# Claude Opus 4.1 vs DeepSeek-R1

> DeepSeek-R1 is the stronger model overall, scoring 42.0 to 40.8 on the Noometry Index.

- Canonical page: https://noometry.com/compare/claude-opus-4-1-vs-deepseek-r1
- Last updated: 2026-10-10
- Shared benchmarks: 30

## Summary

- They share 30 benchmarks with published results for both. Claude Opus 4.1 scores higher in 4 categories and DeepSeek-R1 in 5 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in math, where DeepSeek-R1 leads 42.0 to 22.0.
- The biggest single-benchmark swing is SimpleBench: 60% for Claude Opus 4.1 and 40.8% for DeepSeek-R1.
- DeepSeek-R1 is cheaper at $0.50 / $2.15 per million input/output tokens, against $15 / $75 for Claude Opus 4.1.
- Claude Opus 4.1 accepts more context: 200K tokens versus 164K.

## Snapshot

| | Claude Opus 4.1 | DeepSeek-R1 |
|---|---|---|
| Provider | Anthropic | DeepSeek |
| Noometry Index | 40.8 | 42.0 |
| Rank | 136 | 110 |
| Context | 200K | 164K |
| Input $/M | $15 | $0.50 |
| Output $/M | $75 | $2.15 |
| Weights | Proprietary | Proprietary |

## Coding

- Claude Opus 4.1: 44.3 (#69)
- DeepSeek-R1: 45.9 (#63)

| Benchmark | Claude Opus 4.1 | DeepSeek-R1 |
|---|---|---|
| WeirdML | 45.9% | 41.6% |
| LMArena Coding | 1479 | 1427 |
| ALE-Bench | 674.77 | 804.12 |
| AlgoTune | 1.34 | 1.7 |
| SWE-bench Verified | 73.3% | — |
| Aider Polyglot | — | 71.4% |
| LMArena WebDev | 1390 | — |
| SciCode | — | 35.7% |
| LiveBench Coding | — | 66.7% |

## Agentic & Tool Use

- Claude Opus 4.1: 34.8 (#38)
- DeepSeek-R1: 30.4 (#68)

| Benchmark | Claude Opus 4.1 | DeepSeek-R1 |
|---|---|---|
| DeepResearch Bench | 48.3% | 35.1% |
| METR Time Horizons | 66.8% | 53.8% |
| Terminal-Bench | 38% | — |
| GDPval | 43.6% | — |
| Cybench | 42% | — |
| BALROG | — | 34.9% |
| LMArena Search | 1148 | — |

## Reasoning

- Claude Opus 4.1: 31.6 (#70)
- DeepSeek-R1: 18.7 (#253)

| Benchmark | Claude Opus 4.1 | DeepSeek-R1 |
|---|---|---|
| SimpleBench | 60% | 40.8% |
| LMArena Hard Prompts | 1443 | 1415 |
| Epoch Capabilities Index | 144.11 | 141.3 |
| ForecastBench | 62 | 60 |
| ARC-AGI-2 | — | 1.3% |
| Kagi LLM Benchmark | — | 69.4% |
| ARC-AGI-1 | — | 21.2% |
| CritPt | — | 1.1% |
| Chess Puzzles | 7% | — |
| EnigmaEval | 7.2% | — |
| EBR-Bench | 7.9% | — |
| LiveBench Reasoning | — | 83.2% |
| Mystery Game Puzzles | 21% | — |
| DTBench | 80% | — |
| LiveBench Data Analysis | — | 69.8% |
| LMCA | 37.1% | — |
| LiveBench | — | 71.6% |

