# Claude 3 Sonnet vs DeepSeek-V3.1

> DeepSeek-V3.1 is the stronger model overall, scoring 42.2 to 28.8 on the Noometry Index.

- Canonical page: https://noometry.com/compare/claude-3-sonnet-vs-deepseek-v3-1
- Last updated: 2026-10-10
- Shared benchmarks: 20

## Summary

- They share 20 benchmarks with published results for both. Claude 3 Sonnet scores higher in 1 category and DeepSeek-V3.1 in 7 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in math, where DeepSeek-V3.1 leads 36.1 to 10.0.
- The biggest single-benchmark swing is DTBench: 53.6% for Claude 3 Sonnet and 82.7% for DeepSeek-V3.1.
- DeepSeek-V3.1 has downloadable open weights; the other is API-only.

## Snapshot

| | Claude 3 Sonnet | DeepSeek-V3.1 |
|---|---|---|
| Provider | Anthropic | DeepSeek |
| Noometry Index | 28.8 | 42.2 |
| Rank | 311 | 106 |
| Context | — | 164K |
| Input $/M | — | $0.25 |
| Output $/M | — | $0.95 |
| Weights | Proprietary | Open |

## Coding

- Claude 3 Sonnet: 29.2 (#296)
- DeepSeek-V3.1: 39.8 (#140)

| Benchmark | Claude 3 Sonnet | DeepSeek-V3.1 |
|---|---|---|
| WeirdML | 10.2% | 38.4% |
| LMArena Coding | 1223 | 1417 |
| BigCodeBench Instruct | 42.7% | — |
| BigCodeBench Complete | 53.8% | — |
| HumanEval+ | 64% | — |
| MBPP+ | 69.3% | — |

## Reasoning

- Claude 3 Sonnet: 19.7 (#232)
- DeepSeek-V3.1: 27.3 (#109)

| Benchmark | Claude 3 Sonnet | DeepSeek-V3.1 |
|---|---|---|
| LMArena Hard Prompts | 1197 | 1417 |
| DTBench | 53.6% | 82.7% |
| Epoch Capabilities Index | 120.69 | 139.92 |
| SimpleBench | — | 40% |
| Kagi LLM Benchmark | — | 53.2% |
| LMCA | — | 24.3% |
| ForecastBench | — | 58 |
| WinoGrande | 75.1% | — |

## Math

- Claude 3 Sonnet: 10.0 (#305)
- DeepSeek-V3.1: 36.1 (#125)

| Benchmark | Claude 3 Sonnet | DeepSeek-V3.1 |
|---|---|---|
| LMArena Math | 1213 | 1420 |
| OTIS Mock AIME 2024-2025 | 2.5% | — |
| MATH Level 5 | 18.2% | — |

## Knowledge

- Claude 3 Sonnet: 21.1 (#271)
- DeepSeek-V3.1: 43.0 (#86)

| Benchmark | Claude 3 Sonnet | DeepSeek-V3.1 |
|---|---|---|
| LMArena Expert | 1173 | 1403 |
| GPQA Diamond | 40.6% | — |
| Vectara Hallucination Rate | — | 5.5% |
| MMLU | 75.9% | — |

## Multimodal

- Claude 3 Sonnet: 24.7 (#120)
- DeepSeek-V3.1: —

| Benchmark | Claude 3 Sonnet | DeepSeek-V3.1 |
|---|---|---|
| LMArena Vision | 984 | — |

## Multilingual

- Claude 3 Sonnet: 38.0 (#229)
- DeepSeek-V3.1: 51.8 (#100)

| Benchmark | Claude 3 Sonnet | DeepSeek-V3.1 |
|---|---|---|
| LMArena Non-English | 1205 | 1400 |
| LMArena Chinese | 1188 | 1470 |
| LMArena French | 1228 | 1447 |
| LMArena German | 1204 | 1412 |
| LMArena Japanese | 1131 | 1374 |
| LMArena Korean | 1128 | 1337 |
| LMArena Russian | 1227 | 1405 |
| LMArena Spanish | 1204 | 1429 |

## Instruction Following

- Claude 3 Sonnet: 63.1 (#230)
- DeepSeek-V3.1: 74.1 (#105)

| Benchmark | Claude 3 Sonnet | DeepSeek-V3.1 |
|---|---|---|
| LMArena Instruction Following | 1200 | 1400 |

## Long Context

- Claude 3 Sonnet: 36.7 (#223)
- DeepSeek-V3.1: 36.3 (#227)

| Benchmark | Claude 3 Sonnet | DeepSeek-V3.1 |
|---|---|---|
| LMArena Longer Query | 1211 | 1422 |
| Fiction.LiveBench | — | 52.8% |

## Writing & Preference

- Claude 3 Sonnet: 42.3 (#233)
- DeepSeek-V3.1: 60.5 (#93)

| Benchmark | Claude 3 Sonnet | DeepSeek-V3.1 |
|---|---|---|
| LMArena Text | 1218 | 1420 |
| LMArena Creative Writing | 1186 | 1401 |
| LMArena Multi-Turn | 1227 | 1408 |
| EQ-Bench Creative Writing | — | 1436 |

## FAQ

### Is Claude 3 Sonnet better than DeepSeek-V3.1?

DeepSeek-V3.1 is the stronger model overall, scoring 42.2 to 28.8 on the Noometry Index.

### Is Claude 3 Sonnet or DeepSeek-V3.1 better for coding?

DeepSeek-V3.1 scores higher on coding benchmarks: 39.8 versus 29.2 in the Noometry coding category.

### How many benchmarks do Claude 3 Sonnet and DeepSeek-V3.1 share?

20 benchmarks have published results for both models. Claude 3 Sonnet has 30 scored results on Noometry and DeepSeek-V3.1 has 27.