# MiniMax-M2.1 vs Phi 3 Medium 4k Instruct

> MiniMax-M2.1 is the stronger model overall, scoring 38.9 to 33.0 on the Noometry Index.

- Canonical page: https://noometry.com/compare/minimax-m2-1-vs-phi-3-medium-4k-instruct
- Last updated: 2026-10-10
- Shared benchmarks: 17

## Summary

- They share 17 benchmarks with published results for both. MiniMax-M2.1 scores higher in 7 categories and Phi 3 Medium 4k Instruct in 1 category; 8 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where MiniMax-M2.1 leads 58.3 to 34.1.

## Snapshot

| | MiniMax-M2.1 | Phi 3 Medium 4k Instruct |
|---|---|---|
| Provider | MiniMax | Microsoft |
| Noometry Index | 38.9 | 33.0 |
| Rank | 178 | 250 |
| Context | 205K | — |
| Input $/M | $0.30 | — |
| Output $/M | $1.20 | — |
| Weights | Open | Open |

## Coding

- MiniMax-M2.1: 40.4 (#143)
- Phi 3 Medium 4k Instruct: 32.9 (#268)

| Benchmark | MiniMax-M2.1 | Phi 3 Medium 4k Instruct |
|---|---|---|
| LMArena Coding | 1421 | 1130 |
| LMArena WebDev | 1384 | — |
| ALE-Bench | 623.83 | — |

## Agentic & Tool Use

- MiniMax-M2.1: 27.9 (#98)
- Phi 3 Medium 4k Instruct: —

| Benchmark | MiniMax-M2.1 | Phi 3 Medium 4k Instruct |
|---|---|---|
| Terminal-Bench | 36.6% | — |

## Reasoning

- MiniMax-M2.1: 16.6 (#302)
- Phi 3 Medium 4k Instruct: 21.7 (#214)

| Benchmark | MiniMax-M2.1 | Phi 3 Medium 4k Instruct |
|---|---|---|
| LMArena Hard Prompts | 1411 | 1127 |
| NYT Connections (extended) | 11.2% | — |

## Math

- MiniMax-M2.1: 38.3 (#138)
- Phi 3 Medium 4k Instruct: 33.4 (#202)

| Benchmark | MiniMax-M2.1 | Phi 3 Medium 4k Instruct |
|---|---|---|
| LMArena Math | 1397 | 1173 |

## Knowledge

- MiniMax-M2.1: 38.3 (#147)
- Phi 3 Medium 4k Instruct: 30.2 (#229)

| Benchmark | MiniMax-M2.1 | Phi 3 Medium 4k Instruct |
|---|---|---|
| LMArena Expert | 1431 | 1108 |
| Vectara Hallucination Rate | 11.8% | — |

## Multilingual

- MiniMax-M2.1: 50.0 (#128)
- Phi 3 Medium 4k Instruct: 30.6 (#263)

| Benchmark | MiniMax-M2.1 | Phi 3 Medium 4k Instruct |
|---|---|---|
| LMArena Non-English | 1378 | 1094 |
| LMArena Chinese | 1430 | 1108 |
| LMArena French | 1404 | 1110 |
| LMArena German | 1381 | 1101 |
| LMArena Japanese | 1287 | 1042 |
| LMArena Korean | 1298 | 954 |
| LMArena Russian | 1387 | 1145 |
| LMArena Spanish | 1397 | 1095 |

## Instruction Following

- MiniMax-M2.1: 73.8 (#112)
- Phi 3 Medium 4k Instruct: 57.6 (#268)

| Benchmark | MiniMax-M2.1 | Phi 3 Medium 4k Instruct |
|---|---|---|
| LMArena Instruction Following | 1400 | 1113 |

## Long Context

- MiniMax-M2.1: 43.2 (#101)
- Phi 3 Medium 4k Instruct: 34.0 (#255)

| Benchmark | MiniMax-M2.1 | Phi 3 Medium 4k Instruct |
|---|---|---|
| LMArena Longer Query | 1416 | 1120 |

## Writing & Preference

- MiniMax-M2.1: 58.3 (#120)
- Phi 3 Medium 4k Instruct: 34.1 (#272)

| Benchmark | MiniMax-M2.1 | Phi 3 Medium 4k Instruct |
|---|---|---|
| LMArena Text | 1392 | 1138 |
| LMArena Creative Writing | 1361 | 1107 |
| LMArena Multi-Turn | 1396 | 1088 |

## FAQ

### Is MiniMax-M2.1 better than Phi 3 Medium 4k Instruct?

MiniMax-M2.1 is the stronger model overall, scoring 38.9 to 33.0 on the Noometry Index.

### Is MiniMax-M2.1 or Phi 3 Medium 4k Instruct better for coding?

MiniMax-M2.1 scores higher on coding benchmarks: 40.4 versus 32.9 in the Noometry coding category.

### How many benchmarks do MiniMax-M2.1 and Phi 3 Medium 4k Instruct share?

17 benchmarks have published results for both models. MiniMax-M2.1 has 22 scored results on Noometry and Phi 3 Medium 4k Instruct has 17.