# GPT-5.2 Codex vs MiniMax M1

> GPT-5.2 Codex is the stronger model overall, scoring 42.2 to 39.7 on the Noometry Index. MiniMax M1 costs 5.7× 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-minimax-m1
- Last updated: 2026-10-10
- Shared benchmarks: 0

## Summary

- The widest gap is in coding, where GPT-5.2 Codex leads 45.4 to 39.2.
- MiniMax M1 is cheaper at $0.40 / $2.20 per million input/output tokens, against $1.75 / $14 for GPT-5.2 Codex.
- MiniMax M1 accepts more context: 1M tokens versus 400K.
- MiniMax M1 has downloadable open weights; the other is API-only.

## Snapshot

| | GPT-5.2 Codex | MiniMax M1 |
|---|---|---|
| Provider | OpenAI | MiniMax |
| Noometry Index | 42.2 | 39.7 |
| Rank | 107 | 146 |
| Context | 400K | 1M |
| Input $/M | $1.75 | $0.40 |
| Output $/M | $14 | $2.20 |
| Weights | Proprietary | Open |

## Coding

- GPT-5.2 Codex: 45.4 (#66)
- MiniMax M1: 39.2 (#149)

| Benchmark | GPT-5.2 Codex | MiniMax M1 |
|---|---|---|
| SWE-bench Verified (bash only) | 72.8% | — |
| LMArena WebDev | 1339 | — |
| SWE-bench Multilingual | 66.3% | — |
| LMArena Coding | — | 1359 |
| ALE-Bench | 1,300 | — |

## Agentic & Tool Use

- GPT-5.2 Codex: 40.7 (#20)
- MiniMax M1: —

| Benchmark | GPT-5.2 Codex | MiniMax M1 |
|---|---|---|
| Terminal-Bench | 66.5% | — |

## Reasoning

- GPT-5.2 Codex: —
- MiniMax M1: 25.8 (#125)

| Benchmark | GPT-5.2 Codex | MiniMax M1 |
|---|---|---|
| LMArena Hard Prompts | — | 1340 |

## Math

- GPT-5.2 Codex: —
- MiniMax M1: 34.8 (#152)

| Benchmark | GPT-5.2 Codex | MiniMax M1 |
|---|---|---|
| LMArena Math | — | 1360 |

## Knowledge

- GPT-5.2 Codex: —
- MiniMax M1: 35.7 (#168)

| Benchmark | GPT-5.2 Codex | MiniMax M1 |
|---|---|---|
| LMArena Expert | — | 1316 |

## Multilingual

- GPT-5.2 Codex: —
- MiniMax M1: 46.0 (#157)

| Benchmark | GPT-5.2 Codex | MiniMax M1 |
|---|---|---|
| LMArena Non-English | — | 1320 |
| LMArena Chinese | — | 1361 |
| LMArena French | — | 1369 |
| LMArena German | — | 1350 |
| LMArena Japanese | — | 1220 |
| LMArena Korean | — | 1263 |
| LMArena Russian | — | 1330 |
| LMArena Spanish | — | 1354 |

## Instruction Following

- GPT-5.2 Codex: —
- MiniMax M1: 69.5 (#169)

| Benchmark | GPT-5.2 Codex | MiniMax M1 |
|---|---|---|
| LMArena Instruction Following | — | 1312 |

## Long Context

- GPT-5.2 Codex: —
- MiniMax M1: 41.4 (#136)

| Benchmark | GPT-5.2 Codex | MiniMax M1 |
|---|---|---|
| Fiction.LiveBench | — | 69.4% |
| LMArena Longer Query | — | 1326 |

## Writing & Preference

- GPT-5.2 Codex: —
- MiniMax M1: 53.3 (#155)

| Benchmark | GPT-5.2 Codex | MiniMax M1 |
|---|---|---|
| LMArena Text | — | 1343 |
| LMArena Creative Writing | — | 1298 |
| LMArena Multi-Turn | — | 1335 |

## FAQ

### Is GPT-5.2 Codex better than MiniMax M1?

GPT-5.2 Codex is the stronger model overall, scoring 42.2 to 39.7 on the Noometry Index. MiniMax M1 costs 5.7× 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 MiniMax M1?

MiniMax M1 is cheaper. It lists at $0.40 per million input tokens and $2.20 per million output tokens; GPT-5.2 Codex lists at $1.75 and $14.

### Is GPT-5.2 Codex or MiniMax M1 better for coding?

GPT-5.2 Codex scores higher on coding benchmarks: 45.4 versus 39.2 in the Noometry coding category.

### Which has the bigger context window?

MiniMax M1 does, with 1M tokens against 400K.

### How many benchmarks do GPT-5.2 Codex and MiniMax M1 share?

0 benchmarks have published results for both models. GPT-5.2 Codex has 5 scored results on Noometry and MiniMax M1 has 18.