# MiniMax-M2.5 vs Mixtral 8x22B

> MiniMax-M2.5 is the stronger model overall, scoring 38.1 to 26.7 on the Noometry Index.

- Canonical page: https://noometry.com/compare/minimax-m2-5-vs-mixtral-8x22b
- Last updated: 2026-10-10
- Shared benchmarks: 18

## Summary

- They share 18 benchmarks with published results for both. MiniMax-M2.5 scores higher in 8 categories and Mixtral 8x22B in 1 category; 9 gaps are clear of the uncertainty.
- The widest gap is in coding, where MiniMax-M2.5 leads 47.9 to 23.8.
- MiniMax-M2.5 is cheaper at $0.30 / $1.20 per million input/output tokens, against $2 / $6 for Mixtral 8x22B.
- MiniMax-M2.5 accepts more context: 205K tokens versus 64K.

## Snapshot

| | MiniMax-M2.5 | Mixtral 8x22B |
|---|---|---|
| Provider | MiniMax | Mistral AI |
| Noometry Index | 38.1 | 26.7 |
| Rank | 181 | 330 |
| Context | 205K | 64K |
| Input $/M | $0.30 | $2 |
| Output $/M | $1.20 | $6 |
| Weights | Open | Open |

## Coding

- MiniMax-M2.5: 47.9 (#53)
- Mixtral 8x22B: 23.8 (#324)

| Benchmark | MiniMax-M2.5 | Mixtral 8x22B |
|---|---|---|
| LMArena Coding | 1380 | 1166 |
| SWE-bench Verified (bash only) | 75.8% | — |
| LMArena WebDev | 1386 | — |
| SWE-bench Multilingual | 68.3% | — |
| WeirdML | — | 3.2% |
| BigCodeBench Instruct | — | 40.6% |
| BigCodeBench Complete | — | 50.2% |
| ALE-Bench | 618.17 | — |
| HumanEval+ | — | 72% |
| MBPP+ | — | 64.3% |

## Agentic & Tool Use

- MiniMax-M2.5: 30.2 (#70)
- Mixtral 8x22B: 22.8 (#119)

| Benchmark | MiniMax-M2.5 | Mixtral 8x22B |
|---|---|---|
| Terminal-Bench | 42.7% | — |
| Cybench | — | 7.5% |
| Vending-Bench 2 | -23.16 | — |

## Reasoning

- MiniMax-M2.5: 17.6 (#281)
- Mixtral 8x22B: 19.1 (#246)

| Benchmark | MiniMax-M2.5 | Mixtral 8x22B |
|---|---|---|
| LMArena Hard Prompts | 1372 | 1150 |
| Epoch Capabilities Index | 146.68 | 122 |
| ARC-AGI-2 | 4.9% | — |
| Kagi LLM Benchmark | 55.2% | — |
| NYT Connections (extended) | 16.8% | — |
| ARC-AGI-1 | 63.7% | — |
| DTBench | — | 55.1% |
| ForecastBench | — | 56.3 |

## Math

- MiniMax-M2.5: 25.8 (#242)
- Mixtral 8x22B: 21.2 (#271)

| Benchmark | MiniMax-M2.5 | Mixtral 8x22B |
|---|---|---|
| LMArena Math | 1378 | 1184 |
| ProofBench | 4% | — |
| Omni-MATH | — | 16.3% |
| MATH Level 5 | — | 24.2% |

## Knowledge

- MiniMax-M2.5: 38.6 (#132)
- Mixtral 8x22B: 15.1 (#288)

| Benchmark | MiniMax-M2.5 | Mixtral 8x22B |
|---|---|---|
| LMArena Expert | 1378 | 1113 |
| GPQA Diamond | — | 34.1% |
| MMLU-Pro | — | 46% |
| Vectara Hallucination Rate | 9.1% | — |
| GPQA (HELM) | — | 33.4% |
| MMLU | — | 77.8% |

## Multilingual

- MiniMax-M2.5: 47.3 (#147)
- Mixtral 8x22B: 32.9 (#250)

| Benchmark | MiniMax-M2.5 | Mixtral 8x22B |
|---|---|---|
| LMArena Non-English | 1338 | 1128 |
| LMArena Chinese | 1392 | 1116 |
| LMArena French | 1363 | 1165 |
| LMArena German | 1361 | 1141 |
| LMArena Japanese | 1169 | 1037 |
| LMArena Korean | 1232 | 1056 |
| LMArena Russian | 1359 | 1158 |
| LMArena Spanish | 1354 | 1150 |

## Instruction Following

- MiniMax-M2.5: 71.7 (#143)
- Mixtral 8x22B: 57.9 (#261)

| Benchmark | MiniMax-M2.5 | Mixtral 8x22B |
|---|---|---|
| LMArena Instruction Following | 1353 | 1147 |
| IFEval | — | 72.4% |

## Long Context

- MiniMax-M2.5: 37.4 (#211)
- Mixtral 8x22B: 34.6 (#242)

| Benchmark | MiniMax-M2.5 | Mixtral 8x22B |
|---|---|---|
| LMArena Longer Query | 1367 | 1144 |
| CL-bench | 11.4% | — |
| CL-bench Life | 6.3% | — |

## Writing & Preference

- MiniMax-M2.5: 54.1 (#149)
- Mixtral 8x22B: 37.1 (#257)

| Benchmark | MiniMax-M2.5 | Mixtral 8x22B |
|---|---|---|
| LMArena Text | 1359 | 1162 |
| LMArena Creative Writing | 1331 | 1141 |
| LMArena Multi-Turn | 1364 | 1130 |
| EQ-Bench Creative Writing | 1361 | — |
| WildBench | — | 71.1% |

## FAQ

### Is MiniMax-M2.5 better than Mixtral 8x22B?

MiniMax-M2.5 is the stronger model overall, scoring 38.1 to 26.7 on the Noometry Index.

### Which is cheaper, MiniMax-M2.5 or Mixtral 8x22B?

MiniMax-M2.5 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-M2.5 or Mixtral 8x22B better for coding?

MiniMax-M2.5 scores higher on coding benchmarks: 47.9 versus 23.8 in the Noometry coding category.

### Which has the bigger context window?

MiniMax-M2.5 does, with 205K tokens against 64K.

### How many benchmarks do MiniMax-M2.5 and Mixtral 8x22B share?

18 benchmarks have published results for both models. MiniMax-M2.5 has 33 scored results on Noometry and Mixtral 8x22B has 34.