# GPT-5.2 Codex vs MiniMax-M2

> GPT-5.2 Codex is the stronger model overall, scoring 42.6 to 37.4 on the Noometry Index. MiniMax-M2 costs 9.2× 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-m2
- Last updated: 2026-10-10
- Shared benchmarks: 3

## Summary

- They share 3 benchmarks with published results for both. GPT-5.2 Codex scores higher in 2 categories and MiniMax-M2 in 0 categories; 2 gaps are clear of the uncertainty.
- The widest gap is in agentic & tool use, where GPT-5.2 Codex leads 41.0 to 25.1.
- The biggest single-benchmark swing is Terminal-Bench: 66.5% for GPT-5.2 Codex and 30% for MiniMax-M2.
- MiniMax-M2 is cheaper at $0.30 / $1.20 per million input/output tokens, against $1.75 / $14 for GPT-5.2 Codex.
- GPT-5.2 Codex accepts more context: 400K tokens versus 205K.
- MiniMax-M2 has downloadable open weights; the other is API-only.

## Snapshot

| | GPT-5.2 Codex | MiniMax-M2 |
|---|---|---|
| Provider | OpenAI | MiniMax |
| Noometry Index | 42.6 | 37.4 |
| Rank | 111 | 204 |
| Context | 400K | 205K |
| Input $/M | $1.75 | $0.30 |
| Output $/M | $14 | $1.20 |
| Weights | Proprietary | Open |

## Coding

- GPT-5.2 Codex: 45.5 (#71)
- MiniMax-M2: 39.3 (#159)

| Benchmark | GPT-5.2 Codex | MiniMax-M2 |
|---|---|---|
| SWE-bench Verified (bash only) | 72.8% | 61% |
| LMArena WebDev | 1339 | 1297 |
| SWE-bench Multilingual | 66.3% | — |
| LMArena Coding | — | 1370 |
| ALE-Bench | 1,300 | — |

## Agentic & Tool Use

- GPT-5.2 Codex: 41.0 (#22)
- MiniMax-M2: 25.1 (#109)

| Benchmark | GPT-5.2 Codex | MiniMax-M2 |
|---|---|---|
| Terminal-Bench | 66.5% | 30% |
| Vending-Bench 2 | — | 160.6 |

## Reasoning

- GPT-5.2 Codex: —
- MiniMax-M2: 19.4 (#258)

| Benchmark | GPT-5.2 Codex | MiniMax-M2 |
|---|---|---|
| Kagi LLM Benchmark | — | 57.8% |
| NYT Connections (extended) | — | 14.8% |
| LMArena Hard Prompts | — | 1357 |

## Math

- GPT-5.2 Codex: —
- MiniMax-M2: 37.3 (#160)

| Benchmark | GPT-5.2 Codex | MiniMax-M2 |
|---|---|---|
| LMArena Math | — | 1352 |

## Knowledge

- GPT-5.2 Codex: —
- MiniMax-M2: 37.0 (#163)

| Benchmark | GPT-5.2 Codex | MiniMax-M2 |
|---|---|---|
| LMArena Expert | — | 1337 |

## Multilingual

- GPT-5.2 Codex: —
- MiniMax-M2: 45.3 (#171)

| Benchmark | GPT-5.2 Codex | MiniMax-M2 |
|---|---|---|
| LMArena Non-English | — | 1313 |
| LMArena Chinese | — | 1366 |
| LMArena French | — | 1335 |
| LMArena German | — | 1355 |
| LMArena Russian | — | 1331 |
| LMArena Spanish | — | 1326 |

## Instruction Following

- GPT-5.2 Codex: —
- MiniMax-M2: 70.2 (#166)

| Benchmark | GPT-5.2 Codex | MiniMax-M2 |
|---|---|---|
| LMArena Instruction Following | — | 1328 |

## Long Context

- GPT-5.2 Codex: —
- MiniMax-M2: 40.5 (#153)

| Benchmark | GPT-5.2 Codex | MiniMax-M2 |
|---|---|---|
| LMArena Longer Query | — | 1331 |

## Writing & Preference

- GPT-5.2 Codex: —
- MiniMax-M2: 53.0 (#162)

| Benchmark | GPT-5.2 Codex | MiniMax-M2 |
|---|---|---|
| LMArena Text | — | 1340 |
| LMArena Creative Writing | — | 1286 |
| LMArena Multi-Turn | — | 1361 |

## FAQ

### Is GPT-5.2 Codex better than MiniMax-M2?

GPT-5.2 Codex is the stronger model overall, scoring 42.6 to 37.4 on the Noometry Index. MiniMax-M2 costs 9.2× 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-M2?

MiniMax-M2 is cheaper. It lists at $0.30 per million input tokens and $1.20 per million output tokens; GPT-5.2 Codex lists at $1.75 and $14.

### Is GPT-5.2 Codex or MiniMax-M2 better for coding?

GPT-5.2 Codex scores higher on coding benchmarks: 45.5 versus 39.3 in the Noometry coding category.

### Which has the bigger context window?

GPT-5.2 Codex does, with 400K tokens against 205K.

### How many benchmarks do GPT-5.2 Codex and MiniMax-M2 share?

3 benchmarks have published results for both models. GPT-5.2 Codex has 5 scored results on Noometry and MiniMax-M2 has 21.