# Claude 3 Sonnet vs GPT-4o mini

> Claude 3 Sonnet is the stronger model overall, scoring 28.8 to 25.4 on the Noometry Index.

- Canonical page: https://noometry.com/compare/claude-3-sonnet-vs-gpt-4o-mini
- Last updated: 2026-10-10
- Shared benchmarks: 29

## Summary

- They share 29 benchmarks with published results for both. Claude 3 Sonnet scores higher in 6 categories and GPT-4o mini in 3 categories; 6 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Claude 3 Sonnet leads 19.7 to 8.7.
- The biggest single-benchmark swing is MATH Level 5: 18.2% for Claude 3 Sonnet and 52.6% for GPT-4o mini.

## Snapshot

| | Claude 3 Sonnet | GPT-4o mini |
|---|---|---|
| Provider | Anthropic | OpenAI |
| Noometry Index | 28.8 | 25.4 |
| Rank | 311 | 337 |
| Context | — | 128K |
| Input $/M | — | $0.15 |
| Output $/M | — | $0.60 |
| Weights | Proprietary | Proprietary |

## Coding

- Claude 3 Sonnet: 29.2 (#296)
- GPT-4o mini: 21.6 (#330)

| Benchmark | Claude 3 Sonnet | GPT-4o mini |
|---|---|---|
| WeirdML | 10.2% | 11.8% |
| BigCodeBench Instruct | 42.7% | 46.1% |
| LMArena Coding | 1223 | 1290 |
| BigCodeBench Complete | 53.8% | 57.4% |
| HumanEval+ | 64% | 83.5% |
| MBPP+ | 69.3% | 72.2% |
| Aider Polyglot | — | 3.6% |
| LiveBench Coding | — | 43.1% |

## Agentic & Tool Use

- Claude 3 Sonnet: —
- GPT-4o mini: 27.2 (#95)

| Benchmark | Claude 3 Sonnet | GPT-4o mini |
|---|---|---|
| BALROG | — | 17.4% |

## Reasoning

- Claude 3 Sonnet: 19.7 (#232)
- GPT-4o mini: 8.7 (#343)

| Benchmark | Claude 3 Sonnet | GPT-4o mini |
|---|---|---|
| LMArena Hard Prompts | 1197 | 1267 |
| DTBench | 53.6% | 54.4% |
| Epoch Capabilities Index | 120.69 | 126.56 |
| ARC-AGI-2 | — | 0% |
| SimpleBench | — | 10.7% |
| Kagi LLM Benchmark | — | 28.8% |
| Chess Puzzles | — | 0% |
| LiveBench Reasoning | — | 32.8% |
| Mystery Game Puzzles | — | 12% |
| LiveBench Data Analysis | — | 50% |
| LMCA | — | 10.4% |
| LiveBench | — | 41.3% |
| PIQA | — | 88.7% |
| WinoGrande | 75.1% | — |

## Math

- Claude 3 Sonnet: 10.0 (#305)
- GPT-4o mini: 9.9 (#307)

| Benchmark | Claude 3 Sonnet | GPT-4o mini |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 2.5% | 6.9% |
| LMArena Math | 1213 | 1267 |
| MATH Level 5 | 18.2% | 52.6% |
| FrontierMath (Tiers 1-3) | — | 0.7% |
| Omni-MATH | — | 28% |
| LiveBench Math | — | 36.3% |
| GSM8K | — | 91.3% |

## Knowledge

- Claude 3 Sonnet: 21.1 (#271)
- GPT-4o mini: 17.7 (#279)

| Benchmark | Claude 3 Sonnet | GPT-4o mini |
|---|---|---|
| GPQA Diamond | 40.6% | 37.7% |
| LMArena Expert | 1173 | 1235 |
| MMLU | 75.9% | 81.8% |
| SimpleQA Verified | — | 8.3% |
| MMLU-Pro | — | 60.3% |
| Confabulations | — | 37.2% |
| GPQA (HELM) | — | 36.8% |
| BoolQ | — | 88.7% |

## Multimodal

- Claude 3 Sonnet: 24.7 (#120)
- GPT-4o mini: 25.3 (#117)

| Benchmark | Claude 3 Sonnet | GPT-4o mini |
|---|---|---|
| LMArena Vision | 984 | 1066 |
| Video-MME | — | 64.8% |
| GeoBench | — | 64% |
| VPCT | — | 34% |

## Multilingual

- Claude 3 Sonnet: 38.0 (#229)
- GPT-4o mini: 42.2 (#194)

| Benchmark | Claude 3 Sonnet | GPT-4o mini |
|---|---|---|
| LMArena Non-English | 1205 | 1266 |
| LMArena Chinese | 1188 | 1264 |
| LMArena French | 1228 | 1296 |
| LMArena German | 1204 | 1272 |
| LMArena Japanese | 1131 | 1216 |
| LMArena Korean | 1128 | 1195 |
| LMArena Russian | 1227 | 1275 |
| LMArena Spanish | 1204 | 1276 |

## Instruction Following

- Claude 3 Sonnet: 63.1 (#230)
- GPT-4o mini: 62.1 (#234)

| Benchmark | Claude 3 Sonnet | GPT-4o mini |
|---|---|---|
| LMArena Instruction Following | 1200 | 1259 |
| LiveBench Instruction Following | — | 56.8% |
| IFEval | — | 78.2% |

## Long Context

- Claude 3 Sonnet: 36.7 (#223)
- GPT-4o mini: 39.1 (#181)

| Benchmark | Claude 3 Sonnet | GPT-4o mini |
|---|---|---|
| LMArena Longer Query | 1211 | 1289 |

## Writing & Preference

- Claude 3 Sonnet: 42.3 (#233)
- GPT-4o mini: 39.7 (#243)

| Benchmark | Claude 3 Sonnet | GPT-4o mini |
|---|---|---|
| LMArena Text | 1218 | 1286 |
| LMArena Creative Writing | 1186 | 1268 |
| LMArena Multi-Turn | 1227 | 1285 |
| Short-Story Creative Writing | — | 67.2% |
| EQ-Bench Creative Writing | — | 873 |
| WildBench | — | 79.1% |
| LiveBench Language | — | 28.6% |

## FAQ

### Is Claude 3 Sonnet better than GPT-4o mini?

Claude 3 Sonnet is the stronger model overall, scoring 28.8 to 25.4 on the Noometry Index.

### Is Claude 3 Sonnet or GPT-4o mini better for coding?

Claude 3 Sonnet scores higher on coding benchmarks: 29.2 versus 21.6 in the Noometry coding category.

### How many benchmarks do Claude 3 Sonnet and GPT-4o mini share?

29 benchmarks have published results for both models. Claude 3 Sonnet has 30 scored results on Noometry and GPT-4o mini has 60.