# Claude Opus 4.1 vs GPT-4

> Claude Opus 4.1 is the stronger model overall, scoring 41.0 to 29.1 on the Noometry Index.

- Canonical page: https://noometry.com/compare/claude-opus-4-1-vs-gpt-4
- Last updated: 2026-10-10
- Shared benchmarks: 27

## Summary

- They share 27 benchmarks with published results for both. Claude Opus 4.1 scores higher in 8 categories and GPT-4 in 0 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Claude Opus 4.1 leads 62.4 to 34.9.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 68.9% for Claude Opus 4.1 and 1.1% for GPT-4.
- Claude Opus 4.1 is cheaper at $15 / $75 per million input/output tokens, against $30 / $60 for GPT-4.
- Claude Opus 4.1 accepts more context: 200K tokens versus 8K.

## Snapshot

| | Claude Opus 4.1 | GPT-4 |
|---|---|---|
| Provider | Anthropic | OpenAI |
| Noometry Index | 41.0 | 29.1 |
| Rank | 142 | 316 |
| Context | 200K | 8K |
| Input $/M | $15 | $30 |
| Output $/M | $75 | $60 |
| Weights | Proprietary | Proprietary |

## Coding

- Claude Opus 4.1: 44.4 (#73)
- GPT-4: 31.6 (#283)

| Benchmark | Claude Opus 4.1 | GPT-4 |
|---|---|---|
| WeirdML | 45.9% | 12.4% |
| LMArena Coding | 1479 | 1254 |
| SWE-bench Verified | 73.3% | — |
| LMArena WebDev | 1390 | — |
| BigCodeBench Instruct | — | 46% |
| BigCodeBench Complete | — | 57.2% |
| ALE-Bench | 674.77 | — |
| AlgoTune | 1.34 | — |
| HumanEval+ | — | 79.3% |

## Agentic & Tool Use

- Claude Opus 4.1: 35.0 (#41)
- GPT-4: —

| Benchmark | Claude Opus 4.1 | GPT-4 |
|---|---|---|
| METR Time Horizons | 66.8% | 36.1% |
| Terminal-Bench | 38% | — |
| GDPval | 43.6% | — |
| Cybench | 42% | — |
| DeepResearch Bench | 48.3% | — |
| LMArena Search | 1148 | — |

## Reasoning

- Claude Opus 4.1: 32.2 (#76)
- GPT-4: 17.8 (#289)

| Benchmark | Claude Opus 4.1 | GPT-4 |
|---|---|---|
| Chess Puzzles | 7% | 4% |
| LMArena Hard Prompts | 1443 | 1241 |
| Mystery Game Puzzles | 21% | 12% |
| DTBench | 80% | 62.7% |
| LMCA | 37.1% | 17.1% |
| Epoch Capabilities Index | 144.12 | 125.89 |
| ForecastBench | 62 | 57.8 |
| SimpleBench | 60% | — |
| EnigmaEval | 7.2% | — |
| EBR-Bench | 7.9% | — |
| BIG-Bench Hard | — | 75.1% |
| HellaSwag | — | 95.3% |
| WinoGrande | — | 87.5% |

## Math

- Claude Opus 4.1: 22.3 (#277)
- GPT-4: 10.8 (#309)

| Benchmark | Claude Opus 4.1 | GPT-4 |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 68.9% | 1.1% |
| LMArena Math | 1431 | 1269 |
| FrontierMath (Tiers 1-3) | 12.6% | — |
| FrontierMath Tier 4 | 2.4% | — |
| MATH Level 5 | — | 23% |
| FrontierMath (Feb 2025 set) | 7.2% | — |
| FrontierMath Tier 4 (v1) | 4.2% | — |
| GSM8K | — | 92% |

## Knowledge

- Claude Opus 4.1: 42.0 (#101)
- GPT-4: 18.4 (#282)

| Benchmark | Claude Opus 4.1 | GPT-4 |
|---|---|---|
| GPQA Diamond | 77.3% | 35.7% |
| LMArena Expert | 1439 | 1211 |
| Humanity's Last Exam | 11.5% | — |
| Confabulations | 17.1% | — |
| Vectara Hallucination Rate | 11.8% | — |
| MMLU | — | 86.4% |
| TriviaQA | — | 84.8% |

## Multimodal

- Claude Opus 4.1: 26.8 (#119)
- GPT-4: —

| Benchmark | Claude Opus 4.1 | GPT-4 |
|---|---|---|
| VPCT | 35% | — |

## Multilingual

- Claude Opus 4.1: 52.0 (#95)
- GPT-4: 40.6 (#215)

| Benchmark | Claude Opus 4.1 | GPT-4 |
|---|---|---|
| LMArena Non-English | 1405 | 1246 |
| LMArena Chinese | 1427 | 1242 |
| LMArena French | 1431 | 1283 |
| LMArena German | 1413 | 1251 |
| LMArena Japanese | 1378 | 1209 |
| LMArena Korean | 1380 | 1184 |
| LMArena Russian | 1422 | 1251 |
| LMArena Spanish | 1448 | 1261 |

## Instruction Following

- Claude Opus 4.1: 75.6 (#58)
- GPT-4: 65.3 (#222)

| Benchmark | Claude Opus 4.1 | GPT-4 |
|---|---|---|
| LMArena Instruction Following | 1435 | 1241 |

## Long Context

- Claude Opus 4.1: 44.5 (#63)
- GPT-4: 37.7 (#212)

| Benchmark | Claude Opus 4.1 | GPT-4 |
|---|---|---|
| LMArena Longer Query | 1455 | 1244 |

## Writing & Preference

- Claude Opus 4.1: 62.4 (#74)
- GPT-4: 34.9 (#268)

| Benchmark | Claude Opus 4.1 | GPT-4 |
|---|---|---|
| LMArena Text | 1419 | 1263 |
| LMArena Creative Writing | 1412 | 1244 |
| LMArena Multi-Turn | 1444 | 1257 |
| Short-Story Creative Writing | 84.7% | — |
| EQ-Bench Creative Writing | — | 752 |

## FAQ

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

Claude Opus 4.1 is the stronger model overall, scoring 41.0 to 29.1 on the Noometry Index.

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

Claude Opus 4.1 is cheaper. It lists at $15 per million input tokens and $75 per million output tokens; GPT-4 lists at $30 and $60.

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

Claude Opus 4.1 scores higher on coding benchmarks: 44.4 versus 31.6 in the Noometry coding category.

### Which has the bigger context window?

Claude Opus 4.1 does, with 200K tokens against 8K.

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

27 benchmarks have published results for both models. Claude Opus 4.1 has 48 scored results on Noometry and GPT-4 has 38.