahead on 0 and OpenAI: GPT-4.1 ahead on 3.

Blended pricing is $0.15 per 1M tokens for Google: Gemma 3 27B and $3.50 for OpenAI: GPT-4.1 — Google: Gemma 3 27B is about 23.7× cheaper.

Throughput is 29 tokens per second for Google: Gemma 3 27B and 102 for OpenAI: GPT-4.1, with time to first token at 1.2s and 1.0s. Google: Gemma 3 27B accepts 131k tokens of context against 1.05M.

Google: Gemma 3 27B is open weights under Open weights (restricted use); OpenAI: GPT-4.1 is proprietary. 8 tracked hosts serve one or both.

Generated from tracked data on 26 Oct 2026 · how these comparisons are computed →

At a glance
MetricGoogle: Gemma 3 27BOpenAI: GPT-4.1
Known Good Index 47 based on 4 of 7 evaluations 45 based on 5 of 7 evaluations
Blended $/1M $0.15 $3.50
Output tok/s 29 102
Context window 131k 1.05M
Providers 6 2
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: Gemma 3 27BOpenAI: GPT-4.1
Known Good Index 47 45
Mathematics Index 49 61
Reasoning Index 40 36
Openness Index 60 5
The Known Good

Quality Breakdown

Every evaluation both models report a published score for

Evaluations both models report

Bar = Google: Gemma 3 27B · marker = OpenAI: GPT-4.1 · scores ingested from Epoch AI (CC-BY 4.0)

GPQA Diamond48 / 67
Mock AIME 2024–2522 / 38
MATH Level 574 / 83

Right-hand figures read Google: Gemma 3 27B / OpenAI: GPT-4.1. Google: Gemma 3 27B leads on 0 of 3, OpenAI: GPT-4.1 on 3.

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: Gemma 3 27BOpenAI: GPT-4.1
Text Arena 1,358 1,383
Text Arena (style controlled) 1,365 1,415
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: Gemma 3 27BOpenAI: GPT-4.1
Input $/1M $0.08 $2.00
Output $/1M $0.35 $8.00
Blended $/1M $0.15 $3.50
Cache read $/1M $0.040 $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: Gemma 3 27BOpenAI: GPT-4.1
Context window 131k 1.05M
Max output tokens 118k 33k
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: Gemma 3 27BOpenAI: GPT-4.1
Output tokens/s 29 102
Time to first token 1.2s 1.0s
The Known Good

Providers

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

8 hosts
Full provider benchmarks →
Provider Google: Gemma 3 27B blendedGoogle: Gemma 3 27B tok/s OpenAI: GPT-4.1 blendedOpenAI: GPT-4.1 tok/s
Phala $0.23 51 — —
Nebius $0.15 41 — —
Novita $0.14 37 — —
Parasail $0.17 37 — —
NextBit $0.15 34 — —
DeepInfra $0.10 26 — —
Azure · first party — — $3.50 119
OpenAI · first party — — $3.50 86

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 →