# MiniMax-M2.7 vs Phi 3 Small 8k Instruct

> MiniMax-M2.7 is the stronger model overall, scoring 37.4 to 28.8 on the Noometry Index.

- Canonical page: https://noometry.com/compare/minimax-m2-7-vs-phi-3-small-8k-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 Small 8k Instruct in 1 category; 7 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where MiniMax-M2.7 leads 59.1 to 31.3.

## Snapshot

| | MiniMax-M2.7 | Phi 3 Small 8k Instruct |
|---|---|---|
| Provider | MiniMax | Microsoft |
| Noometry Index | 37.4 | 28.8 |
| Rank | 188 | 310 |
| Context | 205K | — |
| Input $/M | $0.30 | — |
| Output $/M | $1.20 | — |
| Weights | Open | Open |

## Coding

- MiniMax-M2.7: 41.4 (#115)
- Phi 3 Small 8k Instruct: 27.4 (#313)

| Benchmark | MiniMax-M2.7 | Phi 3 Small 8k Instruct |
|---|---|---|
| LMArena Coding | 1454 | 1102 |
| LMArena WebDev | 1397 | — |
| SciCode | 47% | — |
| WeirdML | 37% | — |
| LiveBench Coding | — | 20.3% |
| ALE-Bench | 599.25 | — |

## Agentic & Tool Use

- MiniMax-M2.7: 24.9 (#103)
- Phi 3 Small 8k Instruct: —

| Benchmark | MiniMax-M2.7 | Phi 3 Small 8k Instruct |
|---|---|---|
| Terminal-Bench | 45.1% | — |
| ExploitBench | 13.3% | — |
| GBAEval | 0% | — |

## Reasoning

- MiniMax-M2.7: 19.0 (#248)
- Phi 3 Small 8k Instruct: 14.2 (#319)

| Benchmark | MiniMax-M2.7 | Phi 3 Small 8k Instruct |
|---|---|---|
| LMArena Hard Prompts | 1422 | 1100 |
| NYT Connections (extended) | 24.7% | — |
| CritPt | 0.6% | — |
| Thematic Generalization | 39.3% | — |
| LiveBench Reasoning | — | 15.9% |
| LiveBench Data Analysis | — | 30.3% |
| Adversarial NLI | — | 58.1% |
| BIG-Bench Hard | — | 79.1% |
| Epoch Capabilities Index | 145.84 | — |
| HellaSwag | — | 77% |
| LiveBench | — | 24% |
| WinoGrande | — | 81.5% |

## Math

- MiniMax-M2.7: 24.9 (#254)
- Phi 3 Small 8k Instruct: 25.4 (#247)

| Benchmark | MiniMax-M2.7 | Phi 3 Small 8k Instruct |
|---|---|---|
| LMArena Math | 1420 | 1151 |
| ProofBench | 3% | — |
| LiveBench Math | — | 17.6% |

## Knowledge

- MiniMax-M2.7: 37.1 (#151)
- Phi 3 Small 8k Instruct: 28.5 (#237)

| Benchmark | MiniMax-M2.7 | Phi 3 Small 8k Instruct |
|---|---|---|
| LMArena Expert | 1443 | 1067 |
| Vectara Hallucination Rate | 12.9% | — |
| ARC (AI2) Challenge | — | 90.7% |
| MMLU | — | 75.7% |
| OpenBookQA | — | 88% |
| TriviaQA | — | 58.1% |

## Multilingual

- MiniMax-M2.7: 50.5 (#120)
- Phi 3 Small 8k Instruct: 28.6 (#267)

| Benchmark | MiniMax-M2.7 | Phi 3 Small 8k Instruct |
|---|---|---|
| LMArena Non-English | 1382 | 1058 |
| LMArena Chinese | 1439 | 1061 |
| LMArena French | 1422 | 1134 |
| LMArena German | 1398 | 1080 |
| LMArena Japanese | 1261 | 966 |
| LMArena Korean | 1313 | 894 |
| LMArena Russian | 1383 | 1111 |
| LMArena Spanish | 1403 | 1111 |

## Instruction Following

- MiniMax-M2.7: 74.2 (#101)
- Phi 3 Small 8k Instruct: 52.2 (#287)

| Benchmark | MiniMax-M2.7 | Phi 3 Small 8k Instruct |
|---|---|---|
| LMArena Instruction Following | 1404 | 1087 |
| LiveBench Instruction Following | — | 47.2% |

## Long Context

- MiniMax-M2.7: 43.3 (#94)
- Phi 3 Small 8k Instruct: 33.0 (#262)

| Benchmark | MiniMax-M2.7 | Phi 3 Small 8k Instruct |
|---|---|---|
| LMArena Longer Query | 1419 | 1088 |

## Writing & Preference

- MiniMax-M2.7: 59.1 (#107)
- Phi 3 Small 8k Instruct: 31.3 (#279)

| Benchmark | MiniMax-M2.7 | Phi 3 Small 8k Instruct |
|---|---|---|
| LMArena Text | 1404 | 1110 |
| LMArena Creative Writing | 1354 | 1083 |
| LMArena Multi-Turn | 1413 | 1068 |
| LiveBench Language | — | 12.9% |

## FAQ

### Is MiniMax-M2.7 better than Phi 3 Small 8k Instruct?

MiniMax-M2.7 is the stronger model overall, scoring 37.4 to 28.8 on the Noometry Index.

### Is MiniMax-M2.7 or Phi 3 Small 8k Instruct better for coding?

MiniMax-M2.7 scores higher on coding benchmarks: 41.4 versus 27.4 in the Noometry coding category.

### How many benchmarks do MiniMax-M2.7 and Phi 3 Small 8k Instruct share?

17 benchmarks have published results for both models. MiniMax-M2.7 has 30 scored results on Noometry and Phi 3 Small 8k Instruct has 32.