# Claude Sonnet 5 vs DeepSeek-R1

> Claude Sonnet 5 is the stronger model overall, scoring 54.6 to 42.3 on the Noometry Index. DeepSeek-R1 costs 4.4× less per token, which makes it the better buy when Claude Sonnet 5's lead doesn't matter for your workload.

- Canonical page: https://noometry.com/compare/claude-sonnet-5-vs-deepseek-r1
- Last updated: 2026-10-10
- Shared benchmarks: 27

## Summary

- They share 27 benchmarks with published results for both. Claude Sonnet 5 scores higher in 8 categories and DeepSeek-R1 in 1 category; 8 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Claude Sonnet 5 leads 49.1 to 18.6.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 94.7% for Claude Sonnet 5 and 66.4% for DeepSeek-R1.
- DeepSeek-R1 is cheaper at $0.50 / $2.15 per million input/output tokens, against $2 / $10 for Claude Sonnet 5.
- Claude Sonnet 5 accepts more context: 1M tokens versus 164K.

## Snapshot

| | Claude Sonnet 5 | DeepSeek-R1 |
|---|---|---|
| Provider | Anthropic | DeepSeek |
| Noometry Index | 54.6 | 42.3 |
| Rank | 29 | 115 |
| Context | 1M | 164K |
| Input $/M | $2 | $0.50 |
| Output $/M | $10 | $2.15 |
| Weights | Proprietary | Proprietary |

## Coding

- Claude Sonnet 5: 55.5 (#26)
- DeepSeek-R1: 46.3 (#68)

| Benchmark | Claude Sonnet 5 | DeepSeek-R1 |
|---|---|---|
| SciCode | 54.3% | 35.7% |
| WeirdML | 68.8% | 41.6% |
| LMArena Coding | 1483 | 1427 |
| ALE-Bench | 1,463 | 804.12 |
| DeepSWE | 53.8% | — |
| FrontierCode | 42.7% | — |
| Aider Polyglot | — | 71.4% |
| CursorBench | 34.1% | — |
| LMArena WebDev | 1541 | — |
| GSO | 37.3% | — |
| LiveBench Coding | — | 66.7% |
| AlgoTune | — | 1.7 |

## Agentic & Tool Use

- Claude Sonnet 5: 42.8 (#18)
- DeepSeek-R1: 30.7 (#75)

| Benchmark | Claude Sonnet 5 | DeepSeek-R1 |
|---|---|---|
| APEX-Agents | 54.5% | — |
| DeepResearch Bench | — | 35.1% |
| BALROG | — | 34.9% |
| GBAEval | 65.3% | — |
| LMArena Search | 1194 | — |
| METR Time Horizons | — | 53.8% |
| Vending-Bench 2 | 6,378 | — |

## Reasoning

- Claude Sonnet 5: 49.1 (#39)
- DeepSeek-R1: 18.6 (#278)

| Benchmark | Claude Sonnet 5 | DeepSeek-R1 |
|---|---|---|
| SimpleBench | 60.6% | 40.8% |
| CritPt | 16.9% | 1.1% |
| LMArena Hard Prompts | 1461 | 1416 |
| Epoch Capabilities Index | 156.21 | 141.29 |
| ForecastBench | 61.1 | 60 |
| ARC-AGI-2 | — | 1.3% |
| Kagi LLM Benchmark | — | 69.4% |
| NYT Connections (extended) | 75.1% | — |
| ARC-AGI-1 | — | 21.2% |
| Chess Puzzles | 35% | — |
| LiveBench Reasoning | — | 83.2% |
| Mystery Game Puzzles | 35% | — |
| DTBench | 92.5% | — |
| LiveBench Data Analysis | — | 69.8% |
| LMCA | 50% | — |
| Surface Evolver Bench | 60% | — |
| Bench to the Future 3 | 0.14 | — |
| LiveBench | — | 71.6% |

## Math

- Claude Sonnet 5: 66.2 (#27)
- DeepSeek-R1: 43.8 (#79)

| Benchmark | Claude Sonnet 5 | DeepSeek-R1 |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 94.7% | 66.4% |
| LMArena Math | 1467 | 1400 |
| FrontierMath (Tiers 1-3) | 65.6% | — |
| FrontierMath Tier 4 | 29.3% | — |
| ProofBench | 77% | — |
| Omni-MATH | — | 42.4% |
| LiveBench Math | — | 80.7% |
| MATH Level 5 | — | 96.6% |

