# Codestral vs MiniMax-M2.7

> MiniMax-M2.7 is the stronger model overall, scoring 37.4 to 30.1 on the Noometry Index.

- Canonical page: https://noometry.com/compare/codestral-vs-minimax-m2-7
- Last updated: 2026-10-10
- Shared benchmarks: 1

## Summary

- They share 1 benchmark with published results for both. Codestral scores higher in 1 category and MiniMax-M2.7 in 1 category; one gap is clear of the uncertainty.
- The widest gap is in coding, where MiniMax-M2.7 leads 41.4 to 26.9.
- Codestral is cheaper at $0.30 / $0.90 per million input/output tokens, against $0.30 / $1.20 for MiniMax-M2.7.
- Codestral accepts more context: 256K tokens versus 205K.

## Snapshot

| | Codestral | MiniMax-M2.7 |
|---|---|---|
| Provider | Mistral AI | MiniMax |
| Noometry Index | 30.1 | 37.4 |
| Rank | 287 | 188 |
| Context | 256K | 205K |
| Input $/M | $0.30 | $0.30 |
| Output $/M | $0.90 | $1.20 |
| Weights | Open | Open |

## Coding

- Codestral: 26.9 (#316)
- MiniMax-M2.7: 41.4 (#115)

| Benchmark | Codestral | MiniMax-M2.7 |
|---|---|---|
| ALE-Bench | 137.78 | 599.25 |
| Aider Polyglot | 11.1% | — |
| LMArena WebDev | — | 1397 |
| SciCode | — | 47% |
| WeirdML | — | 37% |
| BigCodeBench Instruct | 41.8% | — |
| LMArena Coding | — | 1454 |
| BigCodeBench Complete | 52.5% | — |
| HumanEval+ | 73.8% | — |
| MBPP+ | 61.9% | — |

## Agentic & Tool Use

- Codestral: —
- MiniMax-M2.7: 24.9 (#103)

| Benchmark | Codestral | MiniMax-M2.7 |
|---|---|---|
| Terminal-Bench | — | 45.1% |
| ExploitBench | — | 13.3% |
| GBAEval | — | 0% |

## Reasoning

- Codestral: 19.1 (#244)
- MiniMax-M2.7: 19.0 (#248)

| Benchmark | Codestral | MiniMax-M2.7 |
|---|---|---|
| Kagi LLM Benchmark | 32.5% | — |
| NYT Connections (extended) | — | 24.7% |
| CritPt | — | 0.6% |
| Thematic Generalization | — | 39.3% |
| LMArena Hard Prompts | — | 1422 |
| Epoch Capabilities Index | — | 145.84 |

## Math

- Codestral: —
- MiniMax-M2.7: 24.9 (#254)

| Benchmark | Codestral | MiniMax-M2.7 |
|---|---|---|
| ProofBench | — | 3% |
| LMArena Math | — | 1420 |

## Knowledge

- Codestral: —
- MiniMax-M2.7: 37.1 (#151)

| Benchmark | Codestral | MiniMax-M2.7 |
|---|---|---|
| Vectara Hallucination Rate | — | 12.9% |
| LMArena Expert | — | 1443 |

## Multilingual

- Codestral: —
- MiniMax-M2.7: 50.5 (#120)

| Benchmark | Codestral | MiniMax-M2.7 |
|---|---|---|
| LMArena Non-English | — | 1382 |
| LMArena Chinese | — | 1439 |
| LMArena French | — | 1422 |
| LMArena German | — | 1398 |
| LMArena Japanese | — | 1261 |
| LMArena Korean | — | 1313 |
| LMArena Russian | — | 1383 |
| LMArena Spanish | — | 1403 |

## Instruction Following

- Codestral: —
- MiniMax-M2.7: 74.2 (#101)

| Benchmark | Codestral | MiniMax-M2.7 |
|---|---|---|
| LMArena Instruction Following | — | 1404 |

## Long Context

- Codestral: —
- MiniMax-M2.7: 43.3 (#94)

| Benchmark | Codestral | MiniMax-M2.7 |
|---|---|---|
| LMArena Longer Query | — | 1419 |

## Writing & Preference

- Codestral: —
- MiniMax-M2.7: 59.1 (#107)

| Benchmark | Codestral | MiniMax-M2.7 |
|---|---|---|
| LMArena Text | — | 1404 |
| LMArena Creative Writing | — | 1354 |
| LMArena Multi-Turn | — | 1413 |

## FAQ

### Is Codestral better than MiniMax-M2.7?

MiniMax-M2.7 is the stronger model overall, scoring 37.4 to 30.1 on the Noometry Index.

### Which is cheaper, Codestral or MiniMax-M2.7?

Codestral is cheaper. It lists at $0.30 per million input tokens and $0.90 per million output tokens; MiniMax-M2.7 lists at $0.30 and $1.20.

### Is Codestral or MiniMax-M2.7 better for coding?

MiniMax-M2.7 scores higher on coding benchmarks: 41.4 versus 26.9 in the Noometry coding category.

### Which has the bigger context window?

Codestral does, with 256K tokens against 205K.

### How many benchmarks do Codestral and MiniMax-M2.7 share?

1 benchmark has published results for both models. Codestral has 7 scored results on Noometry and MiniMax-M2.7 has 30.