DeepSeek R1 Distill Llama 70B

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

ProviderDeepSeek
Familyllama
Typellm-reasoning
Statusactive
Released2025-01-20

Reported benchmark scores

These scores carry one collection date for the whole card (2026-04) and a source list rather than a source per score, so they cannot be attributed individually. They are shown as reported and are not verified evidence. Benchmark pages carry the reviewed, dated evidence where it exists.
BenchmarkCatalogue standingScore
Arena Elo — Codingunassessed1370.0
Arena Elo — Mathunassessed1400.0
Arena Elo — Overall (Text)unassessed1360.0
Artificial Analysis Intelligence Indexunassessed84.0
Artificial Analysis Output Speedunassessed40.0
BIG-Bench Hardunassessed57.2
GPQA Diamondunassessed55.2
HumanEvalunassessed80.5
IFEvalunassessed78.0
LiveCodeBenchunassessed57.5
MATH-500unassessed88.5
MMLU: Astronomyunassessed76.5
MMLU: Biology (subcategory)unassessed84.2
MMLU: Business Ethicsunassessed77.8
MMLU: Chemistry (subcategory)unassessed78.5
MMLU: Clinical Knowledgeunassessed83.5
MMLU: Computer Science (subcategory)unassessed85.5
MMLU: Jurisprudenceunassessed74.5
MMLU: Physics (unresolved key)unassessed82.8
MMLU-Prounassessed68.3
MMLU: Professional Accountingunassessed68.2
MMLU: Professional Lawunassessed72.5
MuSRunassessed25.8

Data

This card as JSON · Edit on GitHub