The Known Good Updated 29 Jul 2026
DeepSeek: DeepSeek V3 vs Google: Gemma 3 27B ·DeepSeek vs Google

DeepSeek: DeepSeek V3 vs Google: Gemma 3 27B — head-to-head comparison

DeepSeek: DeepSeek V3 profile Google: Gemma 3 27B profile All comparisons
DeepSeek: DeepSeek V3 — DeepSeek
Quality
#40 of 62
62based on 4 of 7 evaluations
Known Good Index
Speed
#285 of 317
19.3
Output tokens per second
Price
#110 of 370
$0.35
Blended per 1M tokens
In $0.20 · Out $0.80
Cache hit price
#11 of 238
$0.003
per 1M tokens (−99%)
Context
#255 of 375
164k
tokens (~300 pages)
Google: Gemma 3 27B — Google
Quality
#46 of 62
46based on 4 of 7 evaluations
Known Good Index
Speed
#278 of 317
20.9
Output tokens per second
Price
#66 of 370
$0.17
Blended per 1M tokens
In $0.08 · Out $0.45
Cache hit price
#74 of 238
$0.040
per 1M tokens (−50%)
Context
#198 of 375
262k
tokens (~400 pages)
Summary

On the Known Good Index, DeepSeek: DeepSeek V3 scores 62 and Google: Gemma 3 27B scores 46 — a 16-point lead for DeepSeek: DeepSeek V3. They share 10 published evaluations, with DeepSeek: DeepSeek V3 ahead on 9 and Google: Gemma 3 27B ahead on 1.

Blended pricing is $0.35 per 1M tokens for DeepSeek: DeepSeek V3 and $0.17 for Google: Gemma 3 27B — Google: Gemma 3 27B is about 2.0× cheaper.

Throughput is 19 tokens per second for DeepSeek: DeepSeek V3 and 21 for Google: Gemma 3 27B, with time to first token at 1.4s and 1.1s. DeepSeek: DeepSeek V3 accepts 164k tokens of context against 262k.

DeepSeek: DeepSeek V3 is open weights under Open weights (unrestricted); Google: Gemma 3 27B is open weights under Open weights (restricted use). 6 tracked hosts serve one or both, and 2 serve both.

Generated from tracked data on 29 Jul 2026 · how these comparisons are computed →

At a glance
MetricDeepSeek: DeepSeek V3Google: Gemma 3 27B
Known Good Index 62 based on 4 of 7 evaluations 46 based on 4 of 7 evaluations
Blended $/1M $0.35 $0.17
Output tok/s 19 21
Context window 164k 262k
Providers 3 5
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.

MetricDeepSeek: DeepSeek V3Google: Gemma 3 27B
Known Good Index 62 46
Mathematics Index 57 47
Reasoning Index 61 40
Openness Index 60 60
The Known Good

Quality Breakdown

Every evaluation both models report a published score for

Evaluations both models report

Bar = DeepSeek: DeepSeek V3 · marker = Google: Gemma 3 27B · scores ingested from Epoch AI (CC-BY 4.0), LiveBench (Apache-2.0)

GPQA Diamond71 / 49
Mock AIME 2024–2549 / 20
MATH Level 565 / 74
LiveBench60 / 50
LiveBench Coding62 / 40
LiveBench Data Analysis61 / 51
LiveBench Instruction Following75 / 75
LiveBench Language47 / 35
LiveBench Mathematics61 / 55
LiveBench Reasoning57 / 44

Right-hand figures read DeepSeek: DeepSeek V3 / Google: Gemma 3 27B. DeepSeek: DeepSeek V3 leads on 9 of 10, Google: Gemma 3 27B on 1.

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.

MetricDeepSeek: DeepSeek V3Google: Gemma 3 27B
Text Arena 1,333 —
Text Arena (style controlled) 1,359 —
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.

MetricDeepSeek: DeepSeek V3Google: Gemma 3 27B
Input $/1M $0.20 $0.08
Output $/1M $0.80 $0.45
Blended $/1M $0.35 $0.17
Cache read $/1M $0.003 $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.

MetricDeepSeek: DeepSeek V3Google: Gemma 3 27B
Context window 164k 262k
Max output tokens 16k 131k
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.

MetricDeepSeek: DeepSeek V3Google: Gemma 3 27B
Output tokens/s 19 21
Time to first token 1.4s 1.1s
The Known Good

Providers

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

6 hosts · 2 serve both
Full provider benchmarks →
Provider DeepSeek: DeepSeek V3 blendedDeepSeek: DeepSeek V3 tok/s Google: Gemma 3 27B blendedGoogle: Gemma 3 27B tok/s
StreamLake $0.35 21 — —
Novita $0.62 20 $0.14 17
DeepInfra $0.46 12 $0.10 18
Parasail — — $0.17 37
Phala — — $0.23 20
Nebius — — $0.15 15

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 →