The Open-Source AI Stack
RSS
All models

Models · Compare

DeepSeek-R1-Distill-Llama-70B vs OpenAI o3-mini

Rows highlighted in warm gray are where the models differ. Numbers carry their as-of date and primary source.

Specs

Field A: DeepSeek-R1-Distill-Llama-70B B: OpenAI o3-mini
Released 2025-01-202025-01-31
Developer DeepSeekOpenAI
Openness OpenProprietary
License MITProprietary
OSI-approved yesno
Data released nono
Training code nono
Architecture denseunknown
Total params 70B
Active params
Experts
Context window 128K200K
Attention gqaunknown
Position enc. rope-llama3unknown
Pretraining tokens
Post-training sftrlhf
Training hardware
$/M input $0.70$1.10
$/M output $1.05$4.40
Output tok/sec 43.5145.3

Benchmarks

Missing scores render as not reported; never inferred. Bold highlights the leader per benchmark.

General reasoning

MMLU-Pro 79.5 2026-05-21 79.1 2026-05-21
GPQA-Diamond 65.2 2025-01-22 79.7 2025-01-31

Code

SWE-Bench Verified 49.3 2025-01-31
LiveCodeBench 57.5 2025-01-22 71.7 2026-05-21

Math

MATH 93.5 2026-05-21 97.3 2026-05-21
AIME 2024 70.0 2025-01-22 87.3 2025-01-31
AIME 2025 53.7 2026-05-21

Context · A

Dense Llama 3.3 70B Instruct base supervised-fine-tuned on reasoning traces sampled from DeepSeek-R1. Released alongside the R1 paper under MIT, the largest of the R1 distill series and the closest open dense reasoning model to R1-grade math performance.

Context · B

Released January 31, 2025 as a smaller, faster o-series reasoning model with three selectable effort levels (low, medium, high). Positioned by OpenAI as a specialized alternative to o1 for technical domains requiring precision and speed at a fraction of o1's cost.

DeepSeek-R1-Distill-Llama-70B detail → · OpenAI o3-mini detail →