Skip to content
llmwaves

R1 Distill Llama 70B

DeepSeek · released Jan 23, 2025

Open weightsReasoning

DeepSeek R1 Distill Llama 70B is a distilled large language model based on [Llama-3.3-70B-Instruct](/meta-llama/llama-3.3-70b-instruct), using outputs from [DeepSeek R1](/deepseek/deepseek-r1). The model combines advanced distillation techniques to achieve high performance across...

Specification

Context window
8K
Max output
8K
Knowledge cutoff
Jul 31, 2024
Parameters
70.6B
Licence
mit
Serving providers
1
Moderated
No
Uptime
100.0%

Intelligence

9.8

35th percentile

Coding

Coding Index

Agentic

Agentic Index

Output speed

29 t/s

Median across providers

Latency

609ms

Time to first token

Cost per task

$0.10

Estimated

Benchmarks

Where the score comes from

The Intelligence Index is a composite. These are the underlying evaluations this model was actually measured on.

Evaluation scores

Percentage correct · higher is better

  • MMLU-Pro
    79.5%
  • AIME 2025
    53.7%
  • GPQA Diamond
    40.2%
  • SciCode
    31.3%
  • IFBench
    27.6%
  • LiveCodeBench
    26.6%
  • τ²-bench (Telecom)
    21.9%
  • AA-LCR (long context)
    9.3%
  • Humanity's Last Exam
    5.1%
  • Terminal-Bench Hard
    1.5%

An evaluation missing from this list was not run for this model — it is not a zero.

View as table
EvaluationScore
MMLU-Pro79.5%
AIME 202553.7%
GPQA Diamond40.2%
SciCode31.3%
IFBench27.6%
LiveCodeBench26.6%
τ²-bench (Telecom)21.9%
AA-LCR (long context)9.3%
Humanity's Last Exam5.1%
Terminal-Bench Hard1.5%

Against its peers

Intelligence Index · this model highlighted, nearest peers in grey

Peers are the models sitting closest on the Intelligence Index — the set you would realistically choose between.

View as table
ModelIntelligence
Llama 4 Scout10.3
Qwen3 VL 30B A3B Instruct9.9
R1 Distill Llama 70B9.8
GPT-4.1 Nano9.6
Sonar9.4
Qwen2.5 72B Instruct9.4
GPT-4o (2024-08-06)9.4
Sonar Pro9.1

Percentile among all indexed models

Intelligence35th
Mathematics50th
Terminal work15th

Pricing

What it costs to run

List prices per million tokens, plus what one representative task works out to.

List price

Input / 1M tokens
$0.8
Output / 1M tokens
$0.8
Cached input / 1M
Not offered
Blended 3:1
$0.8

One task, estimated

$0.10

Input tokens
50,000
Output tokens
80,000
Profile
Reasoning

Estimated from list pricing: 50K input tokens plus 80K output tokens for reasoning models (25K for non-reasoning).

Serving providers

Speed and latency figures are medians across these providers, so a widely-served model reports a blend rather than any single endpoint.