The Known Good Updated 29 Jul 2026
DeepSeek: R1 vs DeepSeek: R1 Distill Llama 70B ·DeepSeek vs DeepSeek

DeepSeek: R1 vs DeepSeek: R1 Distill Llama 70B — head-to-head comparison

DeepSeek: R1 profile DeepSeek: R1 Distill Llama 70B profile All comparisons
DeepSeek: R1 — DeepSeek
Quality
#21 of 62
75based on 4 of 7 evaluations
Known Good Index
Speed
#154 of 317
49.1
Output tokens per second
Price
#222 of 370
$1.15
Blended per 1M tokens
In $0.70 · Out $2.50
Cache hit price
unranked
—
per 1M tokens
Context
#251 of 375
164k
tokens (~300 pages)
DeepSeek: R1 Distill Llama 70B — DeepSeek
Quality
#39 of 62
62based on 4 of 7 evaluations
Known Good Index
Speed
#268 of 317
25.3
Output tokens per second
Price
#187 of 370
$0.80
Blended per 1M tokens
In $0.80 · Out $0.80
Cache hit price
unranked
—
per 1M tokens
Context
#368 of 375
8k
tokens (~13 pages)
Summary

On the Known Good Index, DeepSeek: R1 scores 75 and DeepSeek: R1 Distill Llama 70B scores 62 — a 13-point lead for DeepSeek: R1. They share 10 published evaluations, with DeepSeek: R1 ahead on 10 and DeepSeek: R1 Distill Llama 70B ahead on 0.

Blended pricing is $1.15 per 1M tokens for DeepSeek: R1 and $0.80 for DeepSeek: R1 Distill Llama 70B — DeepSeek: R1 Distill Llama 70B is about 1.4× cheaper.

Throughput is 49 tokens per second for DeepSeek: R1 and 25 for DeepSeek: R1 Distill Llama 70B, with time to first token at 1.2s and 0.8s. DeepSeek: R1 accepts 164k tokens of context against 8k.

DeepSeek: R1 is open weights under Open weights (unrestricted); DeepSeek: R1 Distill Llama 70B is open weights under Open weights (unrestricted). 2 tracked hosts serve one or both, and 1 serve both.

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

At a glance
MetricDeepSeek: R1DeepSeek: R1 Distill Llama 70B
Known Good Index 75 based on 4 of 7 evaluations 62 based on 4 of 7 evaluations
Blended $/1M $1.15 $0.80
Output tok/s 49 25
Context window 164k 8k
Providers 2 1
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: R1DeepSeek: R1 Distill Llama 70B
Known Good Index 75 62
Mathematics Index 74 71
Reasoning Index 77 59
Openness Index 60 60
The Known Good

Quality Breakdown

Every evaluation both models report a published score for

Evaluations both models report

Bar = DeepSeek: R1 · marker = DeepSeek: R1 Distill Llama 70B · scores ingested from Epoch AI (CC-BY 4.0), LiveBench (Apache-2.0)

GPQA Diamond69 / 56
Mock AIME 2024–2553 / 51
MATH Level 593 / 90
LiveBench72 / 54
LiveBench Coding67 / 52
LiveBench Data Analysis70 / 56
LiveBench Instruction Following81 / 70
LiveBench Language49 / 24
LiveBench Mathematics81 / 58
LiveBench Reasoning83 / 68

Right-hand figures read DeepSeek: R1 / DeepSeek: R1 Distill Llama 70B. DeepSeek: R1 leads on 10 of 10, DeepSeek: R1 Distill Llama 70B on 0.

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: R1DeepSeek: R1 Distill Llama 70B
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: R1DeepSeek: R1 Distill Llama 70B
Input $/1M $0.70 $0.80
Output $/1M $2.50 $0.80
Blended $/1M $1.15 $0.80
Cache read $/1M — —
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: R1DeepSeek: R1 Distill Llama 70B
Context window 164k 8k
Max output tokens 16k 8k
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: R1DeepSeek: R1 Distill Llama 70B
Output tokens/s 49 25
Time to first token 1.2s 0.8s
The Known Good

Providers

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

2 hosts · 1 serve both
Full provider benchmarks →
Provider DeepSeek: R1 blendedDeepSeek: R1 tok/s DeepSeek: R1 Distill Llama 70B blendedDeepSeek: R1 Distill Llama 70B tok/s
Azure · first party $2.60 64 — —
Novita $1.15 32 $0.80 32

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 →