# MiniMax-M2.1 vs Phi-4 Mini

> MiniMax-M2.1 is the stronger model overall, scoring 38.9 to 30.9 on the Noometry Index. Phi-4 Mini costs 4.0× less per token, which makes it the better buy when MiniMax-M2.1's lead doesn't matter for your workload.

- Canonical page: https://noometry.com/compare/minimax-m2-1-vs-phi-4-mini
- Last updated: 2026-10-11
- Shared benchmarks: 1

## Summary

- They share 1 benchmark with published results for both. MiniMax-M2.1 scores higher in 2 categories and Phi-4 Mini in 1 category; 3 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where MiniMax-M2.1 leads 38.3 to 25.3.
- The biggest single-benchmark swing is Vectara Hallucination Rate: 11.8% for MiniMax-M2.1 and 23.5% for Phi-4 Mini.
- Phi-4 Mini is cheaper at $0.075 / $0.30 per million input/output tokens, against $0.30 / $1.20 for MiniMax-M2.1.
- MiniMax-M2.1 accepts more context: 205K tokens versus 128K.

## Snapshot

| | MiniMax-M2.1 | Phi-4 Mini |
|---|---|---|
| Provider | MiniMax | Microsoft |
| Noometry Index | 38.9 | 30.9 |
| Rank | 178 | 283 |
| Context | 205K | 128K |
| Input $/M | $0.30 | $0.075 |
| Output $/M | $1.20 | $0.30 |
| Weights | Open | Open |

## Coding

- MiniMax-M2.1: 40.4 (#143)
- Phi-4 Mini: 28.1 (#317)

| Benchmark | MiniMax-M2.1 | Phi-4 Mini |
|---|---|---|
| LMArena WebDev | 1384 | — |
| SciCode | — | 10.8% |
| LMArena Coding | 1421 | — |
| ALE-Bench | 623.83 | — |

## Agentic & Tool Use

- MiniMax-M2.1: 27.9 (#98)
- Phi-4 Mini: —

| Benchmark | MiniMax-M2.1 | Phi-4 Mini |
|---|---|---|
| Terminal-Bench | 36.6% | — |

## Reasoning

- MiniMax-M2.1: 16.6 (#302)
- Phi-4 Mini: 22.4 (#195)

| Benchmark | MiniMax-M2.1 | Phi-4 Mini |
|---|---|---|
| NYT Connections (extended) | 11.2% | — |
| CritPt | — | 0% |
| LMArena Hard Prompts | 1411 | — |

## Math

- MiniMax-M2.1: 38.3 (#138)
- Phi-4 Mini: —

| Benchmark | MiniMax-M2.1 | Phi-4 Mini |
|---|---|---|
| LMArena Math | 1397 | — |

## Knowledge

- MiniMax-M2.1: 38.3 (#147)
- Phi-4 Mini: 25.3 (#262)

| Benchmark | MiniMax-M2.1 | Phi-4 Mini |
|---|---|---|
| Vectara Hallucination Rate | 11.8% | 23.5% |
| LMArena Expert | 1431 | — |

## Multilingual

- MiniMax-M2.1: 50.0 (#128)
- Phi-4 Mini: —

| Benchmark | MiniMax-M2.1 | Phi-4 Mini |
|---|---|---|
| LMArena Non-English | 1378 | — |
| LMArena Chinese | 1430 | — |
| LMArena French | 1404 | — |
| LMArena German | 1381 | — |
| LMArena Japanese | 1287 | — |
| LMArena Korean | 1298 | — |
| LMArena Russian | 1387 | — |
| LMArena Spanish | 1397 | — |

## Instruction Following

- MiniMax-M2.1: 73.8 (#112)
- Phi-4 Mini: —

| Benchmark | MiniMax-M2.1 | Phi-4 Mini |
|---|---|---|
| LMArena Instruction Following | 1400 | — |

## Long Context

- MiniMax-M2.1: 43.2 (#101)
- Phi-4 Mini: —

| Benchmark | MiniMax-M2.1 | Phi-4 Mini |
|---|---|---|
| LMArena Longer Query | 1416 | — |

## Writing & Preference

- MiniMax-M2.1: 58.3 (#120)
- Phi-4 Mini: —

| Benchmark | MiniMax-M2.1 | Phi-4 Mini |
|---|---|---|
| LMArena Text | 1392 | — |
| LMArena Creative Writing | 1361 | — |
| LMArena Multi-Turn | 1396 | — |

## FAQ

### Is MiniMax-M2.1 better than Phi-4 Mini?

MiniMax-M2.1 is the stronger model overall, scoring 38.9 to 30.9 on the Noometry Index. Phi-4 Mini costs 4.0× less per token, which makes it the better buy when MiniMax-M2.1's lead doesn't matter for your workload.

### Which is cheaper, MiniMax-M2.1 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-M2.1 lists at $0.30 and $1.20.

### Is MiniMax-M2.1 or Phi-4 Mini better for coding?

MiniMax-M2.1 scores higher on coding benchmarks: 40.4 versus 28.1 in the Noometry coding category.

### Which has the bigger context window?

MiniMax-M2.1 does, with 205K tokens against 128K.

### How many benchmarks do MiniMax-M2.1 and Phi-4 Mini share?

1 benchmark has published results for both models. MiniMax-M2.1 has 22 scored results on Noometry and Phi-4 Mini has 3.