# Claude Sonnet 5 vs GPT-5.3 Codex

> Claude Sonnet 5 is the stronger model overall, scoring 54.6 to 45.8 on the Noometry Index.

- Canonical page: https://noometry.com/compare/claude-sonnet-5-vs-gpt-5-3-codex
- Last updated: 2026-10-11
- Shared benchmarks: 5

## Summary

- They share 5 benchmarks with published results for both. Claude Sonnet 5 scores higher in 1 category and GPT-5.3 Codex in 1 category; 2 gaps are clear of the uncertainty.
- The widest gap is in coding, where Claude Sonnet 5 leads 55.5 to 48.6.
- The biggest single-benchmark swing is WeirdML: 68.8% for Claude Sonnet 5 and 79.3% for GPT-5.3 Codex.
- Claude Sonnet 5 is cheaper at $2 / $10 per million input/output tokens, against $1.75 / $14 for GPT-5.3 Codex.
- Claude Sonnet 5 accepts more context: 1M tokens versus 400K.

## Snapshot

| | Claude Sonnet 5 | GPT-5.3 Codex |
|---|---|---|
| Provider | Anthropic | OpenAI |
| Noometry Index | 54.6 | 45.8 |
| Rank | 29 | 69 |
| Context | 1M | 400K |
| Input $/M | $2 | $1.75 |
| Output $/M | $10 | $14 |
| Weights | Proprietary | Proprietary |

## Coding

- Claude Sonnet 5: 55.5 (#26)
- GPT-5.3 Codex: 48.6 (#56)

| Benchmark | Claude Sonnet 5 | GPT-5.3 Codex |
|---|---|---|
| LMArena WebDev | 1541 | 1409 |
| WeirdML | 68.8% | 79.3% |
| ALE-Bench | 1,463 | 1,655 |
| SWE-bench Verified | — | 74.8% |
| DeepSWE | 53.8% | — |
| FrontierCode | 42.7% | — |
| CursorBench | 34.1% | — |
| SciCode | 54.3% | — |
| GSO | 37.3% | — |
| LMArena Coding | 1483 | — |

## Agentic & Tool Use

- Claude Sonnet 5: 42.8 (#18)
- GPT-5.3 Codex: 48.0 (#9)

| Benchmark | Claude Sonnet 5 | GPT-5.3 Codex |
|---|---|---|
| Vending-Bench 2 | 6,378 | 5,940 |
| Terminal-Bench | — | 78.4% |
| APEX-Agents | 54.5% | — |
| GBAEval | 65.3% | — |
| LMArena Search | 1194 | — |
| METR Time Horizons | — | 74.5% |

## Reasoning

- Claude Sonnet 5: 49.1 (#39)
- GPT-5.3 Codex: —

| Benchmark | Claude Sonnet 5 | GPT-5.3 Codex |
|---|---|---|
| Epoch Capabilities Index | 156.21 | 156.77 |
| SimpleBench | 60.6% | — |
| NYT Connections (extended) | 75.1% | — |
| CritPt | 16.9% | — |
| Chess Puzzles | 35% | — |
| LMArena Hard Prompts | 1461 | — |
| Mystery Game Puzzles | 35% | — |
| DTBench | 92.5% | — |
| LMCA | 50% | — |
| Surface Evolver Bench | 60% | — |
| Bench to the Future 3 | 0.14 | — |
| ForecastBench | 61.1 | — |

## Math

- Claude Sonnet 5: 66.2 (#27)
- GPT-5.3 Codex: —

| Benchmark | Claude Sonnet 5 | GPT-5.3 Codex |
|---|---|---|
| FrontierMath (Tiers 1-3) | 65.6% | — |
| FrontierMath Tier 4 | 29.3% | — |
| OTIS Mock AIME 2024-2025 | 94.7% | — |
| ProofBench | 77% | — |
| LMArena Math | 1467 | — |

## Knowledge

- Claude Sonnet 5: 55.6 (#47)
- GPT-5.3 Codex: —

| Benchmark | Claude Sonnet 5 | GPT-5.3 Codex |
|---|---|---|
| GPQA Diamond | 90.5% | — |
| SimpleQA Verified | 33.7% | — |
| LMArena Expert | 1490 | — |

## Multimodal

- Claude Sonnet 5: 42.4 (#31)
- GPT-5.3 Codex: —

| Benchmark | Claude Sonnet 5 | GPT-5.3 Codex |
|---|---|---|
| LMArena Vision | 1274 | — |
| Blueprint-Bench 2 | 24.9% | — |
| LMArena Document | 1466 | — |

## Multilingual

- Claude Sonnet 5: 53.8 (#55)
- GPT-5.3 Codex: —

| Benchmark | Claude Sonnet 5 | GPT-5.3 Codex |
|---|---|---|
| LMArena Non-English | 1431 | — |
| LMArena Chinese | 1477 | — |
| LMArena French | 1460 | — |
| LMArena German | 1440 | — |
| LMArena Japanese | 1422 | — |
| LMArena Korean | 1411 | — |
| LMArena Russian | 1451 | — |
| LMArena Spanish | 1437 | — |

## Instruction Following

- Claude Sonnet 5: 76.3 (#41)
- GPT-5.3 Codex: —

| Benchmark | Claude Sonnet 5 | GPT-5.3 Codex |
|---|---|---|
| LMArena Instruction Following | 1452 | — |

## Long Context

- Claude Sonnet 5: 44.8 (#55)
- GPT-5.3 Codex: —

| Benchmark | Claude Sonnet 5 | GPT-5.3 Codex |
|---|---|---|
| LMArena Longer Query | 1463 | — |

## Writing & Preference

- Claude Sonnet 5: 69.2 (#25)
- GPT-5.3 Codex: —

| Benchmark | Claude Sonnet 5 | GPT-5.3 Codex |
|---|---|---|
| LMArena Text | 1442 | — |
| LMArena Creative Writing | 1416 | — |
| EQ-Bench Creative Writing | 1794 | — |
| EQ-Bench 4 | 1236 | — |
| LMArena Multi-Turn | 1454 | — |

## FAQ

### Is Claude Sonnet 5 better than GPT-5.3 Codex?

Claude Sonnet 5 is the stronger model overall, scoring 54.6 to 45.8 on the Noometry Index.

### Which is cheaper, Claude Sonnet 5 or GPT-5.3 Codex?

Claude Sonnet 5 is cheaper. It lists at $2 per million input tokens and $10 per million output tokens; GPT-5.3 Codex lists at $1.75 and $14.

### Is Claude Sonnet 5 or GPT-5.3 Codex better for coding?

Claude Sonnet 5 scores higher on coding benchmarks: 55.5 versus 48.6 in the Noometry coding category.

### Which has the bigger context window?

Claude Sonnet 5 does, with 1M tokens against 400K.

### How many benchmarks do Claude Sonnet 5 and GPT-5.3 Codex share?

5 benchmarks have published results for both models. Claude Sonnet 5 has 51 scored results on Noometry and GPT-5.3 Codex has 8.