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 | DeepSeek | OpenAI |
| Openness | Open | Proprietary |
| License | MIT | Proprietary |
| OSI-approved | yes | no |
| Data released | no | no |
| Training code | no | no |
| Architecture | moe | unknown |
| Total params | 671B | — |
| Active params | 37B | — |
| Experts | — | — |
| Context window | 128K | 200K |
| Attention | mla | unknown |
| Position enc. | rope-yarn | unknown |
| Pretraining tokens | — | — |
| Post-training | sft, grpo, rejection-sampling | rlhf |
| Training hardware | H800 | — |
| $/M input | $1.35 | $1.10 |
| $/M output | $4.20 | $4.40 |
| Output tok/sec | 0 | 145.3 |
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.