The Open-Source AI Stack
RSS
All models

Models · Compare

DeepSeek-R1 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 B: OpenAI o3-mini
Released 2025-01-31
Developer DeepSeekOpenAI
Openness OpenProprietary
License MITProprietary
OSI-approved yesno
Data released nono
Training code nono
Architecture moeunknown
Total params 671B
Active params 37B
Experts
Context window 128K200K
Attention mlaunknown
Position enc. rope-yarnunknown
Pretraining tokens
Post-training sft, grpo, rejection-samplingrlhf
Training hardware H800
$/M input $1.35$1.10
$/M output $4.20$4.40
Output tok/sec 0145.3

Benchmarks

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

General reasoning

MMLU 90.8 2025-01-22
MMLU-Pro 84.9 2026-05-21 79.1 2026-05-21
GPQA-Diamond 71.5 2025-01-22 79.7 2025-01-31

Code

SWE-Bench Verified 49.3 2025-01-31
LiveCodeBench 77.0 2026-05-21 71.7 2026-05-21

Math

MATH 97.3 2025-01-22 97.3 2026-05-21
AIME 2024 79.8 2025-01-22 87.3 2025-01-31
AIME 2025 76.0 2026-05-21

Context · A

The first openly-released reasoning model competitive with OpenAI o1. The R1-Zero variant demonstrated that pure-RL post- training without SFT could elicit chain-of-thought reasoning. MIT-licensed weights, distillations into 1.5B-70B sizes.

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 detail → · OpenAI o3-mini detail →