# MiniMax-M2 vs Phi-4 Mini

> MiniMax-M2 is the stronger model overall, scoring 36.9 to 30.4 on the Noometry Index. Phi-4 Mini costs 4.0× less per token, which makes it the better buy when MiniMax-M2's lead doesn't matter for your workload.

- Canonical page: https://noometry.com/compare/minimax-m2-vs-phi-4-mini
- Last updated: 2026-10-10
- Shared benchmarks: 0

## Summary

- The widest gap is in knowledge, where MiniMax-M2 leads 36.3 to 24.8.
- Phi-4 Mini is cheaper at $0.075 / $0.30 per million input/output tokens, against $0.30 / $1.20 for MiniMax-M2.
- MiniMax-M2 accepts more context: 205K tokens versus 128K.

## Snapshot

| | MiniMax-M2 | Phi-4 Mini |
|---|---|---|
| Provider | MiniMax | Microsoft |
| Noometry Index | 36.9 | 30.4 |
| Rank | 201 | 280 |
| Context | 205K | 128K |
| Input $/M | $0.30 | $0.075 |
| Output $/M | $1.20 | $0.30 |
| Weights | Open | Open |

## Coding

- MiniMax-M2: 39.1 (#151)
- Phi-4 Mini: 27.6 (#312)

| Benchmark | MiniMax-M2 | Phi-4 Mini |
|---|---|---|
| SWE-bench Verified (bash only) | 61% | — |
| LMArena WebDev | 1297 | — |
| SciCode | — | 10.8% |
| LMArena Coding | 1370 | — |

## Agentic & Tool Use

- MiniMax-M2: 24.9 (#102)
- Phi-4 Mini: —

| Benchmark | MiniMax-M2 | Phi-4 Mini |
|---|---|---|
| Terminal-Bench | 30% | — |
| Vending-Bench 2 | 160.6 | — |

## Reasoning

- MiniMax-M2: 18.6 (#256)
- Phi-4 Mini: 21.7 (#190)

| Benchmark | MiniMax-M2 | Phi-4 Mini |
|---|---|---|
| Kagi LLM Benchmark | 57.8% | — |
| NYT Connections (extended) | 14.8% | — |
| CritPt | — | 0% |
| LMArena Hard Prompts | 1357 | — |

## Math

- MiniMax-M2: 34.6 (#158)
- Phi-4 Mini: —

| Benchmark | MiniMax-M2 | Phi-4 Mini |
|---|---|---|
| LMArena Math | 1350 | — |

## Knowledge

- MiniMax-M2: 36.3 (#160)
- Phi-4 Mini: 24.8 (#261)

| Benchmark | MiniMax-M2 | Phi-4 Mini |
|---|---|---|
| Vectara Hallucination Rate | — | 23.5% |
| LMArena Expert | 1336 | — |

## Multilingual

- MiniMax-M2: 45.6 (#165)
- Phi-4 Mini: —

| Benchmark | MiniMax-M2 | Phi-4 Mini |
|---|---|---|
| LMArena Non-English | 1314 | — |
| LMArena Chinese | 1367 | — |
| LMArena French | 1336 | — |
| LMArena German | 1366 | — |
| LMArena Russian | 1332 | — |
| LMArena Spanish | 1326 | — |

## Instruction Following

- MiniMax-M2: 70.4 (#160)
- Phi-4 Mini: —

| Benchmark | MiniMax-M2 | Phi-4 Mini |
|---|---|---|
| LMArena Instruction Following | 1329 | — |

## Long Context

- MiniMax-M2: 40.5 (#148)
- Phi-4 Mini: —

| Benchmark | MiniMax-M2 | Phi-4 Mini |
|---|---|---|
| LMArena Longer Query | 1332 | — |

## Writing & Preference

- MiniMax-M2: 53.3 (#157)
- Phi-4 Mini: —

| Benchmark | MiniMax-M2 | Phi-4 Mini |
|---|---|---|
| LMArena Text | 1340 | — |
| LMArena Creative Writing | 1288 | — |
| LMArena Multi-Turn | 1362 | — |

## FAQ

### Is MiniMax-M2 better than Phi-4 Mini?

MiniMax-M2 is the stronger model overall, scoring 36.9 to 30.4 on the Noometry Index. Phi-4 Mini costs 4.0× less per token, which makes it the better buy when MiniMax-M2's lead doesn't matter for your workload.

### Which is cheaper, MiniMax-M2 or Phi-4 Mini?

Phi-4 Mini is cheaper. It lists at $0.075 per million input tokens and $0.30 per million output tokens; MiniMax-M2 lists at $0.30 and $1.20.

### Is MiniMax-M2 or Phi-4 Mini better for coding?

MiniMax-M2 scores higher on coding benchmarks: 39.1 versus 27.6 in the Noometry coding category.

### Which has the bigger context window?

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

### How many benchmarks do MiniMax-M2 and Phi-4 Mini share?

0 benchmarks have published results for both models. MiniMax-M2 has 21 scored results on Noometry and Phi-4 Mini has 3.