DEPLOY

Open-weight LLM comparison

DeepSeek R1 vs DeepSeek V3

Side-by-side

Straight from each model's release page and Hugging Face card. Memory shown is for the weights alone: add roughly 15% for real serving. Bold column marks the more parameters and the smaller memory footprint.

FieldDeepSeek R1DeepSeek V3
Total parameters671 B671 B
Active parameters (MoE)37 B37 B
ArchitectureMoE (671B total, 37B active per token)MoE (671B total, 37B active per token)
VendorDeepSeekDeepSeek
LicenseMITMIT
Released2025-01-202024-12-26
Weights @ FP161342 GB1342 GB
Weights @ INT8671 GB671 GB
Weights @ INT4336 GB336 GB

Which is smarter (published benchmarks)

Vendor-reported quality scores on the standard leaderboards. Bold column marks the higher score on the same test.

BenchmarkDeepSeek R1DeepSeek V3
MMLU (5-shot)90.888.5
MATH (AIME 2024, pass@1)79.8not published
GPQA (Diamond)71.5not published
Codeforces (Elo)2029.0not published
HumanEvalnot published82.6
MATH (0-shot)not published61.6
GPQAnot published59.1

Sources: DeepSeek R1 model card · DeepSeek V3 model card. Benchmark methodology and prompt template can shift these numbers by several points, so treat these as relative rankings, not absolute scores.

Common questions

DeepSeek R1 vs DeepSeek V3: which is newer?

DeepSeek R1 released 2025-01-20; DeepSeek V3 released 2024-12-26.

DeepSeek R1 vs DeepSeek V3: which license is more permissive?

DeepSeek R1: MIT. DeepSeek V3: MIT. Apache 2.0 and MIT allow unrestricted commercial use; Llama Community License allows commercial use but restricts training larger models on outputs; CC-BY-NC and vendor-specific licenses (Qwen 72B, Gemma) have narrower terms. Check the model card for the exact clauses.

See also: every LLM comparison · DeepSeek R1 full page · DeepSeek V3 full page.