# Claude 2 vs GPT-4 Turbo

> GPT-4 Turbo is the stronger model overall, scoring 30.3 to 24.7 on the Noometry Index.

- Canonical page: https://noometry.com/compare/claude-2-vs-gpt-4-turbo
- Last updated: 2026-10-10
- Shared benchmarks: 7

## Summary

- They share 7 benchmarks with published results for both. Claude 2 scores higher in 2 categories and GPT-4 Turbo in 1 category; 2 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where GPT-4 Turbo leads 24.3 to 17.0.
- The biggest single-benchmark swing is MATH Level 5: 11.7% for Claude 2 and 46.7% for GPT-4 Turbo.

## Snapshot

| | Claude 2 | GPT-4 Turbo |
|---|---|---|
| Provider | Anthropic | OpenAI |
| Noometry Index | 24.7 | 30.3 |
| Rank | 342 | 281 |
| Context | — | 128K |
| Input $/M | — | $10 |
| Output $/M | — | $30 |
| Weights | Proprietary | Proprietary |

## Coding

- Claude 2: —
- GPT-4 Turbo: 33.4 (#247)

| Benchmark | Claude 2 | GPT-4 Turbo |
|---|---|---|
| HumanEval+ | 61.6% | 86.6% |
| WeirdML | — | 18% |
| BigCodeBench Instruct | — | 48.2% |
| LMArena Coding | — | 1268 |
| BigCodeBench Complete | — | 58.2% |
| MBPP+ | — | 73.3% |

## Agentic & Tool Use

- Claude 2: —
- GPT-4 Turbo: —

| Benchmark | Claude 2 | GPT-4 Turbo |
|---|---|---|
| METR Time Horizons | — | 36.7% |

## Reasoning

- Claude 2: 20.8 (#213)
- GPT-4 Turbo: 14.9 (#311)

| Benchmark | Claude 2 | GPT-4 Turbo |
|---|---|---|
| DTBench | 51.9% | 61.6% |
| Epoch Capabilities Index | 120.08 | 127.25 |
| SimpleBench | — | 25.1% |
| Chess Puzzles | — | 6% |
| LMArena Hard Prompts | — | 1251 |
| LMCA | — | 9.8% |
| ForecastBench | — | 59.4 |

## Math

- Claude 2: 8.7 (#314)
- GPT-4 Turbo: 8.6 (#316)

| Benchmark | Claude 2 | GPT-4 Turbo |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 2.5% | 6.7% |
| MATH Level 5 | 11.7% | 46.7% |
| FrontierMath (Tiers 1-3) | — | 0.7% |
| LMArena Math | — | 1272 |

## Knowledge

- Claude 2: 17.0 (#282)
- GPT-4 Turbo: 24.3 (#263)

| Benchmark | Claude 2 | GPT-4 Turbo |
|---|---|---|
| GPQA Diamond | 34.7% | 46.6% |
| MMLU | 78.5% | 81.3% |
| Confabulations | — | 28.4% |
| LMArena Expert | — | 1223 |
| TriviaQA | 87.5% | — |

## Multimodal

- Claude 2: —
- GPT-4 Turbo: 30.0 (#104)

| Benchmark | Claude 2 | GPT-4 Turbo |
|---|---|---|
| LMArena Vision | — | 1090 |

## Multilingual

- Claude 2: —
- GPT-4 Turbo: 40.7 (#211)

| Benchmark | Claude 2 | GPT-4 Turbo |
|---|---|---|
| LMArena Non-English | — | 1245 |
| LMArena Chinese | — | 1242 |
| LMArena French | — | 1275 |
| LMArena German | — | 1259 |
| LMArena Japanese | — | 1194 |
| LMArena Korean | — | 1187 |
| LMArena Russian | — | 1259 |
| LMArena Spanish | — | 1260 |

## Instruction Following

- Claude 2: —
- GPT-4 Turbo: 66.0 (#211)

| Benchmark | Claude 2 | GPT-4 Turbo |
|---|---|---|
| LMArena Instruction Following | — | 1250 |

## Long Context

- Claude 2: —
- GPT-4 Turbo: 38.0 (#200)

| Benchmark | Claude 2 | GPT-4 Turbo |
|---|---|---|
| LMArena Longer Query | — | 1254 |

## Writing & Preference

- Claude 2: —
- GPT-4 Turbo: 47.9 (#201)

| Benchmark | Claude 2 | GPT-4 Turbo |
|---|---|---|
| LMArena Text | — | 1272 |
| LMArena Creative Writing | — | 1269 |
| LMArena Multi-Turn | — | 1267 |

## FAQ

### Is Claude 2 better than GPT-4 Turbo?

GPT-4 Turbo is the stronger model overall, scoring 30.3 to 24.7 on the Noometry Index.

### How many benchmarks do Claude 2 and GPT-4 Turbo share?

7 benchmarks have published results for both models. Claude 2 has 8 scored results on Noometry and GPT-4 Turbo has 36.