# GPT-5-Codex vs MiniMax-M2

> GPT-5-Codex and MiniMax-M2 score almost the same on the Noometry Index (37.3 vs 36.9), so choose on price, context window or the category you care about most.

- Canonical page: https://noometry.com/compare/gpt-5-codex-vs-minimax-m2
- Last updated: 2026-10-10
- Shared benchmarks: 2

## Summary

- They share 2 benchmarks with published results for both. GPT-5-Codex scores higher in 3 categories and MiniMax-M2 in 0 categories; 3 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where GPT-5-Codex leads 30.0 to 18.6.
- The biggest single-benchmark swing is Terminal-Bench: 44.3% for GPT-5-Codex and 30% for MiniMax-M2.
- MiniMax-M2 is cheaper at $0.30 / $1.20 per million input/output tokens, against $1.25 / $10 for GPT-5-Codex.
- GPT-5-Codex accepts more context: 400K tokens versus 205K.
- MiniMax-M2 has downloadable open weights; the other is API-only.

## Snapshot

| | GPT-5-Codex | MiniMax-M2 |
|---|---|---|
| Provider | OpenAI | MiniMax |
| Noometry Index | 37.3 | 36.9 |
| Rank | 190 | 201 |
| Context | 400K | 205K |
| Input $/M | $1.25 | $0.30 |
| Output $/M | $10 | $1.20 |
| Weights | Proprietary | Open |

## Coding

- GPT-5-Codex: 41.9 (#100)
- MiniMax-M2: 39.1 (#151)

| Benchmark | GPT-5-Codex | MiniMax-M2 |
|---|---|---|
| SWE-bench Verified (bash only) | — | 61% |
| LMArena WebDev | — | 1297 |
| WeirdML | 54.5% | — |
| LMArena Coding | — | 1370 |

## Agentic & Tool Use

- GPT-5-Codex: 30.8 (#66)
- MiniMax-M2: 24.9 (#102)

| Benchmark | GPT-5-Codex | MiniMax-M2 |
|---|---|---|
| Terminal-Bench | 44.3% | 30% |
| Vending-Bench 2 | — | 160.6 |

## Reasoning

- GPT-5-Codex: 30.0 (#80)
- MiniMax-M2: 18.6 (#256)

| Benchmark | GPT-5-Codex | MiniMax-M2 |
|---|---|---|
| Kagi LLM Benchmark | 70.3% | 57.8% |
| NYT Connections (extended) | — | 14.8% |
| LMArena Hard Prompts | — | 1357 |

## Math

- GPT-5-Codex: —
- MiniMax-M2: 34.6 (#158)

| Benchmark | GPT-5-Codex | MiniMax-M2 |
|---|---|---|
| LMArena Math | — | 1350 |

## Knowledge

- GPT-5-Codex: —
- MiniMax-M2: 36.3 (#160)

| Benchmark | GPT-5-Codex | MiniMax-M2 |
|---|---|---|
| LMArena Expert | — | 1336 |

## Multilingual

- GPT-5-Codex: —
- MiniMax-M2: 45.6 (#165)

| Benchmark | GPT-5-Codex | MiniMax-M2 |
|---|---|---|
| LMArena Non-English | — | 1314 |
| LMArena Chinese | — | 1367 |
| LMArena French | — | 1336 |
| LMArena German | — | 1366 |
| LMArena Russian | — | 1332 |
| LMArena Spanish | — | 1326 |

## Instruction Following

- GPT-5-Codex: —
- MiniMax-M2: 70.4 (#160)

| Benchmark | GPT-5-Codex | MiniMax-M2 |
|---|---|---|
| LMArena Instruction Following | — | 1329 |

## Long Context

- GPT-5-Codex: —
- MiniMax-M2: 40.5 (#148)

| Benchmark | GPT-5-Codex | MiniMax-M2 |
|---|---|---|
| LMArena Longer Query | — | 1332 |

## Writing & Preference

- GPT-5-Codex: —
- MiniMax-M2: 53.3 (#157)

| Benchmark | GPT-5-Codex | MiniMax-M2 |
|---|---|---|
| LMArena Text | — | 1340 |
| LMArena Creative Writing | — | 1288 |
| LMArena Multi-Turn | — | 1362 |

## FAQ

### Is GPT-5-Codex better than MiniMax-M2?

GPT-5-Codex and MiniMax-M2 score almost the same on the Noometry Index (37.3 vs 36.9), so choose on price, context window or the category you care about most.

### Which is cheaper, GPT-5-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-Codex lists at $1.25 and $10.

### Is GPT-5-Codex or MiniMax-M2 better for coding?

GPT-5-Codex scores higher on coding benchmarks: 41.9 versus 39.1 in the Noometry coding category.

### Which has the bigger context window?

GPT-5-Codex does, with 400K tokens against 205K.

### How many benchmarks do GPT-5-Codex and MiniMax-M2 share?

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