## Math

- Claude Opus 4.1: 22.0 (#267)
- DeepSeek-R1: 42.0 (#70)

| Benchmark | Claude Opus 4.1 | DeepSeek-R1 |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 68.9% | 66.4% |
| LMArena Math | 1430 | 1401 |
| FrontierMath (Tiers 1-3) | 12.6% | — |
| FrontierMath Tier 4 | 2.4% | — |
| Omni-MATH | — | 42.4% |
| LiveBench Math | — | 80.7% |
| MATH Level 5 | — | 96.6% |
| FrontierMath (Feb 2025 set) | 7.2% | — |
| FrontierMath Tier 4 (v1) | 4.2% | — |

## Knowledge

- Claude Opus 4.1: 41.9 (#93)
- DeepSeek-R1: 44.3 (#81)

| Benchmark | Claude Opus 4.1 | DeepSeek-R1 |
|---|---|---|
| GPQA Diamond | 77.3% | 76.3% |
| Confabulations | 17.1% | 12.7% |
| Vectara Hallucination Rate | 11.8% | 11.3% |
| LMArena Expert | 1439 | 1394 |
| Humanity's Last Exam | 11.5% | — |
| MMLU-Pro | — | 79.3% |
| GPQA (HELM) | — | 66.6% |

## Multimodal

- Claude Opus 4.1: 26.2 (#114)
- DeepSeek-R1: —

| Benchmark | Claude Opus 4.1 | DeepSeek-R1 |
|---|---|---|
| VPCT | 35% | — |

## Multilingual

- Claude Opus 4.1: 52.1 (#90)
- DeepSeek-R1: 52.6 (#80)

| Benchmark | Claude Opus 4.1 | DeepSeek-R1 |
|---|---|---|
| LMArena Non-English | 1405 | 1412 |
| LMArena Chinese | 1427 | 1443 |
| LMArena French | 1432 | 1415 |
| LMArena German | 1412 | 1405 |
| LMArena Japanese | 1378 | 1394 |
| LMArena Korean | 1381 | 1359 |
| LMArena Russian | 1421 | 1423 |
| LMArena Spanish | 1448 | 1410 |

## Instruction Following

- Claude Opus 4.1: 75.8 (#53)
- DeepSeek-R1: 72.2 (#138)

| Benchmark | Claude Opus 4.1 | DeepSeek-R1 |
|---|---|---|
| LMArena Instruction Following | 1436 | 1382 |
| LiveBench Instruction Following | — | 80.5% |
| IFEval | — | 78.4% |

## Long Context

- Claude Opus 4.1: 44.5 (#60)
- DeepSeek-R1: 45.4 (#36)

| Benchmark | Claude Opus 4.1 | DeepSeek-R1 |
|---|---|---|
| LMArena Longer Query | 1455 | 1391 |
| Fiction.LiveBench | — | 75% |

## Writing & Preference

- Claude Opus 4.1: 62.6 (#70)
- DeepSeek-R1: 61.5 (#84)

| Benchmark | Claude Opus 4.1 | DeepSeek-R1 |
|---|---|---|
| LMArena Text | 1419 | 1428 |
| LMArena Creative Writing | 1412 | 1406 |
| Short-Story Creative Writing | 84.7% | 83% |
| LMArena Multi-Turn | 1444 | 1404 |
| EQ-Bench Creative Writing | — | 1500 |
| WildBench | — | 82.8% |
| LiveBench Language | — | 48.5% |

## FAQ

### Is Claude Opus 4.1 better than DeepSeek-R1?

DeepSeek-R1 is the stronger model overall, scoring 42.0 to 40.8 on the Noometry Index.

### Which is cheaper, Claude Opus 4.1 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 4.1 lists at $15 and $75.

### Is Claude Opus 4.1 or DeepSeek-R1 better for coding?

DeepSeek-R1 scores higher on coding benchmarks: 45.9 versus 44.3 in the Noometry coding category.

### Which has the bigger context window?

Claude Opus 4.1 does, with 200K tokens against 164K.

### How many benchmarks do Claude Opus 4.1 and DeepSeek-R1 share?

30 benchmarks have published results for both models. Claude Opus 4.1 has 48 scored results on Noometry and DeepSeek-R1 has 52.