# GPT-5.2 Codex vs Magistral Medium

> GPT-5.2 Codex is the stronger model overall, scoring 42.6 to 35.2 on the Noometry Index. Magistral Medium costs 1.8× less per token, which makes it the better buy when GPT-5.2 Codex's lead doesn't matter for your workload.

- Canonical page: https://noometry.com/compare/gpt-5-2-codex-vs-magistral-medium
- Last updated: 2026-10-11
- Shared benchmarks: 0

## Summary

- The widest gap is in coding, where GPT-5.2 Codex leads 45.5 to 39.1.
- Magistral Medium is cheaper at $2 / $5 per million input/output tokens, against $1.75 / $14 for GPT-5.2 Codex.
- GPT-5.2 Codex accepts more context: 400K tokens versus 262K.
- Magistral Medium has downloadable open weights; the other is API-only.

## Snapshot

| | GPT-5.2 Codex | Magistral Medium |
|---|---|---|
| Provider | OpenAI | Mistral AI |
| Noometry Index | 42.6 | 35.2 |
| Rank | 111 | 227 |
| Context | 400K | 262K |
| Input $/M | $1.75 | $2 |
| Output $/M | $14 | $5 |
| Weights | Proprietary | Open |

## Coding

- GPT-5.2 Codex: 45.5 (#71)
- Magistral Medium: 39.1 (#161)

| Benchmark | GPT-5.2 Codex | Magistral Medium |
|---|---|---|
| SWE-bench Verified (bash only) | 72.8% | — |
| LMArena WebDev | 1339 | — |
| SWE-bench Multilingual | 66.3% | — |
| SciCode | — | 39.2% |
| LMArena Coding | — | 1319 |
| ALE-Bench | 1,300 | — |

## Agentic & Tool Use

- GPT-5.2 Codex: 41.0 (#22)
- Magistral Medium: —

| Benchmark | GPT-5.2 Codex | Magistral Medium |
|---|---|---|
| Terminal-Bench | 66.5% | — |

## Reasoning

- GPT-5.2 Codex: —
- Magistral Medium: 8.6 (#348)

| Benchmark | GPT-5.2 Codex | Magistral Medium |
|---|---|---|
| ARC-AGI-2 | — | 0% |
| Kagi LLM Benchmark | — | 16.2% |
| ARC-AGI-1 | — | 6.1% |
| CritPt | — | 0.3% |
| LMArena Hard Prompts | — | 1267 |

## Math

- GPT-5.2 Codex: —
- Magistral Medium: 35.1 (#189)

| Benchmark | GPT-5.2 Codex | Magistral Medium |
|---|---|---|
| LMArena Math | — | 1250 |

## Knowledge

- GPT-5.2 Codex: —
- Magistral Medium: 33.5 (#202)

| Benchmark | GPT-5.2 Codex | Magistral Medium |
|---|---|---|
| LMArena Expert | — | 1223 |

## Multilingual

- GPT-5.2 Codex: —
- Magistral Medium: 39.6 (#224)

| Benchmark | GPT-5.2 Codex | Magistral Medium |
|---|---|---|
| LMArena Non-English | — | 1232 |
| LMArena Chinese | — | 1227 |
| LMArena French | — | 1267 |
| LMArena German | — | 1248 |
| LMArena Japanese | — | 1175 |
| LMArena Korean | — | 1125 |
| LMArena Russian | — | 1224 |
| LMArena Spanish | — | 1271 |

## Instruction Following

- GPT-5.2 Codex: —
- Magistral Medium: 66.0 (#211)

| Benchmark | GPT-5.2 Codex | Magistral Medium |
|---|---|---|
| LMArena Instruction Following | — | 1254 |

## Long Context

- GPT-5.2 Codex: —
- Magistral Medium: 39.3 (#183)

| Benchmark | GPT-5.2 Codex | Magistral Medium |
|---|---|---|
| LMArena Longer Query | — | 1295 |

## Writing & Preference

- GPT-5.2 Codex: —
- Magistral Medium: 46.3 (#219)

| Benchmark | GPT-5.2 Codex | Magistral Medium |
|---|---|---|
| LMArena Text | — | 1255 |
| LMArena Creative Writing | — | 1245 |
| LMArena Multi-Turn | — | 1275 |

## FAQ

### Is GPT-5.2 Codex better than Magistral Medium?

GPT-5.2 Codex is the stronger model overall, scoring 42.6 to 35.2 on the Noometry Index. Magistral Medium costs 1.8× less per token, which makes it the better buy when GPT-5.2 Codex's lead doesn't matter for your workload.

### Which is cheaper, GPT-5.2 Codex or Magistral Medium?

Magistral Medium is cheaper. It lists at $2 per million input tokens and $5 per million output tokens; GPT-5.2 Codex lists at $1.75 and $14.

### Is GPT-5.2 Codex or Magistral Medium better for coding?

GPT-5.2 Codex scores higher on coding benchmarks: 45.5 versus 39.1 in the Noometry coding category.

### Which has the bigger context window?

GPT-5.2 Codex does, with 400K tokens against 262K.

### How many benchmarks do GPT-5.2 Codex and Magistral Medium share?

0 benchmarks have published results for both models. GPT-5.2 Codex has 5 scored results on Noometry and Magistral Medium has 22.