# Claude Sonnet 5 vs DeepSeek V4 Pro

> Claude Sonnet 5 and DeepSeek V4 Pro score almost the same on the Noometry Index (54.5 vs 54.2), so choose on price, context window or the category you care about most.

- Canonical page: https://noometry.com/compare/claude-sonnet-5-vs-deepseek-v4-pro
- Last updated: 2026-10-10
- Shared benchmarks: 41

## Summary

- They share 41 benchmarks with published results for both. Claude Sonnet 5 scores higher in 5 categories and DeepSeek V4 Pro in 4 categories; 6 gaps are clear of the uncertainty.
- The widest gap is in agentic & tool use, where Claude Sonnet 5 leads 42.7 to 32.7.
- The biggest single-benchmark swing is ProofBench: 77% for Claude Sonnet 5 and 50% for DeepSeek V4 Pro.
- DeepSeek V4 Pro is cheaper at $0.43 / $0.87 per million input/output tokens, against $2 / $10 for Claude Sonnet 5.
- DeepSeek V4 Pro has downloadable open weights; the other is API-only.

## Snapshot

| | Claude Sonnet 5 | DeepSeek V4 Pro |
|---|---|---|
| Provider | Anthropic | DeepSeek |
| Noometry Index | 54.5 | 54.2 |
| Rank | 26 | 28 |
| Context | 1M | 1M |
| Input $/M | $2 | $0.43 |
| Output $/M | $10 | $0.87 |
| Weights | Proprietary | Open |

## Coding

- Claude Sonnet 5: 55.5 (#20)
- DeepSeek V4 Pro: 52.2 (#31)

| Benchmark | Claude Sonnet 5 | DeepSeek V4 Pro |
|---|---|---|
| FrontierCode | 42.7% | 28.6% |
| LMArena WebDev | 1540 | 1582 |
| SciCode | 53.6% | 51% |
| WeirdML | 68.8% | 66.2% |
| LMArena Coding | 1483 | 1470 |
| ALE-Bench | 1,463 | 1,403 |
| SWE-bench Verified | — | 77.6% |
| DeepSWE | 53.8% | — |
| CursorBench | 34.1% | — |
| GSO | 37.3% | — |

## Agentic & Tool Use

- Claude Sonnet 5: 42.7 (#16)
- DeepSeek V4 Pro: 32.7 (#54)

| Benchmark | Claude Sonnet 5 | DeepSeek V4 Pro |
|---|---|---|
| APEX-Agents | 54.5% | 47.3% |
| Vending-Bench 2 | 6,378 | 3,285 |
| GBAEval | 65.3% | — |
| LMArena Search | 1194 | — |

## Reasoning

- Claude Sonnet 5: 48.2 (#37)
- DeepSeek V4 Pro: 56.4 (#22)

| Benchmark | Claude Sonnet 5 | DeepSeek V4 Pro |
|---|---|---|
| NYT Connections (extended) | 75.1% | 91.3% |
| CritPt | 16.9% | 18% |
| Chess Puzzles | 35% | 47% |
| LMArena Hard Prompts | 1461 | 1461 |
| Mystery Game Puzzles | 35% | 43% |
| DTBench | 92.5% | 93.9% |
| LMCA | 50% | 45.5% |
| Surface Evolver Bench | 60% | 40% |
| Epoch Capabilities Index | 156.34 | 155.39 |
| ForecastBench | 61.1 | 56.1 |
| ARC-AGI-2 | — | 61.3% |
| SimpleBench | 60.6% | — |
| Kagi LLM Benchmark | — | 53.5% |
| ARC-AGI-1 | — | 90.5% |
| Bench to the Future 3 | 0.14 | — |

