# Claude 3.5 Sonnet vs Deepseek Coder v2

> Deepseek Coder v2 is the stronger model overall, scoring 35.9 to 34.6 on the Noometry Index.

- Canonical page: https://noometry.com/compare/claude-3-5-sonnet-vs-deepseek-coder-v2
- Last updated: 2026-10-10
- Shared benchmarks: 21

## Summary

- They share 21 benchmarks with published results for both. Claude 3.5 Sonnet scores higher in 5 categories and Deepseek Coder v2 in 3 categories; 6 gaps are clear of the uncertainty.
- The widest gap is in math, where Deepseek Coder v2 leads 34.9 to 19.2.
- Deepseek Coder v2 has downloadable open weights; the other is API-only.

## Snapshot

| | Claude 3.5 Sonnet | Deepseek Coder v2 |
|---|---|---|
| Provider | Anthropic | DeepSeek |
| Noometry Index | 34.6 | 35.9 |
| Rank | 231 | 220 |
| Context | — | — |
| Input $/M | — | — |
| Output $/M | — | — |
| Weights | Proprietary | Open |

## Coding

- Claude 3.5 Sonnet: 39.0 (#165)
- Deepseek Coder v2: 38.1 (#183)

| Benchmark | Claude 3.5 Sonnet | Deepseek Coder v2 |
|---|---|---|
| BigCodeBench Instruct | 46.8% | 48.2% |
| LMArena Coding | 1342 | 1251 |
| BigCodeBench Complete | 58.6% | 59.7% |
| HumanEval+ | 81.7% | 82.3% |
| MBPP+ | 74.3% | 75.1% |
| Aider Polyglot | 51.6% | — |
| GSO | 4.6% | — |
| WeirdML | 40% | — |
| LiveBench Coding | 67.1% | — |
| CadEval | 48% | — |

## Agentic & Tool Use

- Claude 3.5 Sonnet: 32.3 (#67)
- Deepseek Coder v2: —

| Benchmark | Claude 3.5 Sonnet | Deepseek Coder v2 |
|---|---|---|
| TheAgentCompany | 24% | — |
| Cybench | 17.5% | — |
| BALROG | 32.6% | — |
| METR Time Horizons | 45.2% | — |

## Reasoning

- Claude 3.5 Sonnet: 23.1 (#183)
- Deepseek Coder v2: 23.6 (#176)

| Benchmark | Claude 3.5 Sonnet | Deepseek Coder v2 |
|---|---|---|
| LMArena Hard Prompts | 1305 | 1207 |
| SimpleBench | 41.4% | — |
| EnigmaEval | 0.9% | — |
| LiveBench Reasoning | 56.7% | — |
| DTBench | 67.8% | — |
| LiveBench Data Analysis | 55% | — |
| Epoch Capabilities Index | 133.55 | — |
| ForecastBench | 60.7 | — |
| LiveBench | 59% | — |
| WinoGrande | — | 83.7% |

## Math

- Claude 3.5 Sonnet: 19.2 (#288)
- Deepseek Coder v2: 34.9 (#190)

| Benchmark | Claude 3.5 Sonnet | Deepseek Coder v2 |
|---|---|---|
| LMArena Math | 1307 | 1241 |
| OTIS Mock AIME 2024-2025 | 8.5% | — |
| Omni-MATH | 27.6% | — |
| LiveBench Math | 52.3% | — |
| MATH Level 5 | 56.9% | — |
| FrontierMath (Feb 2025 set) | 2.1% | — |
| FrontierMath Tier 4 (v1) | 0% | — |
| GSM8K | — | 94.5% |

## Knowledge

- Claude 3.5 Sonnet: 28.6 (#245)
- Deepseek Coder v2: 32.3 (#212)

| Benchmark | Claude 3.5 Sonnet | Deepseek Coder v2 |
|---|---|---|
| LMArena Expert | 1265 | 1181 |
| GPQA Diamond | 55.3% | — |
| Humanity's Last Exam | 4.1% | — |
| MMLU-Pro | 77.7% | — |
| Confabulations | 19.9% | — |
| GPQA (HELM) | 56.5% | — |
| ARC (AI2) Challenge | — | 64.3% |
| MMLU | 87.3% | — |

## Multimodal

- Claude 3.5 Sonnet: 26.5 (#120)
- Deepseek Coder v2: —

| Benchmark | Claude 3.5 Sonnet | Deepseek Coder v2 |
|---|---|---|
| LMArena Vision | 1125 | — |
| Video-MME | 60% | — |
| GeoBench | 62% | — |
| VPCT | 33% | — |

## Multilingual

- Claude 3.5 Sonnet: 43.2 (#185)
- Deepseek Coder v2: 36.3 (#240)

| Benchmark | Claude 3.5 Sonnet | Deepseek Coder v2 |
|---|---|---|
| LMArena Non-English | 1283 | 1182 |
| LMArena Chinese | 1272 | 1201 |
| LMArena French | 1305 | 1185 |
| LMArena German | 1297 | 1164 |
| LMArena Japanese | 1234 | 1126 |
| LMArena Korean | 1200 | 1104 |
| LMArena Russian | 1306 | 1188 |
| LMArena Spanish | 1290 | 1153 |

## Instruction Following

- Claude 3.5 Sonnet: 68.8 (#182)
- Deepseek Coder v2: 61.7 (#242)

| Benchmark | Claude 3.5 Sonnet | Deepseek Coder v2 |
|---|---|---|
| LMArena Instruction Following | 1297 | 1180 |
| LiveBench Instruction Following | 69.3% | — |
| IFEval | 85.5% | — |

## Long Context

- Claude 3.5 Sonnet: 39.9 (#167)
- Deepseek Coder v2: 37.0 (#224)

| Benchmark | Claude 3.5 Sonnet | Deepseek Coder v2 |
|---|---|---|
| LMArena Longer Query | 1311 | 1219 |

## Writing & Preference

- Claude 3.5 Sonnet: 52.9 (#164)
- Deepseek Coder v2: 38.2 (#253)

| Benchmark | Claude 3.5 Sonnet | Deepseek Coder v2 |
|---|---|---|
| LMArena Text | 1298 | 1191 |
| LMArena Creative Writing | 1292 | 1120 |
| LMArena Multi-Turn | 1326 | 1177 |
| Short-Story Creative Writing | 80.3% | — |
| EQ-Bench Creative Writing | 1451 | — |
| WildBench | 79.2% | — |
| LiveBench Language | 53.8% | — |

## FAQ

### Is Claude 3.5 Sonnet better than Deepseek Coder v2?

Deepseek Coder v2 is the stronger model overall, scoring 35.9 to 34.6 on the Noometry Index.

### Is Claude 3.5 Sonnet or Deepseek Coder v2 better for coding?

They score almost the same on coding (39.0 vs 38.1); test both on your own repository before choosing.

### How many benchmarks do Claude 3.5 Sonnet and Deepseek Coder v2 share?

21 benchmarks have published results for both models. Claude 3.5 Sonnet has 60 scored results on Noometry and Deepseek Coder v2 has 24.