# MiniMax-M2.7 vs Phi 3 Mini 4k Instruct

> MiniMax-M2.7 is the stronger model overall, scoring 37.7 to 27.9 on the Noometry Index.

- Canonical page: https://noometry.com/compare/minimax-m2-7-vs-phi-3-mini-4k-instruct
- Last updated: 2026-10-10
- Shared benchmarks: 17

## Summary

- They share 17 benchmarks with published results for both. MiniMax-M2.7 scores higher in 7 categories and Phi 3 Mini 4k Instruct in 1 category; 7 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where MiniMax-M2.7 leads 58.9 to 27.6.

## Snapshot

| | MiniMax-M2.7 | Phi 3 Mini 4k Instruct |
|---|---|---|
| Provider | MiniMax | Microsoft |
| Noometry Index | 37.7 | 27.9 |
| Rank | 196 | 328 |
| Context | 205K | — |
| Input $/M | $0.30 | — |
| Output $/M | $1.20 | — |
| Weights | Open | Open |

## Coding

- MiniMax-M2.7: 41.8 (#120)
- Phi 3 Mini 4k Instruct: 26.6 (#323)

| Benchmark | MiniMax-M2.7 | Phi 3 Mini 4k Instruct |
|---|---|---|
| LMArena Coding | 1454 | 1093 |
| LMArena WebDev | 1398 | — |
| SciCode | 47% | — |
| WeirdML | 37% | — |
| LiveBench Coding | — | 15.5% |
| ALE-Bench | 599.25 | — |
| HumanEval+ | — | 59.1% |
| MBPP+ | — | 54.2% |

## Agentic & Tool Use

- MiniMax-M2.7: 25.1 (#111)
- Phi 3 Mini 4k Instruct: —

| Benchmark | MiniMax-M2.7 | Phi 3 Mini 4k Instruct |
|---|---|---|
| Terminal-Bench | 45.1% | — |
| ExploitBench | 13.3% | — |
| GBAEval | 0% | — |

## Reasoning

- MiniMax-M2.7: 19.7 (#253)
- Phi 3 Mini 4k Instruct: 14.1 (#328)

| Benchmark | MiniMax-M2.7 | Phi 3 Mini 4k Instruct |
|---|---|---|
| LMArena Hard Prompts | 1422 | 1072 |
| NYT Connections (extended) | 24.7% | — |
| CritPt | 0.6% | — |
| Chess Puzzles | — | 0% |
| Thematic Generalization | 39.3% | — |
| LiveBench Reasoning | — | 26.8% |
| LiveBench Data Analysis | — | 34.7% |
| Adversarial NLI | — | 52.8% |
| BIG-Bench Hard | — | 71.7% |
| Epoch Capabilities Index | 145.85 | — |
| HellaSwag | — | 76.7% |
| LiveBench | — | 22.4% |
| WinoGrande | — | 70.8% |

## Math

- MiniMax-M2.7: 25.9 (#263)
- Phi 3 Mini 4k Instruct: 26.6 (#257)

| Benchmark | MiniMax-M2.7 | Phi 3 Mini 4k Instruct |
|---|---|---|
| LMArena Math | 1420 | 1111 |
| ProofBench | 3% | — |
| LiveBench Math | — | 15.7% |

## Knowledge

- MiniMax-M2.7: 37.7 (#152)
- Phi 3 Mini 4k Instruct: 28.5 (#246)

| Benchmark | MiniMax-M2.7 | Phi 3 Mini 4k Instruct |
|---|---|---|
| LMArena Expert | 1444 | 1045 |
| Vectara Hallucination Rate | 12.9% | — |
| ARC (AI2) Challenge | — | 84.9% |
| MMLU | — | 68.8% |
| OpenBookQA | — | 88% |
| TriviaQA | — | 64% |

## Multilingual

- MiniMax-M2.7: 50.3 (#123)
- Phi 3 Mini 4k Instruct: 26.3 (#280)

| Benchmark | MiniMax-M2.7 | Phi 3 Mini 4k Instruct |
|---|---|---|
| LMArena Non-English | 1382 | 1021 |
| LMArena Chinese | 1441 | 1021 |
| LMArena French | 1421 | 1076 |
| LMArena German | 1398 | 1044 |
| LMArena Japanese | 1262 | 935 |
| LMArena Korean | 1313 | 905 |
| LMArena Russian | 1383 | 1022 |
| LMArena Spanish | 1403 | 1085 |

## Instruction Following

- MiniMax-M2.7: 74.1 (#103)
- Phi 3 Mini 4k Instruct: 47.7 (#303)

| Benchmark | MiniMax-M2.7 | Phi 3 Mini 4k Instruct |
|---|---|---|
| LMArena Instruction Following | 1405 | 1053 |
| LiveBench Instruction Following | — | 39.1% |

## Long Context

- MiniMax-M2.7: 43.3 (#99)
- Phi 3 Mini 4k Instruct: 31.7 (#276)

| Benchmark | MiniMax-M2.7 | Phi 3 Mini 4k Instruct |
|---|---|---|
| LMArena Longer Query | 1419 | 1044 |

## Writing & Preference

- MiniMax-M2.7: 58.9 (#112)
- Phi 3 Mini 4k Instruct: 27.6 (#300)

| Benchmark | MiniMax-M2.7 | Phi 3 Mini 4k Instruct |
|---|---|---|
| LMArena Text | 1405 | 1073 |
| LMArena Creative Writing | 1354 | 1037 |
| LMArena Multi-Turn | 1412 | 1018 |
| LiveBench Language | — | 9.2% |

## FAQ

### Is MiniMax-M2.7 better than Phi 3 Mini 4k Instruct?

MiniMax-M2.7 is the stronger model overall, scoring 37.7 to 27.9 on the Noometry Index.

### Is MiniMax-M2.7 or Phi 3 Mini 4k Instruct better for coding?

MiniMax-M2.7 scores higher on coding benchmarks: 41.8 versus 26.6 in the Noometry coding category.

### How many benchmarks do MiniMax-M2.7 and Phi 3 Mini 4k Instruct share?

17 benchmarks have published results for both models. MiniMax-M2.7 has 30 scored results on Noometry and Phi 3 Mini 4k Instruct has 35.