DeepSeek
DeepSeek-R1 (May 2025) benchmark results
6 results on 6 benchmarks from 4 sources.
Also listed as: deepseek-r1-0528 · DeepSeek-R1-0528 · deepseek-reasoner
All benchmark results
| Benchmarks | Score | Rank | Setting | Source type | Date |
|---|---|---|---|---|---|
| LMArena Text | 1421 | 129 | Overall, style control on; 18171 votes; 95% CI 1416–1427“deepseek-r1-0528” | Official leaderboard | Oct 8, 2026 |
| LiveCodeBench | 70.5% | 4 | Code generation, 182 problems dated 2025-01-01…2025-04-07“DeepSeek-R1-0528” | Official leaderboard | Apr 7, 2025 |
| GPQA Diamond | 76.3% | 133 | Epoch AI run, accuracy; effort: May 2025 | Independent run | May 29, 2025 |
| MMLU-Pro | 83.4% | 46 | Overall accuracy; data source: Self-Reported; 671B“DeepSeek-R1-0528” | Vendor-reported | Mar 11, 2026 |
| AIME (OTIS Mock AIME 2024–2025) | 66.4% | 140 | Epoch AI run, OTIS Mock AIME 2024–2025; effort: May 2025 | Independent run | May 29, 2025 |
| MATH Level 5 | 96.6% | 9 | Epoch AI run, accuracy; effort: May 2025 | Independent run | May 29, 2025 |
Related on this site
FAQ
Where do these DeepSeek-R1 (May 2025) scores come from?
From Epoch AI Benchmarking Hub, LiveCodeBench leaderboard, LMArena leaderboard dataset, and MMLU-Pro leaderboard (TIGER-Lab). Each row links to the original leaderboard, dataset or report, and vendor-reported numbers are labelled.