## Math

- Claude Sonnet 5: 66.1 (#21)
- DeepSeek V4 Pro: 64.6 (#24)

| Benchmark | Claude Sonnet 5 | DeepSeek V4 Pro |
|---|---|---|
| FrontierMath (Tiers 1-3) | 65.6% | 64.6% |
| FrontierMath Tier 4 | 29.3% | 26.8% |
| OTIS Mock AIME 2024-2025 | 94.7% | 98.6% |
| ProofBench | 77% | 50% |
| LMArena Math | 1467 | 1455 |
| MathArena Final-Answer Competitions | — | 76.6% |

## Knowledge

- Claude Sonnet 5: 55.7 (#42)
- DeepSeek V4 Pro: 59.5 (#28)

| Benchmark | Claude Sonnet 5 | DeepSeek V4 Pro |
|---|---|---|
| GPQA Diamond | 90.5% | 91.7% |
| SimpleQA Verified | 33.7% | 52.9% |
| LMArena Expert | 1491 | 1463 |
| Vectara Hallucination Rate | — | 8.6% |

## Multimodal

- Claude Sonnet 5: 42.4 (#26)
- DeepSeek V4 Pro: —

| Benchmark | Claude Sonnet 5 | DeepSeek V4 Pro |
|---|---|---|
| LMArena Vision | 1275 | — |
| Blueprint-Bench 2 | 24.9% | — |
| LMArena Document | 1466 | — |

## Multilingual

- Claude Sonnet 5: 54.0 (#55)
- DeepSeek V4 Pro: 54.5 (#44)

| Benchmark | Claude Sonnet 5 | DeepSeek V4 Pro |
|---|---|---|
| LMArena Non-English | 1431 | 1438 |
| LMArena Chinese | 1475 | 1486 |
| LMArena French | 1457 | 1473 |
| LMArena German | 1448 | 1458 |
| LMArena Japanese | 1422 | 1448 |
| LMArena Korean | 1411 | 1452 |
| LMArena Russian | 1452 | 1452 |
| LMArena Spanish | 1436 | 1457 |

## Instruction Following

- Claude Sonnet 5: 76.6 (#39)
- DeepSeek V4 Pro: 76.3 (#44)

| Benchmark | Claude Sonnet 5 | DeepSeek V4 Pro |
|---|---|---|
| LMArena Instruction Following | 1453 | 1448 |

## Long Context

- Claude Sonnet 5: 44.8 (#53)
- DeepSeek V4 Pro: 45.0 (#49)

| Benchmark | Claude Sonnet 5 | DeepSeek V4 Pro |
|---|---|---|
| LMArena Longer Query | 1464 | 1459 |
| CL-bench Life | — | 13.5% |

## Writing & Preference

- Claude Sonnet 5: 69.4 (#24)
- DeepSeek V4 Pro: 65.6 (#45)

| Benchmark | Claude Sonnet 5 | DeepSeek V4 Pro |
|---|---|---|
| LMArena Text | 1443 | 1451 |
| LMArena Creative Writing | 1416 | 1446 |
| EQ-Bench Creative Writing | 1794 | 1553 |
| EQ-Bench 4 | 1236 | 1166 |
| LMArena Multi-Turn | 1454 | 1467 |

## FAQ

### Is Claude Sonnet 5 better than DeepSeek V4 Pro?

Claude Sonnet 5 and DeepSeek V4 Pro score almost the same on the Noometry Index (54.5 vs 54.2), so choose on price, context window or the category you care about most.

### Which is cheaper, Claude Sonnet 5 or DeepSeek V4 Pro?

DeepSeek V4 Pro is cheaper. It lists at $0.43 per million input tokens and $0.87 per million output tokens; Claude Sonnet 5 lists at $2 and $10.

### Is Claude Sonnet 5 or DeepSeek V4 Pro better for coding?

Claude Sonnet 5 scores higher on coding benchmarks: 55.5 versus 52.2 in the Noometry coding category.

### Which has the bigger context window?

Both accept 1M tokens.

### How many benchmarks do Claude Sonnet 5 and DeepSeek V4 Pro share?

41 benchmarks have published results for both models. Claude Sonnet 5 has 51 scored results on Noometry and DeepSeek V4 Pro has 48.