# Claude 3.7 Sonnet vs DeepSeek V4 Flash

> DeepSeek V4 Flash is the stronger model overall, scoring 53.6 to 39.4 on the Noometry Index.

- Canonical page: https://noometry.com/compare/claude-3-7-sonnet-vs-deepseek-v4-flash
- Last updated: 2026-10-10
- Shared benchmarks: 24

## Summary

- They share 24 benchmarks with published results for both. Claude 3.7 Sonnet scores higher in 1 category and DeepSeek V4 Flash in 7 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where DeepSeek V4 Flash leads 53.7 to 18.7.
- The biggest single-benchmark swing is ARC-AGI-2: 0.9% for Claude 3.7 Sonnet and 61.4% for DeepSeek V4 Flash.
- DeepSeek V4 Flash has downloadable open weights; the other is API-only.

## Snapshot

| | Claude 3.7 Sonnet | DeepSeek V4 Flash |
|---|---|---|
| Provider | Anthropic | DeepSeek |
| Noometry Index | 39.4 | 53.6 |
| Rank | 154 | 32 |
| Context | — | 1M |
| Input $/M | — | $0.15 |
| Output $/M | — | $0.60 |
| Weights | Proprietary | Open |

## Coding

- Claude 3.7 Sonnet: 41.1 (#120)
- DeepSeek V4 Flash: 47.6 (#56)

| Benchmark | Claude 3.7 Sonnet | DeepSeek V4 Flash |
|---|---|---|
| LMArena Coding | 1361 | 1457 |
| SWE-bench Verified | 61% | — |
| FrontierCode | — | 18.8% |
| SWE-bench Verified (bash only) | 52.8% | — |
| Aider Polyglot | 64.9% | — |
| LMArena WebDev | — | 1581 |
| SciCode | — | 49.9% |
| GSO | 3.8% | — |
| WeirdML | — | 63% |
| LiveBench Coding | 74.5% | — |
| CadEval | 54% | — |
| ALE-Bench | — | 1,306 |

## Agentic & Tool Use

- Claude 3.7 Sonnet: 33.9 (#46)
- DeepSeek V4 Flash: —

| Benchmark | Claude 3.7 Sonnet | DeepSeek V4 Flash |
|---|---|---|
| TheAgentCompany | 30.9% | — |
| Cybench | 20% | — |
| DeepResearch Bench | 43.6% | — |
| OSWorld | 35.8% | — |
| METR Time Horizons | 60% | — |

## Reasoning

- Claude 3.7 Sonnet: 18.7 (#252)
- DeepSeek V4 Flash: 53.7 (#25)

| Benchmark | Claude 3.7 Sonnet | DeepSeek V4 Flash |
|---|---|---|
| ARC-AGI-2 | 0.9% | 61.4% |
| SimpleBench | 46.4% | 61.1% |
| ARC-AGI-1 | 28.6% | 89% |
| LMArena Hard Prompts | 1333 | 1443 |
| Epoch Capabilities Index | 141.16 | 154.51 |
| Kagi LLM Benchmark | — | 52.2% |
| NYT Connections (extended) | — | 89.6% |
| CritPt | — | 16.6% |
| Chess Puzzles | — | 33% |
| EnigmaEval | 4.2% | — |
| LiveBench Reasoning | 87.8% | — |
| Mystery Game Puzzles | — | 34% |
| DTBench | — | 90.9% |
| LiveBench Data Analysis | 74% | — |
| LMCA | — | 41.7% |
| ForecastBench | 61.8 | — |
| LiveBench | 76.1% | — |

## Math

- Claude 3.7 Sonnet: 35.7 (#137)
- DeepSeek V4 Flash: 60.0 (#31)

| Benchmark | Claude 3.7 Sonnet | DeepSeek V4 Flash |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 57.8% | 94.4% |
| LMArena Math | 1336 | 1427 |
| FrontierMath (Tiers 1-3) | — | 57.5% |
| FrontierMath Tier 4 | — | 24.4% |
| MathArena Final-Answer Competitions | — | 76.5% |
| ProofBench | — | 56% |
| Omni-MATH | 33% | — |
| LiveBench Math | 79% | — |
| MATH Level 5 | 91.2% | — |
| FrontierMath (Feb 2025 set) | 4.1% | — |