## Knowledge

- Claude Sonnet 5: 55.6 (#47)
- DeepSeek-R1: 44.5 (#87)

| Benchmark | Claude Sonnet 5 | DeepSeek-R1 |
|---|---|---|
| GPQA Diamond | 90.5% | 76.3% |
| LMArena Expert | 1490 | 1394 |
| SimpleQA Verified | 33.7% | — |
| MMLU-Pro | — | 79.3% |
| Confabulations | — | 12.7% |
| Vectara Hallucination Rate | — | 11.3% |
| GPQA (HELM) | — | 66.6% |

## Multimodal

- Claude Sonnet 5: 42.4 (#31)
- DeepSeek-R1: —

| Benchmark | Claude Sonnet 5 | DeepSeek-R1 |
|---|---|---|
| LMArena Vision | 1274 | — |
| Blueprint-Bench 2 | 24.9% | — |
| LMArena Document | 1466 | — |

## Multilingual

- Claude Sonnet 5: 53.8 (#55)
- DeepSeek-R1: 52.4 (#85)

| Benchmark | Claude Sonnet 5 | DeepSeek-R1 |
|---|---|---|
| LMArena Non-English | 1431 | 1412 |
| LMArena Chinese | 1477 | 1442 |
| LMArena French | 1460 | 1417 |
| LMArena German | 1440 | 1404 |
| LMArena Japanese | 1422 | 1391 |
| LMArena Korean | 1411 | 1360 |
| LMArena Russian | 1451 | 1423 |
| LMArena Spanish | 1437 | 1411 |

## Instruction Following

- Claude Sonnet 5: 76.3 (#41)
- DeepSeek-R1: 72.0 (#143)

| Benchmark | Claude Sonnet 5 | DeepSeek-R1 |
|---|---|---|
| LMArena Instruction Following | 1452 | 1382 |
| LiveBench Instruction Following | — | 80.5% |
| IFEval | — | 78.4% |

## Long Context

- Claude Sonnet 5: 44.8 (#55)
- DeepSeek-R1: 45.4 (#36)

| Benchmark | Claude Sonnet 5 | DeepSeek-R1 |
|---|---|---|
| LMArena Longer Query | 1463 | 1391 |
| Fiction.LiveBench | — | 75% |

## Writing & Preference

- Claude Sonnet 5: 69.2 (#25)
- DeepSeek-R1: 61.4 (#88)

| Benchmark | Claude Sonnet 5 | DeepSeek-R1 |
|---|---|---|
| LMArena Text | 1442 | 1428 |
| LMArena Creative Writing | 1416 | 1405 |
| EQ-Bench Creative Writing | 1794 | 1500 |
| LMArena Multi-Turn | 1454 | 1405 |
| Short-Story Creative Writing | — | 83% |
| WildBench | — | 82.8% |
| EQ-Bench 4 | 1236 | — |
| LiveBench Language | — | 48.5% |

## FAQ

### Is Claude Sonnet 5 better than DeepSeek-R1?

Claude Sonnet 5 is the stronger model overall, scoring 54.6 to 42.3 on the Noometry Index. DeepSeek-R1 costs 4.4× less per token, which makes it the better buy when Claude Sonnet 5's lead doesn't matter for your workload.

### Which is cheaper, Claude Sonnet 5 or DeepSeek-R1?

DeepSeek-R1 is cheaper. It lists at $0.50 per million input tokens and $2.15 per million output tokens; Claude Sonnet 5 lists at $2 and $10.

### Is Claude Sonnet 5 or DeepSeek-R1 better for coding?

Claude Sonnet 5 scores higher on coding benchmarks: 55.5 versus 46.3 in the Noometry coding category.

### Which has the bigger context window?

Claude Sonnet 5 does, with 1M tokens against 164K.

### How many benchmarks do Claude Sonnet 5 and DeepSeek-R1 share?

27 benchmarks have published results for both models. Claude Sonnet 5 has 51 scored results on Noometry and DeepSeek-R1 has 52.