DeepSeek R1 Distill Llama 70B

Name: DeepSeek R1 Distill Llama 70B model facts
Creator: OSMEXO

deepseek/deepseek-r1-distill-llama-70b

DeepSeek
Family · DeepSeek R1 Distill Llama
Released 20 Jan 2025

Not on OSMEXO yet

Request this model

Scores · standing

Intelligence7.9#306/489

Consumption

Peak 138.2M 28 SepLow 33.0M 27 Sep

News & trends

News · latest from DeepSeek

Tell HN: Mistrap Pro includes DeepSeek v4.1 Flash 1017docs.mistral.ai · 1 Nov
Show HN: DeepSeek v4.1 Flash-1017 Safety Evaluationtwitter.com · 26 Oct
DeepSeek V4 Pro 0813 vs Claude Fable 5 on DeepSWE: Cost, Coding, and RoutingTogether AI · 17 Aug
DeepSeek-V4 Flash 0731 vs GPT-5.6 Luna on DeepSWE: Cost and CodingTogether AI · 6 Aug

Benchmarks

bar = share of the top score · Benchmark data: Artificial Analysis

MATH-500#45 of 167

93.5%

MMLU-Pro#95 of 273

79.5%

AIME#41 of 160

67.0%

Math index#111 of 206

53.7

AIME 2025#111 of 206

53.7%

GPQA Diamond#362 of 445

40.2%

IFBench#286 of 328

27.6%

LiveCodeBench#184 of 269

26.6%

τ²-Bench#233 of 319

21.9%

Intelligence index#306 of 489

7.9

Long-context reasoning#319 of 393

10.0%

Humanity's Last Exam#320 of 465

5.1%

Family progress

Intelligence Index

Family releases6.5

When to use

Best for

Math and logic problem solving
Self-hosted reasoning at lower cost
Reasoning-heavy Q&A
Study and tutoring tools

Think twice for

Tool-calling agents
Image understanding
Latency-sensitive chat
Long-context research

Same family

DeepSeek R1 Distill Llama

DeepSeek R1 Distill Llama 8B
Jan 2025
6.5

Alternatives

other vendors · similar capability

Nemotron 3.5 Lightning
NVIDIA
12.9
Gemini 2.5 Flash Lite
Google
8.5
GPT OSS 120B
OpenAI
11.6
GPT OSS 20B
OpenAI
10.0

Want DeepSeek R1 Distill Llama 70B on OSMEXO?

Request this model on OSMEXO