# Claude Sonnet 5.5 vs GPT-4o mini

> Claude Sonnet 5.5 is the stronger model overall, scoring 61.9 to 25.5 on the Noometry Index. GPT-4o mini costs 15× less per token, which makes it the better buy when Claude Sonnet 5.5's lead doesn't matter for your workload.

- Canonical page: https://noometry.com/compare/claude-sonnet-5-5-vs-gpt-4o-mini
- Last updated: 2026-10-12
- Shared benchmarks: 19

## Summary

- They share 19 benchmarks with published results for both. Claude Sonnet 5.5 scores higher in 10 categories and GPT-4o mini in 0 categories; 10 gaps are clear of the uncertainty.
- The widest gap is in math, where Claude Sonnet 5.5 leads 87.9 to 10.4.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 100% for Claude Sonnet 5.5 and 6.9% for GPT-4o mini.
- GPT-4o mini is cheaper at $0.15 / $0.60 per million input/output tokens, against $2 / $10 for Claude Sonnet 5.5.
- Claude Sonnet 5.5 accepts more context: 1M tokens versus 128K.

## Snapshot

| | Claude Sonnet 5.5 | GPT-4o mini |
|---|---|---|
| Provider | Anthropic | OpenAI |
| Noometry Index | 61.9 | 25.5 |
| Rank | 10 | 343 |
| Context | 1M | 128K |
| Input $/M | $2 | $0.15 |
| Output $/M | $10 | $0.60 |
| Weights | Proprietary | Proprietary |

## Coding

- Claude Sonnet 5.5: 67.3 (#6)
- GPT-4o mini: 22.0 (#335)

| Benchmark | Claude Sonnet 5.5 | GPT-4o mini |
|---|---|---|
| LMArena Coding | 1513 | 1290 |
| FrontierCode | 52.1% | — |
| Aider Polyglot | — | 3.6% |
| CursorBench | 55.5% | — |
| LMArena WebDev | 1774 | — |
| FrontierSWE | 61.9% | — |
| SciCode | 61% | — |
| WeirdML | — | 11.8% |
| BigCodeBench Instruct | — | 46.1% |
| LiveBench Coding | — | 43.1% |
| BigCodeBench Complete | — | 57.4% |
| ALE-Bench | 1,819 | — |
| HumanEval+ | — | 83.5% |
| MBPP+ | — | 72.2% |

## Agentic & Tool Use

- Claude Sonnet 5.5: 45.0 (#16)
- GPT-4o mini: 27.5 (#101)

| Benchmark | Claude Sonnet 5.5 | GPT-4o mini |
|---|---|---|
| APEX-Agents | 75.5% | — |
| BALROG | — | 17.4% |

## Reasoning

- Claude Sonnet 5.5: 54.0 (#28)
- GPT-4o mini: 8.7 (#347)

| Benchmark | Claude Sonnet 5.5 | GPT-4o mini |
|---|---|---|
| LMArena Hard Prompts | 1495 | 1267 |
| Mystery Game Puzzles | 65% | 12% |
| Epoch Capabilities Index | 165.03 | 126.56 |
| ARC-AGI-2 | — | 0% |
| SimpleBench | — | 10.7% |
| Kagi LLM Benchmark | — | 28.8% |
| NYT Connections (extended) | 80.5% | — |
| CritPt | 31.4% | — |
| Chess Puzzles | — | 0% |
| LiveBench Reasoning | — | 32.8% |
| DTBench | — | 54.4% |
| LiveBench Data Analysis | — | 50% |
| LMCA | — | 10.4% |
| LiveBench | — | 41.3% |
| PIQA | — | 88.7% |

## Math

- Claude Sonnet 5.5: 87.9 (#6)
- GPT-4o mini: 10.4 (#314)

| Benchmark | Claude Sonnet 5.5 | GPT-4o mini |
|---|---|---|
| FrontierMath (Tiers 1-3) | 88.8% | 0.7% |
| OTIS Mock AIME 2024-2025 | 100% | 6.9% |
| LMArena Math | 1510 | 1267 |
| FrontierMath Tier 4 | 80.5% | — |
| ProofBench | 100% | — |
| Omni-MATH | — | 28% |
| LiveBench Math | — | 36.3% |
| MATH Level 5 | — | 52.6% |
| FrontierMath Erdős | 2.9% | — |
| GSM8K | — | 91.3% |

