# Claude Opus 4 vs GPT-4

> Claude Opus 4 is the stronger model overall, scoring 43.1 to 29.1 on the Noometry Index.

- Canonical page: https://noometry.com/compare/claude-opus-4-vs-gpt-4
- Last updated: 2026-10-11
- Shared benchmarks: 27

## Summary

- They share 27 benchmarks with published results for both. Claude Opus 4 scores higher in 8 categories and GPT-4 in 0 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in math, where Claude Opus 4 leads 42.0 to 10.8.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 64.4% for Claude Opus 4 and 1.1% for GPT-4.
- Claude Opus 4 is cheaper at $15 / $75 per million input/output tokens, against $30 / $60 for GPT-4.
- Claude Opus 4 accepts more context: 200K tokens versus 8K.

## Snapshot

| | Claude Opus 4 | GPT-4 |
|---|---|---|
| Provider | Anthropic | OpenAI |
| Noometry Index | 43.1 | 29.1 |
| Rank | 100 | 316 |
| Context | 200K | 8K |
| Input $/M | $15 | $30 |
| Output $/M | $75 | $60 |
| Weights | Proprietary | Proprietary |

## Coding

- Claude Opus 4: 47.2 (#62)
- GPT-4: 31.6 (#283)

| Benchmark | Claude Opus 4 | GPT-4 |
|---|---|---|
| WeirdML | 43.7% | 12.4% |
| LMArena Coding | 1442 | 1254 |
| SWE-bench Verified | 70.7% | — |
| SWE-bench Verified (bash only) | 67.6% | — |
| Aider Polyglot | 72% | — |
| GSO | 6.9% | — |
| BigCodeBench Instruct | — | 46% |
| BigCodeBench Complete | — | 57.2% |
| AlgoTune | 1.33 | — |
| HumanEval+ | — | 79.3% |

## Agentic & Tool Use

- Claude Opus 4: 34.8 (#42)
- GPT-4: —

| Benchmark | Claude Opus 4 | GPT-4 |
|---|---|---|
| METR Time Horizons | 63.9% | 36.1% |
| Cybench | 38% | — |
| DeepResearch Bench | 46.8% | — |
| LMArena Search | 1127 | — |

## Reasoning

- Claude Opus 4: 27.3 (#121)
- GPT-4: 17.8 (#289)

| Benchmark | Claude Opus 4 | GPT-4 |
|---|---|---|
| LMArena Hard Prompts | 1399 | 1241 |
| DTBench | 81.6% | 62.7% |
| LMCA | 37.4% | 17.1% |
| Epoch Capabilities Index | 142.67 | 125.89 |
| ForecastBench | 61.1 | 57.8 |
| ARC-AGI-2 | 8.6% | — |
| SimpleBench | 58.8% | — |
| Kagi LLM Benchmark | 74.3% | — |
| ARC-AGI-1 | 35.7% | — |
| CritPt | 0.3% | — |
| Chess Puzzles | — | 4% |
| EnigmaEval | 5.6% | — |
| Mystery Game Puzzles | — | 12% |
| BIG-Bench Hard | — | 75.1% |
| HellaSwag | — | 95.3% |
| WinoGrande | — | 87.5% |

## Math

- Claude Opus 4: 42.0 (#86)
- GPT-4: 10.8 (#309)

| Benchmark | Claude Opus 4 | GPT-4 |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 64.4% | 1.1% |
| LMArena Math | 1390 | 1269 |
| MATH Level 5 | 85% | 23% |
| Omni-MATH | 61.6% | — |
| FrontierMath (Feb 2025 set) | 4.5% | — |
| FrontierMath Tier 4 (v1) | 4.2% | — |
| GSM8K | — | 92% |

## Knowledge

- Claude Opus 4: 44.0 (#88)
- GPT-4: 18.4 (#282)

| Benchmark | Claude Opus 4 | GPT-4 |
|---|---|---|
| GPQA Diamond | 76.3% | 35.7% |
| LMArena Expert | 1386 | 1211 |
| Humanity's Last Exam | 10.7% | — |
| MMLU-Pro | 87.5% | — |
| Confabulations | 15.9% | — |
| Vectara Hallucination Rate | 12% | — |
| GPQA (HELM) | 70.8% | — |
| MMLU | — | 86.4% |
| TriviaQA | — | 84.8% |

## Multimodal

- Claude Opus 4: 31.5 (#106)
- GPT-4: —

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

## Multilingual

- Claude Opus 4: 48.8 (#138)
- GPT-4: 40.6 (#215)

| Benchmark | Claude Opus 4 | GPT-4 |
|---|---|---|
| LMArena Non-English | 1362 | 1246 |
| LMArena Chinese | 1386 | 1242 |
| LMArena French | 1372 | 1283 |
| LMArena German | 1391 | 1251 |
| LMArena Japanese | 1331 | 1209 |
| LMArena Korean | 1321 | 1184 |
| LMArena Russian | 1392 | 1251 |
| LMArena Spanish | 1389 | 1261 |

## Instruction Following

- Claude Opus 4: 77.1 (#28)
- GPT-4: 65.3 (#222)

| Benchmark | Claude Opus 4 | GPT-4 |
|---|---|---|
| LMArena Instruction Following | 1406 | 1241 |
| IFEval | 91.8% | — |

## Long Context

- Claude Opus 4: 39.6 (#172)
- GPT-4: 37.7 (#212)

| Benchmark | Claude Opus 4 | GPT-4 |
|---|---|---|
| LMArena Longer Query | 1422 | 1244 |
| Fiction.LiveBench | 61.1% | — |

## Writing & Preference

- Claude Opus 4: 61.2 (#89)
- GPT-4: 34.9 (#268)

| Benchmark | Claude Opus 4 | GPT-4 |
|---|---|---|
| LMArena Text | 1377 | 1263 |
| LMArena Creative Writing | 1387 | 1244 |
| EQ-Bench Creative Writing | 1580 | 752 |
| LMArena Multi-Turn | 1396 | 1257 |
| Short-Story Creative Writing | 83.6% | — |
| WildBench | 85.2% | — |

## FAQ

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

Claude Opus 4 is the stronger model overall, scoring 43.1 to 29.1 on the Noometry Index.

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

Claude Opus 4 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 or GPT-4 better for coding?

Claude Opus 4 scores higher on coding benchmarks: 47.2 versus 31.6 in the Noometry coding category.

### Which has the bigger context window?

Claude Opus 4 does, with 200K tokens against 8K.

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

27 benchmarks have published results for both models. Claude Opus 4 has 56 scored results on Noometry and GPT-4 has 38.