Language Proprietary
- Params
- —
- Context
- —
- Released
- May 2025
Updated R1 model release (R1-0528)..
Full DeepSeek-R1-0528 specs →
🔌
New: connect Claude & other AIs to GenAIList over MCP — research the catalog and contribute to the shared knowledge base. Learn how →
// COMPARISON
DeepSeek-R1-0528
A head-to-head benchmark comparison of DeepSeek-R1-0528 across 19 evaluations.
The models
Benchmark comparison
| Benchmark | DeepSeek-R1-0528 |
|---|---|
| agentic | |
| Terminal-Bench 2.0 | 17.5% |
| code | |
| LiveCodeBench | 77% |
| LiveCodeBench v5 | 75.2% |
| LiveCodeBench v6 | 70.3% |
| SWE-bench Verified | 41.4% |
| SciCode | 40.3% |
| general | |
| IFEval | 87.8% |
| MMLU | 89.1% |
| MMLU-Pro | 85% |
| MMLU-Redux | 93.4% |
| MultiChallenge | 58.2% |
| math | |
| AIME 2024 | 89.3% |
| AIME 2025 | 87.5% |
| HMMT February 2025 | 79.4% |
| MATH-500 | 99.3% |
| reasoning | |
| GPQA Diamond | 81.3% |
| Humanity's Last Exam | 14.9% |
| safety | |
| SimpleQA | 27.8% |
| tool-use | |
| BFCL v3 | 64.7% |
Best result per row highlighted in cyan. Each benchmark links to its definition and sources; each model links to its full scorecard.
Frequently asked questions
Which of these models is best for coding? ▶
DeepSeek-R1-0528 has the strongest result on LiveCodeBench among the models compared here. See the code-category rows in the table for the full picture.
How many benchmarks are compared? ▶
This comparison covers 19 benchmarks on which at least one of the selected models has a published score.
Where do the benchmark scores come from? ▶
Scores are aggregated from official model cards, technical reports and standard public evaluations, and link back to each benchmark's source. They are updated as new results are published.
Explore further
Build a different comparison
Models (0 selected)
Benchmarks (auto)
Select at least two models.