## Knowledge

- Claude Sonnet 5.5: 66.0 (#12)
- GPT-4o mini: 17.7 (#284)

| Benchmark | Claude Sonnet 5.5 | GPT-4o mini |
|---|---|---|
| GPQA Diamond | 95.6% | 37.7% |
| SimpleQA Verified | 46.5% | 8.3% |
| LMArena Expert | 1540 | 1235 |
| MMLU-Pro | — | 60.3% |
| Confabulations | — | 37.2% |
| GPQA (HELM) | — | 36.8% |
| BoolQ | — | 88.7% |
| MMLU | — | 81.8% |

## Multimodal

- Claude Sonnet 5.5: 51.5 (#6)
- GPT-4o mini: 25.9 (#122)

| Benchmark | Claude Sonnet 5.5 | GPT-4o mini |
|---|---|---|
| LMArena Vision | 1289 | 1066 |
| Video-MME | — | 64.8% |
| GeoBench | — | 64% |
| VPCT | — | 34% |
| Furniture Assembly | 75% | — |

## Multilingual

- Claude Sonnet 5.5: 55.3 (#30)
- GPT-4o mini: 42.0 (#199)

| Benchmark | Claude Sonnet 5.5 | GPT-4o mini |
|---|---|---|
| LMArena Non-English | 1452 | 1266 |
| LMArena Chinese | 1522 | 1265 |
| LMArena Russian | 1451 | 1275 |
| LMArena French | — | 1297 |
| LMArena German | — | 1272 |
| LMArena Japanese | — | 1216 |
| LMArena Korean | — | 1195 |
| LMArena Spanish | — | 1276 |

## Instruction Following

- Claude Sonnet 5.5: 78.3 (#11)
- GPT-4o mini: 61.9 (#239)

| Benchmark | Claude Sonnet 5.5 | GPT-4o mini |
|---|---|---|
| LMArena Instruction Following | 1495 | 1258 |
| LiveBench Instruction Following | — | 56.8% |
| IFEval | — | 78.2% |

## Long Context

- Claude Sonnet 5.5: 45.9 (#28)
- GPT-4o mini: 39.1 (#186)

| Benchmark | Claude Sonnet 5.5 | GPT-4o mini |
|---|---|---|
| LMArena Longer Query | 1498 | 1289 |

## Writing & Preference

- Claude Sonnet 5.5: 66.0 (#40)
- GPT-4o mini: 39.5 (#248)

| Benchmark | Claude Sonnet 5.5 | GPT-4o mini |
|---|---|---|
| LMArena Text | 1471 | 1286 |
| LMArena Creative Writing | 1465 | 1268 |
| LMArena Multi-Turn | 1474 | 1285 |
| Short-Story Creative Writing | — | 67.2% |
| EQ-Bench Creative Writing | — | 873 |
| WildBench | — | 79.1% |
| LiveBench Language | — | 28.6% |

## FAQ

### Is Claude Sonnet 5.5 better than GPT-4o mini?

Claude Sonnet 5.5 is the stronger model overall, scoring 61.9 to 25.5 on the Noometry Index. GPT-4o mini costs 15× less per token, which makes it the better buy when Claude Sonnet 5.5's lead doesn't matter for your workload.

### Which is cheaper, Claude Sonnet 5.5 or GPT-4o mini?

GPT-4o mini is cheaper. It lists at $0.15 per million input tokens and $0.60 per million output tokens; Claude Sonnet 5.5 lists at $2 and $10.

### Is Claude Sonnet 5.5 or GPT-4o mini better for coding?

Claude Sonnet 5.5 scores higher on coding benchmarks: 67.3 versus 22.0 in the Noometry coding category.

### Which has the bigger context window?

Claude Sonnet 5.5 does, with 1M tokens against 128K.

### How many benchmarks do Claude Sonnet 5.5 and GPT-4o mini share?

19 benchmarks have published results for both models. Claude Sonnet 5.5 has 32 scored results on Noometry and GPT-4o mini has 60.