# Claude Opus 4.5 vs DeepSeek-R1

> Claude Opus 4.5 is the stronger model overall, scoring 50.5 to 42.0 on the Noometry Index. DeepSeek-R1 costs 11× less per token, which makes it the better buy when Claude Opus 4.5's lead doesn't matter for your workload.

- Canonical page: https://noometry.com/compare/claude-opus-4-5-vs-deepseek-r1
- Last updated: 2026-10-10
- Shared benchmarks: 33

## Summary

- They share 33 benchmarks with published results for both. Claude Opus 4.5 scores higher in 8 categories and DeepSeek-R1 in 1 category; 9 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Claude Opus 4.5 leads 42.5 to 18.7.
- The biggest single-benchmark swing is ARC-AGI-1: 80% for Claude Opus 4.5 and 21.2% for DeepSeek-R1.
- DeepSeek-R1 is cheaper at $0.50 / $2.15 per million input/output tokens, against $5 / $25 for Claude Opus 4.5.
- Claude Opus 4.5 accepts more context: 200K tokens versus 164K.

## Snapshot

| | Claude Opus 4.5 | DeepSeek-R1 |
|---|---|---|
| Provider | Anthropic | DeepSeek |
| Noometry Index | 50.5 | 42.0 |
| Rank | 39 | 110 |
| Context | 200K | 164K |
| Input $/M | $5 | $0.50 |
| Output $/M | $25 | $2.15 |
| Weights | Proprietary | Proprietary |

## Coding

- Claude Opus 4.5: 55.4 (#21)
- DeepSeek-R1: 45.9 (#63)

| Benchmark | Claude Opus 4.5 | DeepSeek-R1 |
|---|---|---|
| WeirdML | 63.7% | 41.6% |
| LMArena Coding | 1504 | 1427 |
| ALE-Bench | 1,025 | 804.12 |
| AlgoTune | 1.77 | 1.7 |
| SWE-bench Verified | 76.7% | — |
| SWE-bench Verified (bash only) | 76.8% | — |
| Aider Polyglot | — | 71.4% |
| LMArena WebDev | 1493 | — |
| SWE-bench Multilingual | 70.7% | — |
| SciCode | — | 35.7% |
| GSO | 26.5% | — |
| LiveBench Coding | — | 66.7% |

## Agentic & Tool Use

- Claude Opus 4.5: 47.2 (#11)
- DeepSeek-R1: 30.4 (#68)

| Benchmark | Claude Opus 4.5 | DeepSeek-R1 |
|---|---|---|
| DeepResearch Bench | 54.8% | 35.1% |
| BALROG | 43.5% | 34.9% |
| METR Time Horizons | 75% | 53.8% |
| Terminal-Bench | 63.1% | — |
| Berkeley Function Calling Leaderboard | 77.5% | — |
| GDPval | 45.5% | — |
| Remote Labor Index | 3.8% | — |
| τ²-bench Airline | 84% | — |
| τ²-bench Banking | 24.7% | — |
| τ²-bench Retail | 79.6% | — |
| τ²-bench Telecom | 92.3% | — |
| Cybench | 82% | — |
| OSWorld | 66.3% | — |
| LMArena Search | 1180 | — |
| Vending-Bench 2 | 4,967 | — |

## Reasoning

- Claude Opus 4.5: 42.5 (#43)
- DeepSeek-R1: 18.7 (#253)

| Benchmark | Claude Opus 4.5 | DeepSeek-R1 |
|---|---|---|
| ARC-AGI-2 | 37.6% | 1.3% |
| SimpleBench | 62% | 40.8% |
| Kagi LLM Benchmark | 80.2% | 69.4% |
| ARC-AGI-1 | 80% | 21.2% |
| LMArena Hard Prompts | 1476 | 1415 |
| Epoch Capabilities Index | 150.1 | 141.3 |
| ForecastBench | 60.7 | 60 |
| NYT Connections (extended) | 52.5% | — |
| CritPt | — | 1.1% |
| Chess Puzzles | 12% | — |
| EnigmaEval | 11.9% | — |
| EBR-Bench | 14.3% | — |
| LiveBench Reasoning | — | 83.2% |
| Mystery Game Puzzles | 22% | — |
| DTBench | 89.9% | — |
| LiveBench Data Analysis | — | 69.8% |
| LMCA | 44.5% | — |
| LiveBench | — | 71.6% |

