# GPT-4 vs GPT-5.1-Codex

> GPT-5.1-Codex is the stronger model overall, scoring 38.2 to 28.9 on the Noometry Index.

- Canonical page: https://noometry.com/compare/gpt-4-vs-gpt-5-1-codex
- Last updated: 2026-10-10
- Shared benchmarks: 1

## Summary

- They share 1 benchmark with published results for both. GPT-4 scores higher in 0 categories and GPT-5.1-Codex in 2 categories; 2 gaps are clear of the uncertainty.
- The widest gap is in math, where GPT-5.1-Codex leads 29.3 to 10.1.
- GPT-5.1-Codex is cheaper at $1.25 / $10 per million input/output tokens, against $30 / $60 for GPT-4.
- GPT-5.1-Codex accepts more context: 400K tokens versus 8K.

## Snapshot

| | GPT-4 | GPT-5.1-Codex |
|---|---|---|
| Provider | OpenAI | OpenAI |
| Noometry Index | 28.9 | 38.2 |
| Rank | 308 | 178 |
| Context | 8K | 400K |
| Input $/M | $30 | $1.25 |
| Output $/M | $60 | $10 |
| Weights | Proprietary | Proprietary |

## Coding

- GPT-4: 31.2 (#277)
- GPT-5.1-Codex: 41.7 (#107)

| Benchmark | GPT-4 | GPT-5.1-Codex |
|---|---|---|
| SWE-bench Verified (bash only) | — | 66% |
| LMArena WebDev | — | 1337 |
| WeirdML | 12.4% | — |
| BigCodeBench Instruct | 46% | — |
| LMArena Coding | 1254 | — |
| BigCodeBench Complete | 57.2% | — |
| ALE-Bench | — | 1,245 |
| HumanEval+ | 79.3% | — |

## Agentic & Tool Use

- GPT-4: —
- GPT-5.1-Codex: 37.8 (#32)

| Benchmark | GPT-4 | GPT-5.1-Codex |
|---|---|---|
| METR Time Horizons | 36.1% | 70.8% |
| Terminal-Bench | — | 60.4% |

## Reasoning

- GPT-4: 17.3 (#285)
- GPT-5.1-Codex: —

| Benchmark | GPT-4 | GPT-5.1-Codex |
|---|---|---|
| Chess Puzzles | 4% | — |
| LMArena Hard Prompts | 1241 | — |
| Mystery Game Puzzles | 12% | — |
| DTBench | 62.7% | — |
| LMCA | 17.1% | — |
| BIG-Bench Hard | 75.1% | — |
| Epoch Capabilities Index | 125.88 | — |
| ForecastBench | 57.8 | — |
| HellaSwag | 95.3% | — |
| WinoGrande | 87.5% | — |

## Math

- GPT-4: 10.1 (#304)
- GPT-5.1-Codex: 29.3 (#218)

| Benchmark | GPT-4 | GPT-5.1-Codex |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 1.1% | — |
| ProofBench | — | 9% |
| LMArena Math | 1269 | — |
| MATH Level 5 | 23% | — |
| GSM8K | 92% | — |

## Knowledge

- GPT-4: 18.4 (#277)
- GPT-5.1-Codex: —

| Benchmark | GPT-4 | GPT-5.1-Codex |
|---|---|---|
| GPQA Diamond | 35.7% | — |
| LMArena Expert | 1211 | — |
| MMLU | 86.4% | — |
| TriviaQA | 84.8% | — |

## Multilingual

- GPT-4: 40.8 (#210)
- GPT-5.1-Codex: —

| Benchmark | GPT-4 | GPT-5.1-Codex |
|---|---|---|
| LMArena Non-English | 1246 | — |
| LMArena Chinese | 1242 | — |
| LMArena French | 1282 | — |
| LMArena German | 1251 | — |
| LMArena Japanese | 1209 | — |
| LMArena Korean | 1184 | — |
| LMArena Russian | 1251 | — |
| LMArena Spanish | 1261 | — |

## Instruction Following

- GPT-4: 65.5 (#217)
- GPT-5.1-Codex: —

| Benchmark | GPT-4 | GPT-5.1-Codex |
|---|---|---|
| LMArena Instruction Following | 1241 | — |

## Long Context

- GPT-4: 37.7 (#207)
- GPT-5.1-Codex: —

| Benchmark | GPT-4 | GPT-5.1-Codex |
|---|---|---|
| LMArena Longer Query | 1244 | — |

## Writing & Preference

- GPT-4: 35.0 (#263)
- GPT-5.1-Codex: —

| Benchmark | GPT-4 | GPT-5.1-Codex |
|---|---|---|
| LMArena Text | 1263 | — |
| LMArena Creative Writing | 1244 | — |
| EQ-Bench Creative Writing | 752 | — |
| LMArena Multi-Turn | 1257 | — |

## FAQ

### Is GPT-4 better than GPT-5.1-Codex?

GPT-5.1-Codex is the stronger model overall, scoring 38.2 to 28.9 on the Noometry Index.

### Which is cheaper, GPT-4 or GPT-5.1-Codex?

GPT-5.1-Codex is cheaper. It lists at $1.25 per million input tokens and $10 per million output tokens; GPT-4 lists at $30 and $60.

### Is GPT-4 or GPT-5.1-Codex better for coding?

GPT-5.1-Codex scores higher on coding benchmarks: 41.7 versus 31.2 in the Noometry coding category.

### Which has the bigger context window?

GPT-5.1-Codex does, with 400K tokens against 8K.

### How many benchmarks do GPT-4 and GPT-5.1-Codex share?

1 benchmark has published results for both models. GPT-4 has 38 scored results on Noometry and GPT-5.1-Codex has 6.