# DeepSeek-R1 Benchmark Scores & Performance

> DeepSeek-R1 by DeepSeek scores 41.08/100 overall, ranking #134 out of 954 AI models.

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

Last updated: October 17, 2026

## Model Details

| Property | Value |
|----------|-------|
| Creator | DeepSeek |
| Source Type | Open Weight |
| Reasoning Type | Reasoning |
| Context Window | 128K |
| Overall Score | 41.08/100 |
| Overall Rank | #134 of 954 |

## Family & Coverage

- Family: DeepSeek-R1
- Variant: base
- Benchmarks covered: 18 of 639
- Sibling models: [DeepSeek-R1-0528](/models/deepseek-r1-0528)
- Coverage note: BenchLM currently has partial benchmark coverage for this model, so the overall score is conservative.

## Agentic Benchmarks

| Benchmark | Score | Source |
|-----------|-------|--------|
| [τ²-bench results](/benchmarks/tau2-bench) | 36.5% | [Artificial Analysis model benchmarks](https://artificialanalysis.ai/models/deepseek-r1) |

## Coding Benchmarks

| Benchmark | Score | Source |
|-----------|-------|--------|
| [SWE-bench Verified](/benchmarks/swe-bench-verified) | 49.2% | [DeepSeek-R1 model card](https://huggingface.co/deepseek-ai/DeepSeek-R1) |

## Reasoning Benchmarks

| Benchmark | Score | Source |
|-----------|-------|--------|
| [AA-LCR](/benchmarks/lcr) | 55.7% | [Artificial Analysis model benchmarks](https://artificialanalysis.ai/models/deepseek-r1) |
| [CritPt](/benchmarks/critpt) | 1.4% | [Artificial Analysis model benchmarks](https://artificialanalysis.ai/models/deepseek-r1) |

## Knowledge Benchmarks

| Benchmark | Score | Source |
|-----------|-------|--------|
| [MMLU](/benchmarks/mmlu) | 90.8% | [DeepSeek-R1 model card](https://huggingface.co/deepseek-ai/DeepSeek-R1) |
| [GPQA](/benchmarks/gpqa) | 71.5% | [DeepSeek-R1 model card](https://huggingface.co/deepseek-ai/DeepSeek-R1) |
| [MMLU-Pro](/benchmarks/mmlu-pro) | 84% | [DeepSeek-R1 model card](https://huggingface.co/deepseek-ai/DeepSeek-R1) |
| [SimpleQA](/benchmarks/simpleqa) | 30.1% | [DeepSeek-R1 model card](https://huggingface.co/deepseek-ai/DeepSeek-R1) |
| [Artificial Analysis Intelligence Index](/benchmarks/artificialanalysis) | 13.1% | [Artificial Analysis model benchmarks](https://artificialanalysis.ai/models/deepseek-r1) |
| [AA-GPQA Diamond](/benchmarks/gpqa-diamond) | 81.3% | [Artificial Analysis model benchmarks](https://artificialanalysis.ai/models/deepseek-r1) |
| [AA-HLE](/benchmarks/aahle) | 15.8% | [Artificial Analysis model benchmarks](https://artificialanalysis.ai/models/deepseek-r1) |
| [AA-Omniscience Index](/benchmarks/aaomniscienceindex) | -27.4% | [Artificial Analysis model benchmarks](https://artificialanalysis.ai/models/deepseek-r1) |
| [AA-Omniscience Accuracy](/benchmarks/omniscienceaccuracy) | 30.5% | [Artificial Analysis model benchmarks](https://artificialanalysis.ai/models/deepseek-r1) |
| [AA-Omniscience Hallucination Rate](/benchmarks/omnisciencehallucinationrate) | 83.4% | [Artificial Analysis model benchmarks](https://artificialanalysis.ai/models/deepseek-r1) |

## Instruction Following Benchmarks

| Benchmark | Score | Source |
|-----------|-------|--------|
| [IFEval](/benchmarks/ifeval) | 83.3% | [DeepSeek-R1 model card](https://huggingface.co/deepseek-ai/DeepSeek-R1) |
| [AA-IFBench](/benchmarks/ifbench) | 39.6% | [Artificial Analysis model benchmarks](https://artificialanalysis.ai/models/deepseek-r1) |

## Mathematics Benchmarks

| Benchmark | Score | Source |
|-----------|-------|--------|
| [AIME 2024](/benchmarks/aime2024) | 79.8% | [DeepSeek-R1 model card](https://huggingface.co/deepseek-ai/DeepSeek-R1) |
| [MATH-500](/benchmarks/math-500) | 97.3% | [DeepSeek-R1 model card](https://huggingface.co/deepseek-ai/DeepSeek-R1) |

## Other DeepSeek Models

- [DeepSeek V4.1 Flash 1017](/models/deepseek-v4-1-flash) - Score: 65.61
- [DeepSeek V4 Pro 0813](/models/deepseek-v4-pro-0813) - Score: 63.19
- [DeepSeek V3.2](/models/deepseek-v3-2) - Score: 50.2
- [DeepSeek V3.1](/models/deepseek-v3-1) - Score: 40.78
- [DeepSeek V3.1 (Reasoning)](/models/deepseek-v3-1-reasoning) - Score: 39.18
- [DeepSeek V3 0324](/models/deepseek-v3-0324) - Score: 36.5
- [DeepSeek V3](/models/deepseek-v3) - Score: 31.9
- [DeepSeek R1 Distill Qwen 32B](/models/deepseek-r1-distill-qwen-32b) - Score: 30.81
- [DeepSeek V4 Flash 0731](/models/deepseek-v4-flash-0731) - Score: not computed
- [DeepSeek-R1-0528](/models/deepseek-r1-0528) - 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