# Claude 3 Opus vs GPT-4 Turbo

> Claude 3 Opus and GPT-4 Turbo score almost the same on the Noometry Index (29.5 vs 30.5), so choose on price, context window or the category you care about most.

- Canonical page: https://noometry.com/compare/claude-3-opus-vs-gpt-4-turbo
- Last updated: 2026-10-12
- Shared benchmarks: 35

## Summary

- They share 35 benchmarks with published results for both. Claude 3 Opus scores higher in 4 categories and GPT-4 Turbo in 5 categories; 3 gaps are clear of the uncertainty.
- The widest gap is in math, where Claude 3 Opus leads 14.8 to 9.0.
- The biggest single-benchmark swing is MATH Level 5: 37.5% for Claude 3 Opus and 46.7% for GPT-4 Turbo.

## Snapshot

| | Claude 3 Opus | GPT-4 Turbo |
|---|---|---|
| Provider | Anthropic | OpenAI |
| Noometry Index | 29.5 | 30.5 |
| Rank | 310 | 292 |
| Context | — | 128K |
| Input $/M | — | $10 |
| Output $/M | — | $30 |
| Weights | Proprietary | Proprietary |

## Coding

- Claude 3 Opus: 32.9 (#267)
- GPT-4 Turbo: 33.8 (#249)

| Benchmark | Claude 3 Opus | GPT-4 Turbo |
|---|---|---|
| WeirdML | 19.2% | 18% |
| BigCodeBench Instruct | 45.5% | 48.2% |
| LMArena Coding | 1264 | 1268 |
| BigCodeBench Complete | 57.4% | 58.2% |
| HumanEval+ | 77.4% | 86.6% |
| MBPP+ | 73.3% | 73.3% |
| LiveBench Coding | 38.6% | — |

## Agentic & Tool Use

- Claude 3 Opus: 24.6 (#116)
- GPT-4 Turbo: —

| Benchmark | Claude 3 Opus | GPT-4 Turbo |
|---|---|---|
| METR Time Horizons | 29.5% | 36.7% |
| Cybench | 10% | — |

## Reasoning

- Claude 3 Opus: 14.6 (#324)
- GPT-4 Turbo: 15.3 (#317)

| Benchmark | Claude 3 Opus | GPT-4 Turbo |
|---|---|---|
| SimpleBench | 23.5% | 25.1% |
| Chess Puzzles | 5% | 6% |
| LMArena Hard Prompts | 1245 | 1251 |
| DTBench | 61.6% | 61.6% |
| LMCA | 17% | 9.8% |
| Epoch Capabilities Index | 126.91 | 127.25 |
| ForecastBench | 58.4 | 59.4 |
| EnigmaEval | 0.8% | — |
| LiveBench Reasoning | 40.6% | — |
| LiveBench Data Analysis | 57.9% | — |
| LiveBench | 49.2% | — |
| WinoGrande | 88.5% | — |

## Math

- Claude 3 Opus: 14.8 (#299)
- GPT-4 Turbo: 9.0 (#322)

| Benchmark | Claude 3 Opus | GPT-4 Turbo |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 4.7% | 6.7% |
| LMArena Math | 1273 | 1272 |
| MATH Level 5 | 37.5% | 46.7% |
| FrontierMath (Tiers 1-3) | — | 0.7% |
| LiveBench Math | 43.6% | — |

## Knowledge

- Claude 3 Opus: 24.5 (#267)
- GPT-4 Turbo: 24.3 (#268)

| Benchmark | Claude 3 Opus | GPT-4 Turbo |
|---|---|---|
| GPQA Diamond | 47.2% | 46.6% |
| Confabulations | 22.7% | 28.4% |
| LMArena Expert | 1223 | 1223 |
| MMLU | 84.6% | 81.3% |
| SimpleQA Verified | 12.6% | — |

## Multimodal

- Claude 3 Opus: 27.1 (#116)
- GPT-4 Turbo: 30.6 (#110)

| Benchmark | Claude 3 Opus | GPT-4 Turbo |
|---|---|---|
| LMArena Vision | 1023 | 1090 |

## Multilingual

- Claude 3 Opus: 41.4 (#207)
- GPT-4 Turbo: 40.5 (#216)

| Benchmark | Claude 3 Opus | GPT-4 Turbo |
|---|---|---|
| LMArena Non-English | 1258 | 1245 |
| LMArena Chinese | 1248 | 1242 |
| LMArena French | 1275 | 1276 |
| LMArena German | 1258 | 1259 |
| LMArena Japanese | 1204 | 1194 |
| LMArena Korean | 1187 | 1187 |
| LMArena Russian | 1280 | 1259 |
| LMArena Spanish | 1246 | 1260 |

## Instruction Following

- Claude 3 Opus: 64.1 (#228)
- GPT-4 Turbo: 65.8 (#216)

| Benchmark | Claude 3 Opus | GPT-4 Turbo |
|---|---|---|
| LMArena Instruction Following | 1248 | 1249 |
| LiveBench Instruction Following | 63.9% | — |

## Long Context

- Claude 3 Opus: 38.2 (#202)
- GPT-4 Turbo: 38.0 (#206)

| Benchmark | Claude 3 Opus | GPT-4 Turbo |
|---|---|---|
| LMArena Longer Query | 1259 | 1254 |

## Writing & Preference

- Claude 3 Opus: 47.2 (#213)
- GPT-4 Turbo: 47.7 (#206)

| Benchmark | Claude 3 Opus | GPT-4 Turbo |
|---|---|---|
| LMArena Text | 1262 | 1272 |
| LMArena Creative Writing | 1235 | 1269 |
| LMArena Multi-Turn | 1275 | 1267 |
| LiveBench Language | 50.4% | — |

## FAQ

### Is Claude 3 Opus better than GPT-4 Turbo?

Claude 3 Opus and GPT-4 Turbo score almost the same on the Noometry Index (29.5 vs 30.5), so choose on price, context window or the category you care about most.

### Is Claude 3 Opus or GPT-4 Turbo better for coding?

They score almost the same on coding (32.9 vs 33.8); test both on your own repository before choosing.

### How many benchmarks do Claude 3 Opus and GPT-4 Turbo share?

35 benchmarks have published results for both models. Claude 3 Opus has 46 scored results on Noometry and GPT-4 Turbo has 36.