# MiniMax-M3 vs Phi 3 Mini 4k Instruct June 2024

> MiniMax-M3 is the stronger model overall, scoring 43.5 to 30.7 on the Noometry Index.

- Canonical page: https://noometry.com/compare/minimax-m3-vs-phi-3-mini-4k-instruct-june
- Last updated: 2026-10-10
- Shared benchmarks: 15

## Summary

- They share 15 benchmarks with published results for both. MiniMax-M3 scores higher in 8 categories and Phi 3 Mini 4k Instruct June 2024 in 0 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where MiniMax-M3 leads 62.3 to 29.7.

## Snapshot

| | MiniMax-M3 | Phi 3 Mini 4k Instruct June 2024 |
|---|---|---|
| Provider | MiniMax | Microsoft |
| Noometry Index | 43.5 | 30.7 |
| Rank | 81 | 274 |
| Context | 1M | — |
| Input $/M | $0.30 | — |
| Output $/M | $1.20 | — |
| Weights | Open | Open |

## Coding

- MiniMax-M3: 41.5 (#111)
- Phi 3 Mini 4k Instruct June 2024: 31.2 (#275)

| Benchmark | MiniMax-M3 | Phi 3 Mini 4k Instruct June 2024 |
|---|---|---|
| LMArena Coding | 1470 | 1093 |
| FrontierCode | 14.7% | — |
| LMArena WebDev | 1482 | — |
| SciCode | 47.1% | — |
| ALE-Bench | 640.02 | — |

## Agentic & Tool Use

- MiniMax-M3: 22.5 (#121)
- Phi 3 Mini 4k Instruct June 2024: —

| Benchmark | MiniMax-M3 | Phi 3 Mini 4k Instruct June 2024 |
|---|---|---|
| APEX-Agents | 37.7% | — |
| OSWorld 2.0 | 4.6% | — |
| GBAEval | 0.9% | — |
| Vending-Bench 2 | 2,158 | — |

## Reasoning

- MiniMax-M3: 29.3 (#83)
- Phi 3 Mini 4k Instruct June 2024: 19.9 (#229)

| Benchmark | MiniMax-M3 | Phi 3 Mini 4k Instruct June 2024 |
|---|---|---|
| LMArena Hard Prompts | 1447 | 1088 |
| SimpleBench | 45.8% | — |
| NYT Connections (extended) | 65.1% | — |
| CritPt | 3.7% | — |
| Chess Puzzles | 14% | — |
| Mystery Game Puzzles | 8% | — |
| DTBench | 78.9% | — |
| LMCA | 33.7% | — |
| Surface Evolver Bench | 55% | — |
| Epoch Capabilities Index | 147 | — |
| ForecastBench | 61.4 | — |

## Math

- MiniMax-M3: 39.1 (#83)
- Phi 3 Mini 4k Instruct June 2024: 30.4 (#209)

| Benchmark | MiniMax-M3 | Phi 3 Mini 4k Instruct June 2024 |
|---|---|---|
| LMArena Math | 1432 | 1152 |
| OTIS Mock AIME 2024-2025 | 71.1% | — |
| ProofBench | 18% | — |

## Knowledge

- MiniMax-M3: 58.4 (#32)
- Phi 3 Mini 4k Instruct June 2024: 28.1 (#240)

| Benchmark | MiniMax-M3 | Phi 3 Mini 4k Instruct June 2024 |
|---|---|---|
| LMArena Expert | 1462 | 1051 |
| GPQA Diamond | 90.9% | — |

## Multimodal

- MiniMax-M3: 39.5 (#45)
- Phi 3 Mini 4k Instruct June 2024: —

| Benchmark | MiniMax-M3 | Phi 3 Mini 4k Instruct June 2024 |
|---|---|---|
| LMArena Vision | 1254 | — |
| LMArena Document | 1435 | — |

## Multilingual

- MiniMax-M3: 53.2 (#70)
- Phi 3 Mini 4k Instruct June 2024: 26.0 (#277)

| Benchmark | MiniMax-M3 | Phi 3 Mini 4k Instruct June 2024 |
|---|---|---|
| LMArena Non-English | 1420 | 1013 |
| LMArena Chinese | 1465 | 1033 |
| LMArena German | 1424 | 1031 |
| LMArena Japanese | 1381 | 954 |
| LMArena Korean | 1372 | 880 |
| LMArena Russian | 1430 | 1019 |
| LMArena French | 1445 | — |
| LMArena Spanish | 1431 | — |

## Instruction Following

- MiniMax-M3: 75.7 (#56)
- Phi 3 Mini 4k Instruct June 2024: 54.3 (#277)

| Benchmark | MiniMax-M3 | Phi 3 Mini 4k Instruct June 2024 |
|---|---|---|
| LMArena Instruction Following | 1433 | 1058 |

## Long Context

- MiniMax-M3: 44.2 (#68)
- Phi 3 Mini 4k Instruct June 2024: 31.6 (#272)

| Benchmark | MiniMax-M3 | Phi 3 Mini 4k Instruct June 2024 |
|---|---|---|
| LMArena Longer Query | 1445 | 1042 |

## Writing & Preference

- MiniMax-M3: 62.3 (#79)
- Phi 3 Mini 4k Instruct June 2024: 29.7 (#289)

| Benchmark | MiniMax-M3 | Phi 3 Mini 4k Instruct June 2024 |
|---|---|---|
| LMArena Text | 1433 | 1080 |
| LMArena Creative Writing | 1405 | 1045 |
| LMArena Multi-Turn | 1441 | 1049 |
| EQ-Bench 4 | 1150 | — |

## FAQ

### Is MiniMax-M3 better than Phi 3 Mini 4k Instruct June 2024?

MiniMax-M3 is the stronger model overall, scoring 43.5 to 30.7 on the Noometry Index.

### Is MiniMax-M3 or Phi 3 Mini 4k Instruct June 2024 better for coding?

MiniMax-M3 scores higher on coding benchmarks: 41.5 versus 31.2 in the Noometry coding category.

### How many benchmarks do MiniMax-M3 and Phi 3 Mini 4k Instruct June 2024 share?

15 benchmarks have published results for both models. MiniMax-M3 has 41 scored results on Noometry and Phi 3 Mini 4k Instruct June 2024 has 15.