# GPT-4 Turbo vs GPT-5.3 Codex

> GPT-5.3 Codex is the stronger model overall, scoring 45.5 to 30.3 on the Noometry Index.

- Canonical page: https://noometry.com/compare/gpt-4-turbo-vs-gpt-5-3-codex
- Last updated: 2026-10-10
- Shared benchmarks: 3

## Summary

- They share 3 benchmarks with published results for both. GPT-4 Turbo scores higher in 0 categories and GPT-5.3 Codex in 1 category; one gap is clear of the uncertainty.
- The widest gap is in coding, where GPT-5.3 Codex leads 48.5 to 33.4.
- The biggest single-benchmark swing is WeirdML: 18% for GPT-4 Turbo and 79.3% for GPT-5.3 Codex.
- GPT-5.3 Codex is cheaper at $1.75 / $14 per million input/output tokens, against $10 / $30 for GPT-4 Turbo.
- GPT-5.3 Codex accepts more context: 400K tokens versus 128K.

## Snapshot

| | GPT-4 Turbo | GPT-5.3 Codex |
|---|---|---|
| Provider | OpenAI | OpenAI |
| Noometry Index | 30.3 | 45.5 |
| Rank | 281 | 61 |
| Context | 128K | 400K |
| Input $/M | $10 | $1.75 |
| Output $/M | $30 | $14 |
| Weights | Proprietary | Proprietary |

## Coding

- GPT-4 Turbo: 33.4 (#247)
- GPT-5.3 Codex: 48.5 (#51)

| Benchmark | GPT-4 Turbo | GPT-5.3 Codex |
|---|---|---|
| WeirdML | 18% | 79.3% |
| SWE-bench Verified | — | 74.8% |
| LMArena WebDev | — | 1408 |
| BigCodeBench Instruct | 48.2% | — |
| LMArena Coding | 1268 | — |
| BigCodeBench Complete | 58.2% | — |
| ALE-Bench | — | 1,655 |
| HumanEval+ | 86.6% | — |
| MBPP+ | 73.3% | — |

## Agentic & Tool Use

- GPT-4 Turbo: —
- GPT-5.3 Codex: 47.8 (#9)

| Benchmark | GPT-4 Turbo | GPT-5.3 Codex |
|---|---|---|
| METR Time Horizons | 36.7% | 74.5% |
| Terminal-Bench | — | 78.4% |
| Vending-Bench 2 | — | 5,940 |

## Reasoning

- GPT-4 Turbo: 14.9 (#311)
- GPT-5.3 Codex: —

| Benchmark | GPT-4 Turbo | GPT-5.3 Codex |
|---|---|---|
| Epoch Capabilities Index | 127.25 | 156.84 |
| SimpleBench | 25.1% | — |
| Chess Puzzles | 6% | — |
| LMArena Hard Prompts | 1251 | — |
| DTBench | 61.6% | — |
| LMCA | 9.8% | — |
| ForecastBench | 59.4 | — |

## Math

- GPT-4 Turbo: 8.6 (#316)
- GPT-5.3 Codex: —

| Benchmark | GPT-4 Turbo | GPT-5.3 Codex |
|---|---|---|
| FrontierMath (Tiers 1-3) | 0.7% | — |
| OTIS Mock AIME 2024-2025 | 6.7% | — |
| LMArena Math | 1272 | — |
| MATH Level 5 | 46.7% | — |

## Knowledge

- GPT-4 Turbo: 24.3 (#263)
- GPT-5.3 Codex: —

| Benchmark | GPT-4 Turbo | GPT-5.3 Codex |
|---|---|---|
| GPQA Diamond | 46.6% | — |
| Confabulations | 28.4% | — |
| LMArena Expert | 1223 | — |
| MMLU | 81.3% | — |

## Multimodal

- GPT-4 Turbo: 30.0 (#104)
- GPT-5.3 Codex: —

| Benchmark | GPT-4 Turbo | GPT-5.3 Codex |
|---|---|---|
| LMArena Vision | 1090 | — |

## Multilingual

- GPT-4 Turbo: 40.7 (#211)
- GPT-5.3 Codex: —

| Benchmark | GPT-4 Turbo | GPT-5.3 Codex |
|---|---|---|
| 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

- GPT-4 Turbo: 66.0 (#211)
- GPT-5.3 Codex: —

| Benchmark | GPT-4 Turbo | GPT-5.3 Codex |
|---|---|---|
| LMArena Instruction Following | 1250 | — |

## Long Context

- GPT-4 Turbo: 38.0 (#200)
- GPT-5.3 Codex: —

| Benchmark | GPT-4 Turbo | GPT-5.3 Codex |
|---|---|---|
| LMArena Longer Query | 1254 | — |

## Writing & Preference

- GPT-4 Turbo: 47.9 (#201)
- GPT-5.3 Codex: —

| Benchmark | GPT-4 Turbo | GPT-5.3 Codex |
|---|---|---|
| LMArena Text | 1272 | — |
| LMArena Creative Writing | 1269 | — |
| LMArena Multi-Turn | 1267 | — |

## FAQ

### Is GPT-4 Turbo better than GPT-5.3 Codex?

GPT-5.3 Codex is the stronger model overall, scoring 45.5 to 30.3 on the Noometry Index.

### Which is cheaper, GPT-4 Turbo or GPT-5.3 Codex?

GPT-5.3 Codex is cheaper. It lists at $1.75 per million input tokens and $14 per million output tokens; GPT-4 Turbo lists at $10 and $30.

### Is GPT-4 Turbo or GPT-5.3 Codex better for coding?

GPT-5.3 Codex scores higher on coding benchmarks: 48.5 versus 33.4 in the Noometry coding category.

### Which has the bigger context window?

GPT-5.3 Codex does, with 400K tokens against 128K.

### How many benchmarks do GPT-4 Turbo and GPT-5.3 Codex share?

3 benchmarks have published results for both models. GPT-4 Turbo has 36 scored results on Noometry and GPT-5.3 Codex has 8.