# DeepSeek-R1-0528 Benchmark Scores & Performance

> DeepSeek-R1-0528 by DeepSeek has 10 source-displayable benchmark rows but no public overall score. It remains unranked.

Canonical page: https://benchlm.ai/models/deepseek-r1-0528

Last updated: October 14, 2026

## Model Details

| Property | Value |
|----------|-------|
| Creator | DeepSeek |
| Source Type | Open Weight |
| Reasoning Type | Reasoning |
| Context Window | 128K |
| Official model card | [DeepSeek-R1-0528 model card](https://huggingface.co/deepseek-ai/DeepSeek-R1-0528) |
| Overall Score | Not computed (unranked) |
| Overall Rank | Unranked |

## Family & Coverage

- Family: DeepSeek-R1
- Variant: snapshot (0528)
- Benchmarks covered: 10 of 628
- Sibling models: [DeepSeek-R1](/models/deepseek-r1)
- Related earlier model: [DeepSeek-R1](/models/deepseek-r1)
- Coverage note: Published evidence is shown below; no public overall score is assigned.

## Coding Benchmarks

| Benchmark | Score | Source |
|-----------|-------|--------|
| [LiveCodeBench](/benchmarks/livecodebench) | 73.3% | [DeepSeek: DeepSeek-R1-0528 model card](https://huggingface.co/deepseek-ai/DeepSeek-R1-0528) |
| [Codeforces](/benchmarks/codeforces) | 1930.0 | [DeepSeek: DeepSeek-R1-0528 model card](https://huggingface.co/deepseek-ai/DeepSeek-R1-0528) |
| [SWE-bench Verified](/benchmarks/swe-bench-verified) | 57.6% | [DeepSeek: DeepSeek-R1-0528 model card](https://huggingface.co/deepseek-ai/DeepSeek-R1-0528) |

## Knowledge Benchmarks

| Benchmark | Score | Source |
|-----------|-------|--------|
| [MMLU-Redux](/benchmarks/mmluredux) | 93.4% | [DeepSeek: DeepSeek-R1-0528 model card](https://huggingface.co/deepseek-ai/DeepSeek-R1-0528) |
| [MMLU-Pro](/benchmarks/mmlu-pro) | 85% | [DeepSeek: DeepSeek-R1-0528 model card](https://huggingface.co/deepseek-ai/DeepSeek-R1-0528) |
| [GPQA](/benchmarks/gpqa) | 81% | [DeepSeek: DeepSeek-R1-0528 model card](https://huggingface.co/deepseek-ai/DeepSeek-R1-0528) |
| [SimpleQA](/benchmarks/simpleqa) | 27.8% | [DeepSeek: DeepSeek-R1-0528 model card](https://huggingface.co/deepseek-ai/DeepSeek-R1-0528) |
| [HLE](/benchmarks/hle) | 17.7% | [DeepSeek: DeepSeek-R1-0528 model card](https://huggingface.co/deepseek-ai/DeepSeek-R1-0528) |

## Mathematics Benchmarks

| Benchmark | Score | Source |
|-----------|-------|--------|
| [AIME 2024](/benchmarks/aime2024) | 91.4% | [DeepSeek: DeepSeek-R1-0528 model card](https://huggingface.co/deepseek-ai/DeepSeek-R1-0528) |
| [AIME 2025](/benchmarks/aime2025) | 87.5% | [DeepSeek: DeepSeek-R1-0528 model card](https://huggingface.co/deepseek-ai/DeepSeek-R1-0528) |

## Other DeepSeek Models

- [DeepSeek V4.1 Flash](/models/deepseek-v4-1-flash) - Score: 64.59
- [DeepSeek V4 Pro 0813](/models/deepseek-v4-pro-0813) - Score: 62.89
- [DeepSeek V3.2](/models/deepseek-v3-2) - Score: 50.09
- [DeepSeek-R1](/models/deepseek-r1) - Score: 41.19
- [DeepSeek V3.1](/models/deepseek-v3-1) - Score: 40.59
- [DeepSeek V3.1 (Reasoning)](/models/deepseek-v3-1-reasoning) - Score: 38.87
- [DeepSeek V3 0324](/models/deepseek-v3-0324) - Score: 36.18
- [DeepSeek V3](/models/deepseek-v3) - Score: 31.78
- [DeepSeek R1 Distill Qwen 32B](/models/deepseek-r1-distill-qwen-32b) - Score: 30.68
- [DeepSeek V4 Flash 0731](/models/deepseek-v4-flash-0731) - Score: not computed
- [DeepSeek V3.2 (Thinking)](/models/deepseek-v3-2-thinking) - Score: not computed
- [DeepSeek LLM 2.0](/models/deepseek-llm-2-0) - Score: not computed
- [DeepSeek Coder 2.0](/models/deepseek-coder-2-0) - Score: not computed
- [DeepSeekMath V2](/models/deepseekmath-v2) - Score: not computed
- [DeepSeek-V2.5](/models/deepseek-v2-5) - Score: not computed