# MiniMax-M3 vs Phi 3 Mini 4k Instruct

> MiniMax-M3 is the stronger model overall, scoring 43.8 to 27.9 on the Noometry Index.

- Canonical page: https://noometry.com/compare/minimax-m3-vs-phi-3-mini-4k-instruct
- Last updated: 2026-10-11
- Shared benchmarks: 18

## Summary

- They share 18 benchmarks with published results for both. MiniMax-M3 scores higher in 8 categories and Phi 3 Mini 4k Instruct in 0 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where MiniMax-M3 leads 62.1 to 27.6.
- The biggest single-benchmark swing is Chess Puzzles: 14% for MiniMax-M3 and 0% for Phi 3 Mini 4k Instruct.

## Snapshot

| | MiniMax-M3 | Phi 3 Mini 4k Instruct |
|---|---|---|
| Provider | MiniMax | Microsoft |
| Noometry Index | 43.8 | 27.9 |
| Rank | 85 | 328 |
| Context | 1M | — |
| Input $/M | $0.30 | — |
| Output $/M | $1.20 | — |
| Weights | Open | Open |

## Coding

- MiniMax-M3: 41.8 (#118)
- Phi 3 Mini 4k Instruct: 26.6 (#323)

| Benchmark | MiniMax-M3 | Phi 3 Mini 4k Instruct |
|---|---|---|
| LMArena Coding | 1469 | 1093 |
| FrontierCode | 14.7% | — |
| LMArena WebDev | 1482 | — |
| SciCode | 47.1% | — |
| LiveBench Coding | — | 15.5% |
| ALE-Bench | 640.02 | — |
| HumanEval+ | — | 59.1% |
| MBPP+ | — | 54.2% |

## Agentic & Tool Use

- MiniMax-M3: 22.6 (#130)
- Phi 3 Mini 4k Instruct: —

| Benchmark | MiniMax-M3 | Phi 3 Mini 4k Instruct |
|---|---|---|
| APEX-Agents | 37.7% | — |
| OSWorld 2.0 | 4.6% | — |
| GBAEval | 0.9% | — |
| Vending-Bench 2 | 2,158 | — |

## Reasoning

- MiniMax-M3: 30.1 (#87)
- Phi 3 Mini 4k Instruct: 14.1 (#328)

| Benchmark | MiniMax-M3 | Phi 3 Mini 4k Instruct |
|---|---|---|
| Chess Puzzles | 14% | 0% |
| LMArena Hard Prompts | 1447 | 1072 |
| SimpleBench | 45.8% | — |
| NYT Connections (extended) | 65.1% | — |
| CritPt | 3.7% | — |
| LiveBench Reasoning | — | 26.8% |
| Mystery Game Puzzles | 8% | — |
| DTBench | 78.9% | — |
| LiveBench Data Analysis | — | 34.7% |
| LMCA | 33.7% | — |
| Surface Evolver Bench | 55% | — |
| Adversarial NLI | — | 52.8% |
| BIG-Bench Hard | — | 71.7% |
| Epoch Capabilities Index | 146.95 | — |
| ForecastBench | 61.4 | — |
| HellaSwag | — | 76.7% |
| LiveBench | — | 22.4% |
| WinoGrande | — | 70.8% |

## Math

- MiniMax-M3: 40.0 (#95)
- Phi 3 Mini 4k Instruct: 26.6 (#257)

| Benchmark | MiniMax-M3 | Phi 3 Mini 4k Instruct |
|---|---|---|
| LMArena Math | 1429 | 1111 |
| OTIS Mock AIME 2024-2025 | 71.1% | — |
| ProofBench | 18% | — |
| LiveBench Math | — | 15.7% |

## Knowledge

- MiniMax-M3: 58.4 (#35)
- Phi 3 Mini 4k Instruct: 28.5 (#246)

| Benchmark | MiniMax-M3 | Phi 3 Mini 4k Instruct |
|---|---|---|
| LMArena Expert | 1461 | 1045 |
| GPQA Diamond | 90.9% | — |
| ARC (AI2) Challenge | — | 84.9% |
| MMLU | — | 68.8% |
| OpenBookQA | — | 88% |
| TriviaQA | — | 64% |

## Multimodal

- MiniMax-M3: 40.2 (#51)
- Phi 3 Mini 4k Instruct: —

| Benchmark | MiniMax-M3 | Phi 3 Mini 4k Instruct |
|---|---|---|
| LMArena Vision | 1253 | — |
| LMArena Document | 1435 | — |

## Multilingual

- MiniMax-M3: 53.0 (#75)
- Phi 3 Mini 4k Instruct: 26.3 (#280)

| Benchmark | MiniMax-M3 | Phi 3 Mini 4k Instruct |
|---|---|---|
| LMArena Non-English | 1420 | 1021 |
| LMArena Chinese | 1463 | 1021 |
| LMArena French | 1447 | 1076 |
| LMArena German | 1426 | 1044 |
| LMArena Japanese | 1381 | 935 |
| LMArena Korean | 1372 | 905 |
| LMArena Russian | 1428 | 1022 |
| LMArena Spanish | 1432 | 1085 |

## Instruction Following

- MiniMax-M3: 75.5 (#62)
- Phi 3 Mini 4k Instruct: 47.7 (#303)

| Benchmark | MiniMax-M3 | Phi 3 Mini 4k Instruct |
|---|---|---|
| LMArena Instruction Following | 1433 | 1053 |
| LiveBench Instruction Following | — | 39.1% |

## Long Context

- MiniMax-M3: 44.2 (#72)
- Phi 3 Mini 4k Instruct: 31.7 (#276)

| Benchmark | MiniMax-M3 | Phi 3 Mini 4k Instruct |
|---|---|---|
| LMArena Longer Query | 1445 | 1044 |

## Writing & Preference

- MiniMax-M3: 62.1 (#83)
- Phi 3 Mini 4k Instruct: 27.6 (#300)

| Benchmark | MiniMax-M3 | Phi 3 Mini 4k Instruct |
|---|---|---|
| LMArena Text | 1433 | 1073 |
| LMArena Creative Writing | 1404 | 1037 |
| LMArena Multi-Turn | 1442 | 1018 |
| EQ-Bench 4 | 1150 | — |
| LiveBench Language | — | 9.2% |

## FAQ

### Is MiniMax-M3 better than Phi 3 Mini 4k Instruct?

MiniMax-M3 is the stronger model overall, scoring 43.8 to 27.9 on the Noometry Index.

### Is MiniMax-M3 or Phi 3 Mini 4k Instruct better for coding?

MiniMax-M3 scores higher on coding benchmarks: 41.8 versus 26.6 in the Noometry coding category.

### How many benchmarks do MiniMax-M3 and Phi 3 Mini 4k Instruct share?

18 benchmarks have published results for both models. MiniMax-M3 has 41 scored results on Noometry and Phi 3 Mini 4k Instruct has 35.