# Claude Sonnet 5 vs DeepSeek-V3.1

> Claude Sonnet 5 is the stronger model overall, scoring 54.5 to 42.2 on the Noometry Index. DeepSeek-V3.1 costs 9.4× 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-v3-1
- Last updated: 2026-10-10
- Shared benchmarks: 24

## Summary

- They share 24 benchmarks with published results for both. Claude Sonnet 5 scores higher in 8 categories and DeepSeek-V3.1 in 0 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in math, where Claude Sonnet 5 leads 66.1 to 36.1.
- The biggest single-benchmark swing is WeirdML: 68.8% for Claude Sonnet 5 and 38.4% for DeepSeek-V3.1.
- DeepSeek-V3.1 is cheaper at $0.25 / $0.95 per million input/output tokens, against $2 / $10 for Claude Sonnet 5.
- Claude Sonnet 5 accepts more context: 1M tokens versus 164K.
- DeepSeek-V3.1 has downloadable open weights; the other is API-only.

## Snapshot

| | Claude Sonnet 5 | DeepSeek-V3.1 |
|---|---|---|
| Provider | Anthropic | DeepSeek |
| Noometry Index | 54.5 | 42.2 |
| Rank | 26 | 106 |
| Context | 1M | 164K |
| Input $/M | $2 | $0.25 |
| Output $/M | $10 | $0.95 |
| Weights | Proprietary | Open |

## Coding

- Claude Sonnet 5: 55.5 (#20)
- DeepSeek-V3.1: 39.8 (#140)

| Benchmark | Claude Sonnet 5 | DeepSeek-V3.1 |
|---|---|---|
| WeirdML | 68.8% | 38.4% |
| LMArena Coding | 1483 | 1417 |
| DeepSWE | 53.8% | — |
| FrontierCode | 42.7% | — |
| CursorBench | 34.1% | — |
| LMArena WebDev | 1540 | — |
| SciCode | 53.6% | — |
| GSO | 37.3% | — |
| ALE-Bench | 1,463 | — |

## Agentic & Tool Use

- Claude Sonnet 5: 42.7 (#16)
- DeepSeek-V3.1: —

| Benchmark | Claude Sonnet 5 | DeepSeek-V3.1 |
|---|---|---|
| APEX-Agents | 54.5% | — |
| GBAEval | 65.3% | — |
| LMArena Search | 1194 | — |
| Vending-Bench 2 | 6,378 | — |

## Reasoning

- Claude Sonnet 5: 48.2 (#37)
- DeepSeek-V3.1: 27.3 (#109)

| Benchmark | Claude Sonnet 5 | DeepSeek-V3.1 |
|---|---|---|
| SimpleBench | 60.6% | 40% |
| LMArena Hard Prompts | 1461 | 1417 |
| DTBench | 92.5% | 82.7% |
| LMCA | 50% | 24.3% |
| Epoch Capabilities Index | 156.34 | 139.92 |
| ForecastBench | 61.1 | 58 |
| Kagi LLM Benchmark | — | 53.2% |
| NYT Connections (extended) | 75.1% | — |
| CritPt | 16.9% | — |
| Chess Puzzles | 35% | — |
| Mystery Game Puzzles | 35% | — |
| Surface Evolver Bench | 60% | — |
| Bench to the Future 3 | 0.14 | — |

## Math

- Claude Sonnet 5: 66.1 (#21)
- DeepSeek-V3.1: 36.1 (#125)

| Benchmark | Claude Sonnet 5 | DeepSeek-V3.1 |
|---|---|---|
| LMArena Math | 1467 | 1420 |
| FrontierMath (Tiers 1-3) | 65.6% | — |
| FrontierMath Tier 4 | 29.3% | — |
| OTIS Mock AIME 2024-2025 | 94.7% | — |
| ProofBench | 77% | — |

## Knowledge

- Claude Sonnet 5: 55.7 (#42)
- DeepSeek-V3.1: 43.0 (#86)

| Benchmark | Claude Sonnet 5 | DeepSeek-V3.1 |
|---|---|---|
| LMArena Expert | 1491 | 1403 |
| GPQA Diamond | 90.5% | — |
| SimpleQA Verified | 33.7% | — |
| Vectara Hallucination Rate | — | 5.5% |

## Multimodal

- Claude Sonnet 5: 42.4 (#26)
- DeepSeek-V3.1: —

| Benchmark | Claude Sonnet 5 | DeepSeek-V3.1 |
|---|---|---|
| LMArena Vision | 1275 | — |
| Blueprint-Bench 2 | 24.9% | — |
| LMArena Document | 1466 | — |

## Multilingual

- Claude Sonnet 5: 54.0 (#55)
- DeepSeek-V3.1: 51.8 (#100)

| Benchmark | Claude Sonnet 5 | DeepSeek-V3.1 |
|---|---|---|
| LMArena Non-English | 1431 | 1400 |
| LMArena Chinese | 1475 | 1470 |
| LMArena French | 1457 | 1447 |
| LMArena German | 1448 | 1412 |
| LMArena Japanese | 1422 | 1374 |
| LMArena Korean | 1411 | 1337 |
| LMArena Russian | 1452 | 1405 |
| LMArena Spanish | 1436 | 1429 |

## Instruction Following

- Claude Sonnet 5: 76.6 (#39)
- DeepSeek-V3.1: 74.1 (#105)

| Benchmark | Claude Sonnet 5 | DeepSeek-V3.1 |
|---|---|---|
| LMArena Instruction Following | 1453 | 1400 |

## Long Context

- Claude Sonnet 5: 44.8 (#53)
- DeepSeek-V3.1: 36.3 (#227)

| Benchmark | Claude Sonnet 5 | DeepSeek-V3.1 |
|---|---|---|
| LMArena Longer Query | 1464 | 1422 |
| Fiction.LiveBench | — | 52.8% |

## Writing & Preference

- Claude Sonnet 5: 69.4 (#24)
- DeepSeek-V3.1: 60.5 (#93)

| Benchmark | Claude Sonnet 5 | DeepSeek-V3.1 |
|---|---|---|
| LMArena Text | 1443 | 1420 |
| LMArena Creative Writing | 1416 | 1401 |
| EQ-Bench Creative Writing | 1794 | 1436 |
| LMArena Multi-Turn | 1454 | 1408 |
| EQ-Bench 4 | 1236 | — |

## FAQ

### Is Claude Sonnet 5 better than DeepSeek-V3.1?

Claude Sonnet 5 is the stronger model overall, scoring 54.5 to 42.2 on the Noometry Index. DeepSeek-V3.1 costs 9.4× 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-V3.1?

DeepSeek-V3.1 is cheaper. It lists at $0.25 per million input tokens and $0.95 per million output tokens; Claude Sonnet 5 lists at $2 and $10.

### Is Claude Sonnet 5 or DeepSeek-V3.1 better for coding?

Claude Sonnet 5 scores higher on coding benchmarks: 55.5 versus 39.8 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-V3.1 share?

24 benchmarks have published results for both models. Claude Sonnet 5 has 51 scored results on Noometry and DeepSeek-V3.1 has 27.