The Known Good Updated 8 Oct 2026 Subscribe
DeepSeek: R1 vs Google: Gemini 3.5 Flash ·DeepSeek vs Google

DeepSeek: R1 vs Google: Gemini 3.5 Flash — head-to-head comparison

DeepSeek: R1 profile Google: Gemini 3.5 Flash profile All comparisons
DeepSeek: R1 — DeepSeek
Quality
#22 of 65
75based on 4 of 7 evaluations
Known Good Index
Speed
#343 of 356
22.4
Output tokens per second
Price
#292 of 504
$1.15
Blended per 1M tokens
In $0.70 · Out $2.50
Cache hit price
unranked
—
per 1M tokens
Context
#517 of 550
64k
tokens (~98 pages)
Google: Gemini 3.5 Flash — Google
Quality
#2 of 65
95based on 3 of 7 evaluations
Known Good Index
Speed
#21 of 356
161.0
Output tokens per second
Price
#382 of 504
$3.38
Blended per 1M tokens
In $1.50 · Out $9.00
Cache hit price
#256 of 384
$0.15
per 1M tokens (−90%)
Context
#107 of 550
1.05M
tokens (~1,600 pages)
Summary

On the Known Good Index, DeepSeek: R1 scores 75 and Google: Gemini 3.5 Flash scores 95 — a 20-point lead for Google: Gemini 3.5 Flash. They share 2 published evaluations, with DeepSeek: R1 ahead on 0 and Google: Gemini 3.5 Flash ahead on 2.

Blended pricing is $1.15 per 1M tokens for DeepSeek: R1 and $3.38 for Google: Gemini 3.5 Flash — DeepSeek: R1 is about 2.9× cheaper.

Throughput is 22 tokens per second for DeepSeek: R1 and 161 for Google: Gemini 3.5 Flash, with time to first token at 1.2s and 1.9s. DeepSeek: R1 accepts 64k tokens of context against 1.05M.

DeepSeek: R1 is open weights under Open weights (unrestricted); Google: Gemini 3.5 Flash is proprietary. 4 tracked hosts serve one or both.

Generated from tracked data on 9 Oct 2026 · how these comparisons are computed →

At a glance
MetricDeepSeek: R1Google: Gemini 3.5 Flash
Known Good Index 75 based on 4 of 7 evaluations 95 based on 3 of 7 evaluations
Blended $/1M $1.15 $3.38
Output tok/s 22 161
Context window 64k 1.05M
Providers 2 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.

MetricDeepSeek: R1Google: Gemini 3.5 Flash
Known Good Index 75 95
Mathematics Index 74 —
Reasoning Index 77 —
Openness Index 60 5
The Known Good

Quality Breakdown

Every evaluation both models report a published score for

Evaluations both models report

Bar = DeepSeek: R1 · marker = Google: Gemini 3.5 Flash · scores ingested from Epoch AI (CC-BY 4.0)

GPQA Diamond69 / 93
Mock AIME 2024–2553 / 96

Right-hand figures read DeepSeek: R1 / Google: Gemini 3.5 Flash. DeepSeek: R1 leads on 0 of 2, Google: Gemini 3.5 Flash 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.

MetricDeepSeek: R1Google: Gemini 3.5 Flash
Text Arena 1,373 —
Text Arena (style controlled) 1,398 —
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: R1Google: Gemini 3.5 Flash
Input $/1M $0.70 $1.50
Output $/1M $2.50 $9.00
Blended $/1M $1.15 $3.38
Cache read $/1M — $0.150
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: R1Google: Gemini 3.5 Flash
Context window 64k 1.05M
Max output tokens 16k 66k
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.

MetricDeepSeek: R1Google: Gemini 3.5 Flash
Output tokens/s 22 161
Time to first token 1.2s 1.9s
The Known Good

Providers

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

4 hosts
Full provider benchmarks →
Provider DeepSeek: R1 blendedDeepSeek: R1 tok/s Google: Gemini 3.5 Flash blendedGoogle: Gemini 3.5 Flash tok/s
Novita $1.15 27 — —
Azure · first party $2.60 — — —
Google AI Studio — — $1.69 204
Google · first party — — $1.69 120

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 →