# Claude 2 vs GPT-3.5-turbo

> Claude 2 is the stronger model overall, scoring 24.7 to 23.1 on the Noometry Index.

- Canonical page: https://noometry.com/compare/claude-2-vs-gpt-3-5-turbo
- Last updated: 2026-10-10
- Shared benchmarks: 8

## Summary

- They share 8 benchmarks with published results for both. Claude 2 scores higher in 3 categories and GPT-3.5-turbo in 0 categories; 3 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Claude 2 leads 20.8 to 13.3.
- The biggest single-benchmark swing is GPQA Diamond: 34.7% for Claude 2 and 28% for GPT-3.5-turbo.

## Snapshot

| | Claude 2 | GPT-3.5-turbo |
|---|---|---|
| Provider | Anthropic | OpenAI |
| Noometry Index | 24.7 | 23.1 |
| Rank | 342 | 345 |
| Context | — | 16K |
| Input $/M | — | $0.50 |
| Output $/M | — | $1.50 |
| Weights | Proprietary | Proprietary |

## Coding

- Claude 2: —
- GPT-3.5-turbo: 23.5 (#326)

| Benchmark | Claude 2 | GPT-3.5-turbo |
|---|---|---|
| HumanEval+ | 61.6% | 70.7% |
| WeirdML | — | 3.5% |
| BigCodeBench Instruct | — | 39.1% |
| LMArena Coding | — | 1137 |
| BigCodeBench Complete | — | 50.6% |
| MBPP+ | — | 69.7% |

## Agentic & Tool Use

- Claude 2: —
- GPT-3.5-turbo: —

| Benchmark | Claude 2 | GPT-3.5-turbo |
|---|---|---|
| METR Time Horizons | — | 21.5% |

## Reasoning

- Claude 2: 20.8 (#213)
- GPT-3.5-turbo: 13.3 (#328)

| Benchmark | Claude 2 | GPT-3.5-turbo |
|---|---|---|
| DTBench | 51.9% | 48.5% |
| Epoch Capabilities Index | 120.08 | 118.48 |
| Chess Puzzles | — | 0% |
| LMArena Hard Prompts | — | 1108 |
| Mystery Game Puzzles | — | 3% |
| LMCA | — | 9.7% |
| Adversarial NLI | — | 58.1% |
| BIG-Bench Hard | — | 61.6% |
| CommonsenseQA 2.0 | — | 57% |
| ForecastBench | — | 50.4 |
| WinoGrande | — | 81.6% |

## Math

- Claude 2: 8.7 (#314)
- GPT-3.5-turbo: 6.0 (#321)

| Benchmark | Claude 2 | GPT-3.5-turbo |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 2.5% | 2.2% |
| MATH Level 5 | 11.7% | 15.9% |
| FrontierMath (Tiers 1-3) | — | 0% |
| LMArena Math | — | 1142 |
| GSM8K | — | 57.8% |

## Knowledge

- Claude 2: 17.0 (#282)
- GPT-3.5-turbo: 10.0 (#298)

| Benchmark | Claude 2 | GPT-3.5-turbo |
|---|---|---|
| GPQA Diamond | 34.7% | 28% |
| MMLU | 78.5% | 71.4% |
| TriviaQA | 87.5% | 85.8% |
| LMArena Expert | — | 1070 |
| ARC (AI2) Challenge | — | 87.4% |
| BoolQ | — | 87% |
| OpenBookQA | — | 86% |

## Multilingual

- Claude 2: —
- GPT-3.5-turbo: 31.6 (#253)

| Benchmark | Claude 2 | GPT-3.5-turbo |
|---|---|---|
| LMArena Non-English | — | 1108 |
| LMArena Chinese | — | 1075 |
| LMArena French | — | 1117 |
| LMArena German | — | 1090 |
| LMArena Japanese | — | 1043 |
| LMArena Korean | — | 1019 |
| LMArena Russian | — | 1123 |
| LMArena Spanish | — | 1120 |

## Instruction Following

- Claude 2: —
- GPT-3.5-turbo: 58.1 (#257)

| Benchmark | Claude 2 | GPT-3.5-turbo |
|---|---|---|
| LMArena Instruction Following | — | 1119 |

## Long Context

- Claude 2: —
- GPT-3.5-turbo: 34.0 (#249)

| Benchmark | Claude 2 | GPT-3.5-turbo |
|---|---|---|
| LMArena Longer Query | — | 1121 |

## Writing & Preference

- Claude 2: —
- GPT-3.5-turbo: 25.4 (#300)

| Benchmark | Claude 2 | GPT-3.5-turbo |
|---|---|---|
| LMArena Text | — | 1125 |
| LMArena Creative Writing | — | 1092 |
| EQ-Bench Creative Writing | — | 451 |
| LMArena Multi-Turn | — | 1117 |

## FAQ

### Is Claude 2 better than GPT-3.5-turbo?

Claude 2 is the stronger model overall, scoring 24.7 to 23.1 on the Noometry Index.

### How many benchmarks do Claude 2 and GPT-3.5-turbo share?

8 benchmarks have published results for both models. Claude 2 has 8 scored results on Noometry and GPT-3.5-turbo has 44.