# Claude Opus 4 vs Claude Opus 4.1

> Claude Opus 4 is the stronger model overall, scoring 42.9 to 40.8 on the Noometry Index.

- Canonical page: https://noometry.com/compare/claude-opus-4-vs-claude-opus-4-1
- Last updated: 2026-10-10
- Shared benchmarks: 39

## Summary

- They share 39 benchmarks with published results for both. Claude Opus 4 scores higher in 5 categories and Claude Opus 4.1 in 5 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in math, where Claude Opus 4 leads 40.2 to 22.0.
- Both cost about the same: $15 input and $75 output per million tokens.

## Snapshot

| | Claude Opus 4 | Claude Opus 4.1 |
|---|---|---|
| Provider | Anthropic | Anthropic |
| Noometry Index | 42.9 | 40.8 |
| Rank | 93 | 136 |
| Context | 200K | 200K |
| Input $/M | $15 | $15 |
| Output $/M | $75 | $75 |
| Weights | Proprietary | Proprietary |

## Coding

- Claude Opus 4: 47.8 (#55)
- Claude Opus 4.1: 44.3 (#69)

| Benchmark | Claude Opus 4 | Claude Opus 4.1 |
|---|---|---|
| SWE-bench Verified | 70.7% | 73.3% |
| WeirdML | 43.7% | 45.9% |
| LMArena Coding | 1442 | 1479 |
| AlgoTune | 1.33 | 1.34 |
| SWE-bench Verified (bash only) | 67.6% | — |
| Aider Polyglot | 72% | — |
| LMArena WebDev | — | 1390 |
| GSO | 6.9% | — |
| ALE-Bench | — | 674.77 |

## Agentic & Tool Use

- Claude Opus 4: 34.5 (#39)
- Claude Opus 4.1: 34.8 (#38)

| Benchmark | Claude Opus 4 | Claude Opus 4.1 |
|---|---|---|
| Cybench | 38% | 42% |
| DeepResearch Bench | 46.8% | 48.3% |
| LMArena Search | 1127 | 1148 |
| METR Time Horizons | 63.9% | 66.8% |
| Terminal-Bench | — | 38% |
| GDPval | — | 43.6% |

## Reasoning

- Claude Opus 4: 27.4 (#104)
- Claude Opus 4.1: 31.6 (#70)

| Benchmark | Claude Opus 4 | Claude Opus 4.1 |
|---|---|---|
| SimpleBench | 58.8% | 60% |
| EnigmaEval | 5.6% | 7.2% |
| LMArena Hard Prompts | 1399 | 1443 |
| DTBench | 81.6% | 80% |
| LMCA | 37.4% | 37.1% |
| Epoch Capabilities Index | 142.67 | 144.11 |
| ForecastBench | 61.1 | 62 |
| ARC-AGI-2 | 8.6% | — |
| Kagi LLM Benchmark | 74.3% | — |
| ARC-AGI-1 | 35.7% | — |
| CritPt | 0.3% | — |
| Chess Puzzles | — | 7% |
| EBR-Bench | — | 7.9% |
| Mystery Game Puzzles | — | 21% |

## Math

- Claude Opus 4: 40.2 (#80)
- Claude Opus 4.1: 22.0 (#267)

| Benchmark | Claude Opus 4 | Claude Opus 4.1 |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 64.4% | 68.9% |
| LMArena Math | 1391 | 1430 |
| FrontierMath (Feb 2025 set) | 4.5% | 7.2% |
| FrontierMath Tier 4 (v1) | 4.2% | 4.2% |
| FrontierMath (Tiers 1-3) | — | 12.6% |
| FrontierMath Tier 4 | — | 2.4% |
| Omni-MATH | 61.6% | — |
| MATH Level 5 | 85% | — |

## Knowledge

- Claude Opus 4: 43.9 (#82)
- Claude Opus 4.1: 41.9 (#93)

| Benchmark | Claude Opus 4 | Claude Opus 4.1 |
|---|---|---|
| GPQA Diamond | 76.3% | 77.3% |
| Humanity's Last Exam | 10.7% | 11.5% |
| Confabulations | 15.9% | 17.1% |
| Vectara Hallucination Rate | 12% | 11.8% |
| LMArena Expert | 1384 | 1439 |
| MMLU-Pro | 87.5% | — |
| GPQA (HELM) | 70.8% | — |

## Multimodal

- Claude Opus 4: 30.9 (#101)
- Claude Opus 4.1: 26.2 (#114)

| Benchmark | Claude Opus 4 | Claude Opus 4.1 |
|---|---|---|
| VPCT | 38% | 35% |
| LMArena Vision | 1192 | — |
| GeoBench | 49% | — |

## Multilingual

- Claude Opus 4: 49.0 (#133)
- Claude Opus 4.1: 52.1 (#90)

| Benchmark | Claude Opus 4 | Claude Opus 4.1 |
|---|---|---|
| LMArena Non-English | 1362 | 1405 |
| LMArena Chinese | 1386 | 1427 |
| LMArena French | 1370 | 1432 |
| LMArena German | 1391 | 1412 |
| LMArena Japanese | 1332 | 1378 |
| LMArena Korean | 1318 | 1381 |
| LMArena Russian | 1392 | 1421 |
| LMArena Spanish | 1388 | 1448 |

## Instruction Following

- Claude Opus 4: 77.3 (#26)
- Claude Opus 4.1: 75.8 (#53)

| Benchmark | Claude Opus 4 | Claude Opus 4.1 |
|---|---|---|
| LMArena Instruction Following | 1406 | 1436 |
| IFEval | 91.8% | — |

## Long Context

- Claude Opus 4: 39.5 (#167)
- Claude Opus 4.1: 44.5 (#60)

| Benchmark | Claude Opus 4 | Claude Opus 4.1 |
|---|---|---|
| LMArena Longer Query | 1422 | 1455 |
| Fiction.LiveBench | 61.1% | — |

## Writing & Preference

- Claude Opus 4: 61.4 (#85)
- Claude Opus 4.1: 62.6 (#70)

| Benchmark | Claude Opus 4 | Claude Opus 4.1 |
|---|---|---|
| LMArena Text | 1377 | 1419 |
| LMArena Creative Writing | 1386 | 1412 |
| Short-Story Creative Writing | 83.6% | 84.7% |
| LMArena Multi-Turn | 1396 | 1444 |
| EQ-Bench Creative Writing | 1580 | — |
| WildBench | 85.2% | — |

## FAQ

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

Claude Opus 4 is the stronger model overall, scoring 42.9 to 40.8 on the Noometry Index.

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

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

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

Claude Opus 4 scores higher on coding benchmarks: 47.8 versus 44.3 in the Noometry coding category.

### Which has the bigger context window?

Both accept 200K tokens.

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

39 benchmarks have published results for both models. Claude Opus 4 has 56 scored results on Noometry and Claude Opus 4.1 has 48.