# Claude Opus 5 vs DeepSeek V4 Pro

> Claude Opus 5 is the stronger model overall, scoring 67.7 to 54.2 on the Noometry Index. DeepSeek V4 Pro costs 18× less per token, which makes it the better buy when Claude Opus 5's lead doesn't matter for your workload.

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

## Summary

- They share 41 benchmarks with published results for both. Claude Opus 5 scores higher in 9 categories and DeepSeek V4 Pro in 0 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in agentic & tool use, where Claude Opus 5 leads 55.5 to 32.7.
- The biggest single-benchmark swing is ProofBench: 99% for Claude Opus 5 and 50% for DeepSeek V4 Pro.
- DeepSeek V4 Pro is cheaper at $0.43 / $0.87 per million input/output tokens, against $5 / $25 for Claude Opus 5.
- DeepSeek V4 Pro has downloadable open weights; the other is API-only.

## Snapshot

| | Claude Opus 5 | DeepSeek V4 Pro |
|---|---|---|
| Provider | Anthropic | DeepSeek |
| Noometry Index | 67.7 | 54.2 |
| Rank | 4 | 28 |
| Context | 1M | 1M |
| Input $/M | $5 | $0.43 |
| Output $/M | $25 | $0.87 |
| Weights | Proprietary | Open |

## Coding

- Claude Opus 5: 67.0 (#5)
- DeepSeek V4 Pro: 52.2 (#31)

| Benchmark | Claude Opus 5 | DeepSeek V4 Pro |
|---|---|---|
| FrontierCode | 53.4% | 28.6% |
| LMArena WebDev | 1694 | 1582 |
| SciCode | 56.4% | 51% |
| WeirdML | 91.8% | 66.2% |
| LMArena Coding | 1533 | 1470 |
| ALE-Bench | 2,165 | 1,403 |
| SWE-bench Verified | — | 77.6% |
| DeepSWE | 73.6% | — |
| CursorBench | 46.6% | — |
| FrontierSWE | 52% | — |

## Agentic & Tool Use

- Claude Opus 5: 55.5 (#1)
- DeepSeek V4 Pro: 32.7 (#54)

| Benchmark | Claude Opus 5 | DeepSeek V4 Pro |
|---|---|---|
| APEX-Agents | 65.8% | 47.3% |
| Vending-Bench 2 | 11,182 | 3,285 |
| OSWorld 2.0 | 31.4% | — |
| τ²-bench Banking | 48.7% | — |
| PostTrainBench | 35% | — |
| BALROG | 63.4% | — |
| GBAEval | 79.6% | — |
| GDP.pdf | 24% | — |

## Reasoning

- Claude Opus 5: 77.1 (#3)
- DeepSeek V4 Pro: 56.4 (#22)

| Benchmark | Claude Opus 5 | DeepSeek V4 Pro |
|---|---|---|
| ARC-AGI-2 | 90.4% | 61.3% |
| NYT Connections (extended) | 94.3% | 91.3% |
| ARC-AGI-1 | 97.5% | 90.5% |
| CritPt | 29.1% | 18% |
| Chess Puzzles | 42% | 47% |
| LMArena Hard Prompts | 1525 | 1461 |
| Mystery Game Puzzles | 59% | 43% |
| DTBench | 97.9% | 93.9% |
| LMCA | 64.5% | 45.5% |
| Epoch Capabilities Index | 162.67 | 155.39 |
| SimpleBench | 80.6% | — |
| Kagi LLM Benchmark | — | 53.5% |
| EBR-Bench | 45.7% | — |
| Surface Evolver Bench | — | 40% |
| Bench to the Future 3 | 0.12 | — |
| ForecastBench | — | 56.1 |

## Math

- Claude Opus 5: 86.1 (#6)
- DeepSeek V4 Pro: 64.6 (#24)

| Benchmark | Claude Opus 5 | DeepSeek V4 Pro |
|---|---|---|
| FrontierMath (Tiers 1-3) | 85.6% | 64.6% |
| FrontierMath Tier 4 | 73.2% | 26.8% |
| OTIS Mock AIME 2024-2025 | 98.9% | 98.6% |
| ProofBench | 99% | 50% |
| LMArena Math | 1533 | 1455 |
| MathArena Final-Answer Competitions | — | 76.6% |

## Knowledge

- Claude Opus 5: 66.8 (#8)
- DeepSeek V4 Pro: 59.5 (#28)

| Benchmark | Claude Opus 5 | DeepSeek V4 Pro |
|---|---|---|
| GPQA Diamond | 93.9% | 91.7% |
| SimpleQA Verified | 59.9% | 52.9% |
| LMArena Expert | 1558 | 1463 |
| Vectara Hallucination Rate | — | 8.6% |

## Multimodal

- Claude Opus 5: 51.1 (#6)
- DeepSeek V4 Pro: —

| Benchmark | Claude Opus 5 | DeepSeek V4 Pro |
|---|---|---|
| LMArena Vision | 1321 | — |
| Blueprint-Bench 2 | 30.4% | — |
| Furniture Assembly | 60.8% | — |
| LMArena Document | 1516 | — |

## Multilingual

- Claude Opus 5: 58.8 (#3)
- DeepSeek V4 Pro: 54.5 (#44)

| Benchmark | Claude Opus 5 | DeepSeek V4 Pro |
|---|---|---|
| LMArena Non-English | 1500 | 1438 |
| LMArena Chinese | 1575 | 1486 |
| LMArena French | 1522 | 1473 |
| LMArena German | 1522 | 1458 |
| LMArena Japanese | 1510 | 1448 |
| LMArena Korean | 1526 | 1452 |
| LMArena Russian | 1507 | 1452 |
| LMArena Spanish | 1519 | 1457 |

## Instruction Following

- Claude Opus 5: 79.3 (#5)
- DeepSeek V4 Pro: 76.3 (#44)

| Benchmark | Claude Opus 5 | DeepSeek V4 Pro |
|---|---|---|
| LMArena Instruction Following | 1516 | 1448 |

## Long Context

- Claude Opus 5: 46.5 (#20)
- DeepSeek V4 Pro: 45.0 (#49)

| Benchmark | Claude Opus 5 | DeepSeek V4 Pro |
|---|---|---|
| LMArena Longer Query | 1516 | 1459 |
| CL-bench Life | — | 13.5% |

## Writing & Preference

- Claude Opus 5: 79.3 (#2)
- DeepSeek V4 Pro: 65.6 (#45)

| Benchmark | Claude Opus 5 | DeepSeek V4 Pro |
|---|---|---|
| LMArena Text | 1506 | 1451 |
| LMArena Creative Writing | 1491 | 1446 |
| EQ-Bench Creative Writing | 2133 | 1553 |
| EQ-Bench 4 | 1385 | 1166 |
| LMArena Multi-Turn | 1496 | 1467 |

## FAQ

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

Claude Opus 5 is the stronger model overall, scoring 67.7 to 54.2 on the Noometry Index. DeepSeek V4 Pro costs 18× less per token, which makes it the better buy when Claude Opus 5's lead doesn't matter for your workload.

### Which is cheaper, Claude Opus 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 Opus 5 lists at $5 and $25.

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

Claude Opus 5 scores higher on coding benchmarks: 67.0 versus 52.2 in the Noometry coding category.

### Which has the bigger context window?

Both accept 1M tokens.

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

41 benchmarks have published results for both models. Claude Opus 5 has 57 scored results on Noometry and DeepSeek V4 Pro has 48.