# Magistral Medium vs MiniMax-M2.7

> MiniMax-M2.7 is the stronger model overall, scoring 37.4 to 34.8 on the Noometry Index.

- Canonical page: https://noometry.com/compare/magistral-medium-vs-minimax-m2-7
- Last updated: 2026-10-10
- Shared benchmarks: 19

## Summary

- They share 19 benchmarks with published results for both. Magistral Medium scores higher in 1 category and MiniMax-M2.7 in 7 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where MiniMax-M2.7 leads 59.1 to 46.5.
- The biggest single-benchmark swing is SciCode: 39.2% for Magistral Medium and 47% for MiniMax-M2.7.
- MiniMax-M2.7 is cheaper at $0.30 / $1.20 per million input/output tokens, against $2 / $5 for Magistral Medium.
- MiniMax-M2.7 accepts more context: 205K tokens versus 128K.

## Snapshot

| | Magistral Medium | MiniMax-M2.7 |
|---|---|---|
| Provider | Mistral AI | MiniMax |
| Noometry Index | 34.8 | 37.4 |
| Rank | 224 | 188 |
| Context | 128K | 205K |
| Input $/M | $2 | $0.30 |
| Output $/M | $5 | $1.20 |
| Weights | Open | Open |

## Coding

- Magistral Medium: 38.6 (#161)
- MiniMax-M2.7: 41.4 (#115)

| Benchmark | Magistral Medium | MiniMax-M2.7 |
|---|---|---|
| SciCode | 39.2% | 47% |
| LMArena Coding | 1319 | 1454 |
| LMArena WebDev | — | 1397 |
| WeirdML | — | 37% |
| ALE-Bench | — | 599.25 |

## Agentic & Tool Use

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

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

## Reasoning

- Magistral Medium: 8.7 (#342)
- MiniMax-M2.7: 19.0 (#248)

| Benchmark | Magistral Medium | MiniMax-M2.7 |
|---|---|---|
| CritPt | 0.3% | 0.6% |
| LMArena Hard Prompts | 1267 | 1422 |
| ARC-AGI-2 | 0% | — |
| Kagi LLM Benchmark | 16.2% | — |
| NYT Connections (extended) | — | 24.7% |
| ARC-AGI-1 | 6.1% | — |
| Thematic Generalization | — | 39.3% |
| Epoch Capabilities Index | — | 145.84 |

## Math

- Magistral Medium: 32.4 (#187)
- MiniMax-M2.7: 24.9 (#254)

| Benchmark | Magistral Medium | MiniMax-M2.7 |
|---|---|---|
| LMArena Math | 1249 | 1420 |
| ProofBench | — | 3% |

## Knowledge

- Magistral Medium: 32.9 (#199)
- MiniMax-M2.7: 37.1 (#151)

| Benchmark | Magistral Medium | MiniMax-M2.7 |
|---|---|---|
| LMArena Expert | 1222 | 1443 |
| Vectara Hallucination Rate | — | 12.9% |

## Multilingual

- Magistral Medium: 39.8 (#219)
- MiniMax-M2.7: 50.5 (#120)

| Benchmark | Magistral Medium | MiniMax-M2.7 |
|---|---|---|
| LMArena Non-English | 1232 | 1382 |
| LMArena Chinese | 1225 | 1439 |
| LMArena French | 1268 | 1422 |
| LMArena German | 1248 | 1398 |
| LMArena Japanese | 1176 | 1261 |
| LMArena Korean | 1125 | 1313 |
| LMArena Russian | 1224 | 1383 |
| LMArena Spanish | 1269 | 1403 |

## Instruction Following

- Magistral Medium: 66.2 (#207)
- MiniMax-M2.7: 74.2 (#101)

| Benchmark | Magistral Medium | MiniMax-M2.7 |
|---|---|---|
| LMArena Instruction Following | 1254 | 1404 |

## Long Context

- Magistral Medium: 39.3 (#178)
- MiniMax-M2.7: 43.3 (#94)

| Benchmark | Magistral Medium | MiniMax-M2.7 |
|---|---|---|
| LMArena Longer Query | 1295 | 1419 |

## Writing & Preference

- Magistral Medium: 46.5 (#214)
- MiniMax-M2.7: 59.1 (#107)

| Benchmark | Magistral Medium | MiniMax-M2.7 |
|---|---|---|
| LMArena Text | 1255 | 1404 |
| LMArena Creative Writing | 1245 | 1354 |
| LMArena Multi-Turn | 1275 | 1413 |

## FAQ

### Is Magistral Medium better than MiniMax-M2.7?

MiniMax-M2.7 is the stronger model overall, scoring 37.4 to 34.8 on the Noometry Index.

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

MiniMax-M2.7 is cheaper. It lists at $0.30 per million input tokens and $1.20 per million output tokens; Magistral Medium lists at $2 and $5.

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

MiniMax-M2.7 scores higher on coding benchmarks: 41.4 versus 38.6 in the Noometry coding category.

### Which has the bigger context window?

MiniMax-M2.7 does, with 205K tokens against 128K.

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

19 benchmarks have published results for both models. Magistral Medium has 22 scored results on Noometry and MiniMax-M2.7 has 30.