The Known Good Updated 25 Jul 2026
DeepSeek: R1 Distill Llama 70B vs Google: Gemini 3.5 Flash ·DeepSeek vs Google

DeepSeek: R1 Distill Llama 70B vs Google: Gemini 3.5 Flash — head-to-head comparison

DeepSeek: R1 Distill Llama 70B profile Google: Gemini 3.5 Flash profile All comparisons
DeepSeek: R1 Distill Llama 70B — DeepSeek
Quality
#41 of 61
52based on 3 of 6 evaluations
Known Good Index
Speed
#264 of 316
24.3
Output tokens per second
Price
#176 of 340
$0.80
Blended per 1M tokens
In $0.80 · Out $0.80
Cache hit price
unranked
—
per 1M tokens
Context
#338 of 345
8k
tokens (~13 pages)
Google: Gemini 3.5 Flash — Google
Quality
#3 of 61
95based on 3 of 6 evaluations
Known Good Index
Speed
#31 of 316
119.0
Output tokens per second
Price
#257 of 340
$3.38
Blended per 1M tokens
In $1.50 · Out $9.00
Cache hit price
#127 of 206
$0.15
per 1M tokens (−90%)
Context
#46 of 345
1.05M
tokens (~1,600 pages)
Summary

On the Known Good Index, DeepSeek: R1 Distill Llama 70B scores 52 and Google: Gemini 3.5 Flash scores 95 — a 43-point lead for Google: Gemini 3.5 Flash. They share 2 published evaluations, with DeepSeek: R1 Distill Llama 70B ahead on 0 and Google: Gemini 3.5 Flash ahead on 2.

Blended pricing is $0.80 per 1M tokens for DeepSeek: R1 Distill Llama 70B and $3.38 for Google: Gemini 3.5 Flash — DeepSeek: R1 Distill Llama 70B is about 4.2× cheaper.

Throughput is 24 tokens per second for DeepSeek: R1 Distill Llama 70B and 119 for Google: Gemini 3.5 Flash, with time to first token at 0.8s and 1.7s. DeepSeek: R1 Distill Llama 70B accepts 8k tokens of context against 1.05M.

DeepSeek: R1 Distill Llama 70B is open weights under Open weights (unrestricted); Google: Gemini 3.5 Flash is proprietary. 3 tracked hosts serve one or both.

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

At a glance
MetricDeepSeek: R1 Distill Llama 70BGoogle: Gemini 3.5 Flash
Known Good Index 52 based on 3 of 6 evaluations 95 based on 3 of 6 evaluations
Blended $/1M $0.80 $3.38
Output tok/s 24 119
Context window 8k 1.05M
Providers 1 2
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.

MetricDeepSeek: R1 Distill Llama 70BGoogle: Gemini 3.5 Flash
Known Good Index 52 95
Mathematics Index 71 96
Science Index 52 98
Reasoning Index 59 —
Agentic Index — 92
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 Distill Llama 70B · marker = Google: Gemini 3.5 Flash · scores ingested from Epoch AI (CC-BY 4.0)

GPQA Diamond56 / 93
MATH / AIME51 / 96

Right-hand figures read DeepSeek: R1 Distill Llama 70B / Google: Gemini 3.5 Flash. DeepSeek: R1 Distill Llama 70B 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.

Neither model currently appears in an arena we ingest.

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.

MetricDeepSeek: R1 Distill Llama 70BGoogle: Gemini 3.5 Flash
Input $/1M $0.80 $1.50
Output $/1M $0.80 $9.00
Blended $/1M $0.80 $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: R1 Distill Llama 70BGoogle: Gemini 3.5 Flash
Context window 8k 1.05M
Max output tokens 8k 66k
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: R1 Distill Llama 70BGoogle: Gemini 3.5 Flash
Output tokens/s 24 119
Time to first token 0.8s 1.7s
The Known Good

Providers

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

3 hosts
Full provider benchmarks →
Provider DeepSeek: R1 Distill Llama 70B blendedDeepSeek: R1 Distill Llama 70B tok/s Google: Gemini 3.5 Flash blendedGoogle: Gemini 3.5 Flash tok/s
Novita $0.80 19 — —
Google AI Studio — — $1.69 205
Google · first party — — $1.69 121

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) Full attribution →