# MiniMax-M2.5 vs Ministral 8B

> MiniMax-M2.5 is the stronger model overall, scoring 38.3 to 28.2 on the Noometry Index. Ministral 8B costs 3.5× less per token, which makes it the better buy when MiniMax-M2.5's lead doesn't matter for your workload.

- Canonical page: https://noometry.com/compare/minimax-m2-5-vs-ministral-8b
- Last updated: 2026-10-10
- Shared benchmarks: 13

## Summary

- They share 13 benchmarks with published results for both. MiniMax-M2.5 scores higher in 8 categories and Ministral 8B in 1 category; 7 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where MiniMax-M2.5 leads 39.2 to 12.6.
- Ministral 8B is cheaper at $0.15 / $0.15 per million input/output tokens, against $0.30 / $1.20 for MiniMax-M2.5.
- Ministral 8B accepts more context: 262K tokens versus 205K.

## Snapshot

| | MiniMax-M2.5 | Ministral 8B |
|---|---|---|
| Provider | MiniMax | Mistral AI |
| Noometry Index | 38.3 | 28.2 |
| Rank | 188 | 325 |
| Context | 205K | 262K |
| Input $/M | $0.30 | $0.15 |
| Output $/M | $1.20 | $0.15 |
| Weights | Open | Open |

## Coding

- MiniMax-M2.5: 48.1 (#58)
- Ministral 8B: 35.0 (#230)

| Benchmark | MiniMax-M2.5 | Ministral 8B |
|---|---|---|
| LMArena Coding | 1381 | 1202 |
| SWE-bench Verified (bash only) | 75.8% | — |
| LMArena WebDev | 1387 | — |
| SWE-bench Multilingual | 68.3% | — |
| ALE-Bench | 618.17 | — |

## Agentic & Tool Use

- MiniMax-M2.5: 30.4 (#77)
- Ministral 8B: 16.4 (#148)

| Benchmark | MiniMax-M2.5 | Ministral 8B |
|---|---|---|
| Terminal-Bench | 42.7% | — |
| Berkeley Function Calling Leaderboard | — | 11.1% |
| Vending-Bench 2 | -23.16 | — |

## Reasoning

- MiniMax-M2.5: 17.5 (#292)
- Ministral 8B: 18.4 (#281)

| Benchmark | MiniMax-M2.5 | Ministral 8B |
|---|---|---|
| LMArena Hard Prompts | 1372 | 1191 |
| ARC-AGI-2 | 4.9% | — |
| Kagi LLM Benchmark | 55.2% | — |
| NYT Connections (extended) | 16.8% | — |
| ARC-AGI-1 | 63.7% | — |
| DTBench | — | 45.7% |
| Epoch Capabilities Index | 146.68 | — |

## Math

- MiniMax-M2.5: 26.9 (#253)
- Ministral 8B: 25.7 (#267)

| Benchmark | MiniMax-M2.5 | Ministral 8B |
|---|---|---|
| LMArena Math | 1378 | 1188 |
| ProofBench | 4% | — |
| MATH Level 5 | — | 14.9% |

## Knowledge

- MiniMax-M2.5: 39.2 (#135)
- Ministral 8B: 12.6 (#297)

| Benchmark | MiniMax-M2.5 | Ministral 8B |
|---|---|---|
| Vectara Hallucination Rate | 9.1% | 7.4% |
| LMArena Expert | 1379 | 1170 |
| GPQA Diamond | — | 27.1% |

## Multilingual

- MiniMax-M2.5: 47.1 (#152)
- Ministral 8B: 35.1 (#247)

| Benchmark | MiniMax-M2.5 | Ministral 8B |
|---|---|---|
| LMArena Non-English | 1338 | 1165 |
| LMArena Chinese | 1393 | 1193 |
| LMArena Russian | 1358 | 1195 |
| LMArena French | 1362 | — |
| LMArena German | 1362 | — |
| LMArena Japanese | 1171 | — |
| LMArena Korean | 1232 | — |
| LMArena Spanish | 1354 | — |

## Instruction Following

- MiniMax-M2.5: 71.5 (#148)
- Ministral 8B: 60.5 (#250)

| Benchmark | MiniMax-M2.5 | Ministral 8B |
|---|---|---|
| LMArena Instruction Following | 1353 | 1161 |

## Long Context

- MiniMax-M2.5: 37.5 (#216)
- Ministral 8B: 36.7 (#227)

| Benchmark | MiniMax-M2.5 | Ministral 8B |
|---|---|---|
| LMArena Longer Query | 1366 | 1212 |
| CL-bench | 11.4% | — |
| CL-bench Life | 6.3% | — |

## Writing & Preference

- MiniMax-M2.5: 53.9 (#153)
- Ministral 8B: 39.6 (#246)

| Benchmark | MiniMax-M2.5 | Ministral 8B |
|---|---|---|
| LMArena Text | 1359 | 1191 |
| LMArena Creative Writing | 1331 | 1175 |
| LMArena Multi-Turn | 1364 | 1166 |
| EQ-Bench Creative Writing | 1361 | — |

## FAQ

### Is MiniMax-M2.5 better than Ministral 8B?

MiniMax-M2.5 is the stronger model overall, scoring 38.3 to 28.2 on the Noometry Index. Ministral 8B costs 3.5× less per token, which makes it the better buy when MiniMax-M2.5's lead doesn't matter for your workload.

### Which is cheaper, MiniMax-M2.5 or Ministral 8B?

Ministral 8B is cheaper. It lists at $0.15 per million input tokens and $0.15 per million output tokens; MiniMax-M2.5 lists at $0.30 and $1.20.

### Is MiniMax-M2.5 or Ministral 8B better for coding?

MiniMax-M2.5 scores higher on coding benchmarks: 48.1 versus 35.0 in the Noometry coding category.

### Which has the bigger context window?

Ministral 8B does, with 262K tokens against 205K.

### How many benchmarks do MiniMax-M2.5 and Ministral 8B share?

13 benchmarks have published results for both models. MiniMax-M2.5 has 33 scored results on Noometry and Ministral 8B has 17.