# Claude Opus 4.1 vs Claude Sonnet 4

> Claude Opus 4.1 and Claude Sonnet 4 score almost the same on the Noometry Index (40.8 vs 40.6), so choose on price, context window or the category you care about most.

- Canonical page: https://noometry.com/compare/claude-opus-4-1-vs-claude-sonnet-4
- Last updated: 2026-10-10
- Shared benchmarks: 37

## Summary

- They share 37 benchmarks with published results for both. Claude Opus 4.1 scores higher in 8 categories and Claude Sonnet 4 in 2 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in math, where Claude Sonnet 4 leads 41.5 to 22.0.
- The biggest single-benchmark swing is SimpleBench: 60% for Claude Opus 4.1 and 45.5% for Claude Sonnet 4.
- Claude Sonnet 4 is cheaper at $3 / $15 per million input/output tokens, against $15 / $75 for Claude Opus 4.1.

## Snapshot

| | Claude Opus 4.1 | Claude Sonnet 4 |
|---|---|---|
| Provider | Anthropic | Anthropic |
| Noometry Index | 40.8 | 40.6 |
| Rank | 136 | 139 |
| Context | 200K | 200K |
| Input $/M | $15 | $3 |
| Output $/M | $75 | $15 |
| Weights | Proprietary | Proprietary |

## Coding

- Claude Opus 4.1: 44.3 (#69)
- Claude Sonnet 4: 44.0 (#70)

| Benchmark | Claude Opus 4.1 | Claude Sonnet 4 |
|---|---|---|
| WeirdML | 45.9% | 46.1% |
| LMArena Coding | 1479 | 1414 |
| ALE-Bench | 674.77 | 655.35 |
| SWE-bench Verified | 73.3% | — |
| SWE-bench Verified (bash only) | — | 64.9% |
| Aider Polyglot | — | 61.3% |
| LMArena WebDev | 1390 | — |
| SciCode | — | 40% |
| GSO | — | 4.9% |
| AlgoTune | 1.34 | — |

## Agentic & Tool Use

- Claude Opus 4.1: 34.8 (#38)
- Claude Sonnet 4: 38.3 (#29)

| Benchmark | Claude Opus 4.1 | Claude Sonnet 4 |
|---|---|---|
| Cybench | 42% | 35% |
| DeepResearch Bench | 48.3% | 46.6% |
| METR Time Horizons | 66.8% | 62% |
| Terminal-Bench | 38% | — |
| GDPval | 43.6% | — |
| TheAgentCompany | — | 33.1% |
| OSWorld | — | 43.9% |
| LMArena Search | 1148 | — |

## Reasoning

- Claude Opus 4.1: 31.6 (#70)
- Claude Sonnet 4: 23.0 (#169)

| Benchmark | Claude Opus 4.1 | Claude Sonnet 4 |
|---|---|---|
| SimpleBench | 60% | 45.5% |
| EnigmaEval | 7.2% | 3.1% |
| LMArena Hard Prompts | 1443 | 1372 |
| DTBench | 80% | 77.1% |
| LMCA | 37.1% | 29% |
| Epoch Capabilities Index | 144.11 | 141.69 |
| ForecastBench | 62 | 60.2 |
| ARC-AGI-2 | — | 5.9% |
| Kagi LLM Benchmark | — | 73% |
| ARC-AGI-1 | — | 40% |
| CritPt | — | 0.3% |
| Chess Puzzles | 7% | — |
| EBR-Bench | 7.9% | — |
| Mystery Game Puzzles | 21% | — |

## Math

- Claude Opus 4.1: 22.0 (#267)
- Claude Sonnet 4: 41.5 (#71)

| Benchmark | Claude Opus 4.1 | Claude Sonnet 4 |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 68.9% | 71.1% |
| LMArena Math | 1430 | 1375 |
| FrontierMath (Feb 2025 set) | 7.2% | 4.1% |
| FrontierMath Tier 4 (v1) | 4.2% | 0% |
| FrontierMath (Tiers 1-3) | 12.6% | — |
| FrontierMath Tier 4 | 2.4% | — |
| Omni-MATH | — | 60.2% |
| MATH Level 5 | — | 84.4% |

