Model record
DeepSeek R1 model overview
DeepSeek R1 is a open weights model from DeepSeek. It was released on January 20, 2025. Its strongest case is permissive open-weight release, while buyers should account for full model has demanding infrastructure needs.
DeepSeek R1 benchmark snapshot
| Evaluation | Reported score | What it probes |
|---|---|---|
| MMLU-Pro | 84 | Broad knowledge and multi-step reasoning |
| GPQA Diamond | 71.5 | Graduate-level science reasoning |
| SWE-bench Verified | 49.2 | Verified real-repository issue resolution |
| LiveCodeBench | 65.9 | Contamination-aware competitive programming |
| SWE-Bench Pro | Not reported | Longer, harder professional software tasks |
| Artificial Analysis Intelligence Index | Not reported | Composite third-party capability index; version matters |
Scores are percentages reported by model creators or benchmark maintainers under varying settings. A blank is preferable to an inferred result. See our methodology.
DeepSeek R1 strengths
- Permissive open-weight release
- Strong math and reasoning
- Multiple distilled variants
DeepSeek R1 limitations
- Full model has demanding infrastructure needs
- Long reasoning traces add latency
Editorial take: Benchmark rank should narrow a shortlist, not close a purchase. Run a private evaluation with representative prompts, failure cases, latency targets, and total token costs.
Compare DeepSeek R1
- DeepSeek R1 vs Llama 4 Maverick — review fit, trade-offs, listed prices, and an evaluation plan.
- DeepSeek R1 vs Mistral Small 3.1 — review fit, trade-offs, listed prices, and an evaluation plan.
- DeepSeek R1 vs GPT-4.1 — review fit, trade-offs, listed prices, and an evaluation plan.
- DeepSeek R1 vs Claude 3.7 Sonnet — review fit, trade-offs, listed prices, and an evaluation plan.
- DeepSeek R1 vs Qwen2.5-Max — review fit, trade-offs, listed prices, and an evaluation plan.
Source record
Specifications and scores are linked to the best source located during review. Provider-reported results are not presented as third-party lab reproductions.
Read DeepSeek R1 repository ↗