## Math

- Claude Opus 4.5: 38.5 (#85)
- DeepSeek-R1: 42.0 (#70)

| Benchmark | Claude Opus 4.5 | DeepSeek-R1 |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 86.1% | 66.4% |
| LMArena Math | 1463 | 1401 |
| FrontierMath (Tiers 1-3) | 34.4% | — |
| FrontierMath Tier 4 | 4.9% | — |
| ProofBench | 36% | — |
| Omni-MATH | — | 42.4% |
| LiveBench Math | — | 80.7% |
| MATH Level 5 | — | 96.6% |
| FrontierMath (Feb 2025 set) | 20.7% | — |
| FrontierMath Tier 4 (v1) | 4.2% | — |

## Knowledge

- Claude Opus 4.5: 56.4 (#38)
- DeepSeek-R1: 44.3 (#81)

| Benchmark | Claude Opus 4.5 | DeepSeek-R1 |
|---|---|---|
| GPQA Diamond | 86% | 76.3% |
| Vectara Hallucination Rate | 10.9% | 11.3% |
| LMArena Expert | 1488 | 1394 |
| Humanity's Last Exam | 25.2% | — |
| SimpleQA Verified | 45.7% | — |
| MMLU-Pro | — | 79.3% |
| Confabulations | — | 12.7% |
| GPQA (HELM) | — | 66.6% |

## Multimodal

- Claude Opus 4.5: 31.1 (#99)
- DeepSeek-R1: —

| Benchmark | Claude Opus 4.5 | DeepSeek-R1 |
|---|---|---|
| GeoBench | 75% | — |
| VPCT | 40% | — |
| Furniture Assembly | 28.3% | — |
| LMArena Document | 1462 | — |

## Multilingual

- Claude Opus 4.5: 54.5 (#45)
- DeepSeek-R1: 52.6 (#80)

| Benchmark | Claude Opus 4.5 | DeepSeek-R1 |
|---|---|---|
| LMArena Non-English | 1438 | 1412 |
| LMArena Chinese | 1470 | 1443 |
| LMArena French | 1471 | 1415 |
| LMArena German | 1449 | 1405 |
| LMArena Japanese | 1415 | 1394 |
| LMArena Korean | 1424 | 1359 |
| LMArena Russian | 1448 | 1423 |
| LMArena Spanish | 1455 | 1410 |

## Instruction Following

- Claude Opus 4.5: 77.7 (#20)
- DeepSeek-R1: 72.2 (#138)

| Benchmark | Claude Opus 4.5 | DeepSeek-R1 |
|---|---|---|
| LMArena Instruction Following | 1478 | 1382 |
| LiveBench Instruction Following | — | 80.5% |
| IFEval | — | 78.4% |

## Long Context

- Claude Opus 4.5: 46.4 (#21)
- DeepSeek-R1: 45.4 (#36)

| Benchmark | Claude Opus 4.5 | DeepSeek-R1 |
|---|---|---|
| LMArena Longer Query | 1480 | 1391 |
| Fiction.LiveBench | — | 75% |
| CL-bench | 21.1% | — |

## Writing & Preference

- Claude Opus 4.5: 68.2 (#28)
- DeepSeek-R1: 61.5 (#84)

| Benchmark | Claude Opus 4.5 | DeepSeek-R1 |
|---|---|---|
| LMArena Text | 1451 | 1428 |
| LMArena Creative Writing | 1445 | 1406 |
| EQ-Bench Creative Writing | 1687 | 1500 |
| LMArena Multi-Turn | 1466 | 1404 |
| Short-Story Creative Writing | — | 83% |
| WildBench | — | 82.8% |
| LiveBench Language | — | 48.5% |

## FAQ

### Is Claude Opus 4.5 better than DeepSeek-R1?

Claude Opus 4.5 is the stronger model overall, scoring 50.5 to 42.0 on the Noometry Index. DeepSeek-R1 costs 11× less per token, which makes it the better buy when Claude Opus 4.5's lead doesn't matter for your workload.

### Which is cheaper, Claude Opus 4.5 or DeepSeek-R1?

DeepSeek-R1 is cheaper. It lists at $0.50 per million input tokens and $2.15 per million output tokens; Claude Opus 4.5 lists at $5 and $25.

### Is Claude Opus 4.5 or DeepSeek-R1 better for coding?

Claude Opus 4.5 scores higher on coding benchmarks: 55.4 versus 45.9 in the Noometry coding category.

### Which has the bigger context window?

Claude Opus 4.5 does, with 200K tokens against 164K.

### How many benchmarks do Claude Opus 4.5 and DeepSeek-R1 share?

33 benchmarks have published results for both models. Claude Opus 4.5 has 69 scored results on Noometry and DeepSeek-R1 has 52.