## Knowledge

- Claude Opus 4.1: 41.9 (#93)
- Claude Sonnet 4: 41.6 (#99)

| Benchmark | Claude Opus 4.1 | Claude Sonnet 4 |
|---|---|---|
| GPQA Diamond | 77.3% | 79.2% |
| Humanity's Last Exam | 11.5% | 7.8% |
| Confabulations | 17.1% | 13.2% |
| Vectara Hallucination Rate | 11.8% | 10.3% |
| LMArena Expert | 1439 | 1371 |
| MMLU-Pro | — | 84.3% |
| GPQA (HELM) | — | 70.6% |

## Multimodal

- Claude Opus 4.1: 26.2 (#114)
- Claude Sonnet 4: 25.6 (#116)

| Benchmark | Claude Opus 4.1 | Claude Sonnet 4 |
|---|---|---|
| VPCT | 35% | 34% |
| LMArena Vision | — | 1191 |
| GeoBench | — | 37% |
| MindCube | — | 44.8% |

## Multilingual

- Claude Opus 4.1: 52.1 (#90)
- Claude Sonnet 4: 46.9 (#151)

| Benchmark | Claude Opus 4.1 | Claude Sonnet 4 |
|---|---|---|
| LMArena Non-English | 1405 | 1333 |
| LMArena Chinese | 1427 | 1351 |
| LMArena French | 1432 | 1364 |
| LMArena German | 1412 | 1331 |
| LMArena Japanese | 1378 | 1301 |
| LMArena Korean | 1381 | 1293 |
| LMArena Russian | 1421 | 1355 |
| LMArena Spanish | 1448 | 1356 |

## Instruction Following

- Claude Opus 4.1: 75.8 (#53)
- Claude Sonnet 4: 71.8 (#141)

| Benchmark | Claude Opus 4.1 | Claude Sonnet 4 |
|---|---|---|
| LMArena Instruction Following | 1436 | 1375 |
| IFEval | — | 84% |

## Long Context

- Claude Opus 4.1: 44.5 (#60)
- Claude Sonnet 4: 33.6 (#254)

| Benchmark | Claude Opus 4.1 | Claude Sonnet 4 |
|---|---|---|
| LMArena Longer Query | 1455 | 1398 |
| Fiction.LiveBench | — | 46.9% |

## Writing & Preference

- Claude Opus 4.1: 62.6 (#70)
- Claude Sonnet 4: 57.3 (#127)

| Benchmark | Claude Opus 4.1 | Claude Sonnet 4 |
|---|---|---|
| LMArena Text | 1419 | 1351 |
| LMArena Creative Writing | 1412 | 1345 |
| Short-Story Creative Writing | 84.7% | 81.4% |
| LMArena Multi-Turn | 1444 | 1376 |
| EQ-Bench Creative Writing | — | 1483 |
| WildBench | — | 83.8% |

## FAQ

### Is Claude Opus 4.1 better than Claude Sonnet 4?

Claude Opus 4.1 and Claude Sonnet 4 score almost the same on the Noometry Index (40.8 vs 40.6), so choose on price, context window or the category you care about most.

### Which is cheaper, Claude Opus 4.1 or Claude Sonnet 4?

Claude Sonnet 4 is cheaper. It lists at $3 per million input tokens and $15 per million output tokens; Claude Opus 4.1 lists at $15 and $75.

### Is Claude Opus 4.1 or Claude Sonnet 4 better for coding?

They score almost the same on coding (44.3 vs 44.0); test both on your own repository before choosing.

### Which has the bigger context window?

Both accept 200K tokens.

### How many benchmarks do Claude Opus 4.1 and Claude Sonnet 4 share?

37 benchmarks have published results for both models. Claude Opus 4.1 has 48 scored results on Noometry and Claude Sonnet 4 has 58.