# MiniMax-M2.7 vs Mixtral 8x22B

> MiniMax-M2.7 is the stronger model overall, scoring 37.4 to 26.7 on the Noometry Index.

- Canonical page: https://noometry.com/compare/minimax-m2-7-vs-mixtral-8x22b
- Last updated: 2026-10-10
- Shared benchmarks: 19

## Summary

- They share 19 benchmarks with published results for both. MiniMax-M2.7 scores higher in 8 categories and Mixtral 8x22B in 1 category; 8 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where MiniMax-M2.7 leads 37.1 to 15.1.
- The biggest single-benchmark swing is WeirdML: 37% for MiniMax-M2.7 and 3.2% for Mixtral 8x22B.
- MiniMax-M2.7 is cheaper at $0.30 / $1.20 per million input/output tokens, against $2 / $6 for Mixtral 8x22B.
- MiniMax-M2.7 accepts more context: 205K tokens versus 64K.

## Snapshot

| | MiniMax-M2.7 | Mixtral 8x22B |
|---|---|---|
| Provider | MiniMax | Mistral AI |
| Noometry Index | 37.4 | 26.7 |
| Rank | 188 | 330 |
| Context | 205K | 64K |
| Input $/M | $0.30 | $2 |
| Output $/M | $1.20 | $6 |
| Weights | Open | Open |

## Coding

- MiniMax-M2.7: 41.4 (#115)
- Mixtral 8x22B: 23.8 (#324)

| Benchmark | MiniMax-M2.7 | Mixtral 8x22B |
|---|---|---|
| WeirdML | 37% | 3.2% |
| LMArena Coding | 1454 | 1166 |
| LMArena WebDev | 1397 | — |
| SciCode | 47% | — |
| BigCodeBench Instruct | — | 40.6% |
| BigCodeBench Complete | — | 50.2% |
| ALE-Bench | 599.25 | — |
| HumanEval+ | — | 72% |
| MBPP+ | — | 64.3% |

## Agentic & Tool Use

- MiniMax-M2.7: 24.9 (#103)
- Mixtral 8x22B: 22.8 (#119)

| Benchmark | MiniMax-M2.7 | Mixtral 8x22B |
|---|---|---|
| Terminal-Bench | 45.1% | — |
| Cybench | — | 7.5% |
| ExploitBench | 13.3% | — |
| GBAEval | 0% | — |

## Reasoning

- MiniMax-M2.7: 19.0 (#248)
- Mixtral 8x22B: 19.1 (#246)

| Benchmark | MiniMax-M2.7 | Mixtral 8x22B |
|---|---|---|
| LMArena Hard Prompts | 1422 | 1150 |
| Epoch Capabilities Index | 145.84 | 122 |
| NYT Connections (extended) | 24.7% | — |
| CritPt | 0.6% | — |
| Thematic Generalization | 39.3% | — |
| DTBench | — | 55.1% |
| ForecastBench | — | 56.3 |

## Math

- MiniMax-M2.7: 24.9 (#254)
- Mixtral 8x22B: 21.2 (#271)

| Benchmark | MiniMax-M2.7 | Mixtral 8x22B |
|---|---|---|
| LMArena Math | 1420 | 1184 |
| ProofBench | 3% | — |
| Omni-MATH | — | 16.3% |
| MATH Level 5 | — | 24.2% |

## Knowledge

- MiniMax-M2.7: 37.1 (#151)
- Mixtral 8x22B: 15.1 (#288)

| Benchmark | MiniMax-M2.7 | Mixtral 8x22B |
|---|---|---|
| LMArena Expert | 1443 | 1113 |
| GPQA Diamond | — | 34.1% |
| MMLU-Pro | — | 46% |
| Vectara Hallucination Rate | 12.9% | — |
| GPQA (HELM) | — | 33.4% |
| MMLU | — | 77.8% |

## Multilingual

- MiniMax-M2.7: 50.5 (#120)
- Mixtral 8x22B: 32.9 (#250)

| Benchmark | MiniMax-M2.7 | Mixtral 8x22B |
|---|---|---|
| LMArena Non-English | 1382 | 1128 |
| LMArena Chinese | 1439 | 1116 |
| LMArena French | 1422 | 1165 |
| LMArena German | 1398 | 1141 |
| LMArena Japanese | 1261 | 1037 |
| LMArena Korean | 1313 | 1056 |
| LMArena Russian | 1383 | 1158 |
| LMArena Spanish | 1403 | 1150 |

## Instruction Following

- MiniMax-M2.7: 74.2 (#101)
- Mixtral 8x22B: 57.9 (#261)

| Benchmark | MiniMax-M2.7 | Mixtral 8x22B |
|---|---|---|
| LMArena Instruction Following | 1404 | 1147 |
| IFEval | — | 72.4% |

## Long Context

- MiniMax-M2.7: 43.3 (#94)
- Mixtral 8x22B: 34.6 (#242)

| Benchmark | MiniMax-M2.7 | Mixtral 8x22B |
|---|---|---|
| LMArena Longer Query | 1419 | 1144 |

## Writing & Preference

- MiniMax-M2.7: 59.1 (#107)
- Mixtral 8x22B: 37.1 (#257)

| Benchmark | MiniMax-M2.7 | Mixtral 8x22B |
|---|---|---|
| LMArena Text | 1404 | 1162 |
| LMArena Creative Writing | 1354 | 1141 |
| LMArena Multi-Turn | 1413 | 1130 |
| WildBench | — | 71.1% |

## FAQ

### Is MiniMax-M2.7 better than Mixtral 8x22B?

MiniMax-M2.7 is the stronger model overall, scoring 37.4 to 26.7 on the Noometry Index.

### Which is cheaper, MiniMax-M2.7 or Mixtral 8x22B?

MiniMax-M2.7 is cheaper. It lists at $0.30 per million input tokens and $1.20 per million output tokens; Mixtral 8x22B lists at $2 and $6.

### Is MiniMax-M2.7 or Mixtral 8x22B better for coding?

MiniMax-M2.7 scores higher on coding benchmarks: 41.4 versus 23.8 in the Noometry coding category.

### Which has the bigger context window?

MiniMax-M2.7 does, with 205K tokens against 64K.

### How many benchmarks do MiniMax-M2.7 and Mixtral 8x22B share?

19 benchmarks have published results for both models. MiniMax-M2.7 has 30 scored results on Noometry and Mixtral 8x22B has 34.