The Known Good Updated 25 Jul 2026
Google: Gemma 3 27B vs Microsoft: Phi 4 ·Google vs Microsoft

Google: Gemma 3 27B vs Microsoft: Phi 4 — head-to-head comparison

Google: Gemma 3 27B profile Microsoft: Phi 4 profile All comparisons
Google: Gemma 3 27B — Google
Quality
#47 of 61
37based on 3 of 6 evaluations
Known Good Index
Speed
#262 of 316
24.4
Output tokens per second
Price
#64 of 340
$0.17
Blended per 1M tokens
In $0.08 · Out $0.45
Cache hit price
#62 of 206
$0.040
per 1M tokens (−50%)
Context
#171 of 345
262k
tokens (~400 pages)
Microsoft: Phi 4 — Microsoft
Quality
#50 of 61
33based on 3 of 6 evaluations
Known Good Index
Speed
#142 of 316
56.1
Output tokens per second
Price
#40 of 340
$0.09
Blended per 1M tokens
In $0.07 · Out $0.14
Cache hit price
unranked
—
per 1M tokens
Context
#334 of 345
16k
tokens (~25 pages)
Summary

On the Known Good Index, Google: Gemma 3 27B scores 37 and Microsoft: Phi 4 scores 33 — a 4-point lead for Google: Gemma 3 27B. They share 10 published evaluations, with Google: Gemma 3 27B ahead on 8 and Microsoft: Phi 4 ahead on 2.

Blended pricing is $0.17 per 1M tokens for Google: Gemma 3 27B and $0.09 for Microsoft: Phi 4 — Microsoft: Phi 4 is about 2.0× cheaper.

Throughput is 24 tokens per second for Google: Gemma 3 27B and 56 for Microsoft: Phi 4, with time to first token at 0.9s and 0.2s. Google: Gemma 3 27B accepts 262k tokens of context against 16k.

Google: Gemma 3 27B is open weights under Open weights (restricted use); Microsoft: Phi 4 is open weights under Open weights (unrestricted). 5 tracked hosts serve one or both, and 1 serve both.

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

At a glance
MetricGoogle: Gemma 3 27BMicrosoft: Phi 4
Known Good Index 37 based on 3 of 6 evaluations 33 based on 3 of 6 evaluations
Blended $/1M $0.17 $0.09
Output tok/s 24 56
Context window 262k 16k
Providers 5 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: Gemma 3 27BMicrosoft: Phi 4
Known Good Index 37 33
Mathematics Index 47 39
Science Index 44 53
Reasoning Index 40 47
Openness Index 60 60
The Known Good

Quality Breakdown

Every evaluation both models report a published score for

Evaluations both models report

Bar = Google: Gemma 3 27B · marker = Microsoft: Phi 4 · scores ingested from Epoch AI (CC-BY 4.0), LiveBench (Apache-2.0)

GPQA Diamond49 / 56
MATH / AIME20 / 14
LiveBench50 / 42
LiveBench Coding40 / 31
LiveBench Data Analysis51 / 45
LiveBench Instruction Following75 / 58
LiveBench Language35 / 26
LiveBench Mathematics55 / 42
LiveBench Reasoning44 / 48
MATH Level 574 / 65

Right-hand figures read Google: Gemma 3 27B / Microsoft: Phi 4. Google: Gemma 3 27B leads on 8 of 10, Microsoft: Phi 4 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: Gemma 3 27BMicrosoft: Phi 4
Text Arena — 1,217
Text Arena (style controlled) — 1,256
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: Gemma 3 27BMicrosoft: Phi 4
Input $/1M $0.08 $0.07
Output $/1M $0.45 $0.14
Blended $/1M $0.17 $0.09
Cache read $/1M $0.040 —
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 27BMicrosoft: Phi 4
Context window 262k 16k
Max output tokens 131k 16k
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: Gemma 3 27BMicrosoft: Phi 4
Output tokens/s 24 56
Time to first token 0.9s 0.2s
The Known Good

Providers

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

5 hosts · 1 serve both
Full provider benchmarks →
Provider Google: Gemma 3 27B blendedGoogle: Gemma 3 27B tok/s Microsoft: Phi 4 blendedMicrosoft: Phi 4 tok/s
Parasail $0.17 54 — —
Novita $0.14 32 — —
DeepInfra $0.10 22 $0.09 70
Phala $0.23 15 — —
Nebius $0.15 12 — —

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)Benchmarks — LiveBench (Apache-2.0)Elo — Arena Full attribution →