## Knowledge

- Claude 3.7 Sonnet: 39.7 (#117)
- DeepSeek V4 Flash: 55.5 (#43)

| Benchmark | Claude 3.7 Sonnet | DeepSeek V4 Flash |
|---|---|---|
| GPQA Diamond | 79.7% | 91% |
| LMArena Expert | 1321 | 1441 |
| Humanity's Last Exam | 8% | — |
| SimpleQA Verified | — | 33.6% |
| MMLU-Pro | 78.4% | — |
| Confabulations | 14.7% | — |
| GPQA (HELM) | 60.8% | — |

## Multimodal

- Claude 3.7 Sonnet: 33.1 (#90)
- DeepSeek V4 Flash: —

| Benchmark | Claude 3.7 Sonnet | DeepSeek V4 Flash |
|---|---|---|
| LMArena Vision | 1169 | — |
| GeoBench | 68% | — |
| VPCT | 39% | — |
| SpatialViz-Bench | 33.9% | — |

## Multilingual

- Claude 3.7 Sonnet: 44.3 (#174)
- DeepSeek V4 Flash: 53.2 (#71)

| Benchmark | Claude 3.7 Sonnet | DeepSeek V4 Flash |
|---|---|---|
| LMArena Non-English | 1296 | 1420 |
| LMArena Chinese | 1299 | 1467 |
| LMArena French | 1302 | 1438 |
| LMArena German | 1301 | 1418 |
| LMArena Japanese | 1268 | 1403 |
| LMArena Korean | 1249 | 1383 |
| LMArena Russian | 1311 | 1428 |
| LMArena Spanish | 1299 | 1437 |

## Instruction Following

- Claude 3.7 Sonnet: 73.1 (#120)
- DeepSeek V4 Flash: 75.1 (#76)

| Benchmark | Claude 3.7 Sonnet | DeepSeek V4 Flash |
|---|---|---|
| LMArena Instruction Following | 1352 | 1421 |
| LiveBench Instruction Following | 81.3% | — |
| IFEval | 83.4% | — |

## Long Context

- Claude 3.7 Sonnet: 50.2 (#10)
- DeepSeek V4 Flash: 43.8 (#81)

| Benchmark | Claude 3.7 Sonnet | DeepSeek V4 Flash |
|---|---|---|
| LMArena Longer Query | 1373 | 1435 |
| Fiction.LiveBench | 83.3% | — |

## Writing & Preference

- Claude 3.7 Sonnet: 54.6 (#145)
- DeepSeek V4 Flash: 64.0 (#59)

| Benchmark | Claude 3.7 Sonnet | DeepSeek V4 Flash |
|---|---|---|
| LMArena Text | 1314 | 1432 |
| LMArena Creative Writing | 1332 | 1403 |
| EQ-Bench Creative Writing | 1412 | 1559 |
| LMArena Multi-Turn | 1339 | 1449 |
| Short-Story Creative Writing | 81.1% | — |
| WildBench | 81.4% | — |
| LiveBench Language | 59.9% | — |

## FAQ

### Is Claude 3.7 Sonnet better than DeepSeek V4 Flash?

DeepSeek V4 Flash is the stronger model overall, scoring 53.6 to 39.4 on the Noometry Index.

### Is Claude 3.7 Sonnet or DeepSeek V4 Flash better for coding?

DeepSeek V4 Flash scores higher on coding benchmarks: 47.6 versus 41.1 in the Noometry coding category.

### How many benchmarks do Claude 3.7 Sonnet and DeepSeek V4 Flash share?

24 benchmarks have published results for both models. Claude 3.7 Sonnet has 58 scored results on Noometry and DeepSeek V4 Flash has 41.