# MiniMax-M2.5 vs Phi 3 Small 8k Instruct

> MiniMax-M2.5 is the stronger model overall, scoring 38.3 to 29.3 on the Noometry Index.

- Canonical page: https://noometry.com/compare/minimax-m2-5-vs-phi-3-small-8k-instruct
- Last updated: 2026-10-11
- Shared benchmarks: 17

## Summary

- They share 17 benchmarks with published results for both. MiniMax-M2.5 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-M2.5 leads 53.9 to 31.1.

## Snapshot

| | MiniMax-M2.5 | Phi 3 Small 8k Instruct |
|---|---|---|
| Provider | MiniMax | Microsoft |
| Noometry Index | 38.3 | 29.3 |
| Rank | 188 | 314 |
| Context | 205K | — |
| Input $/M | $0.30 | — |
| Output $/M | $1.20 | — |
| Weights | Open | Open |

## Coding

- MiniMax-M2.5: 48.1 (#58)
- Phi 3 Small 8k Instruct: 27.9 (#318)

| Benchmark | MiniMax-M2.5 | Phi 3 Small 8k Instruct |
|---|---|---|
| LMArena Coding | 1381 | 1101 |
| SWE-bench Verified (bash only) | 75.8% | — |
| LMArena WebDev | 1387 | — |
| SWE-bench Multilingual | 68.3% | — |
| LiveBench Coding | — | 20.3% |
| ALE-Bench | 618.17 | — |

## Agentic & Tool Use

- MiniMax-M2.5: 30.4 (#77)
- Phi 3 Small 8k Instruct: —

| Benchmark | MiniMax-M2.5 | Phi 3 Small 8k Instruct |
|---|---|---|
| Terminal-Bench | 42.7% | — |
| Vending-Bench 2 | -23.16 | — |

## Reasoning

- MiniMax-M2.5: 17.5 (#292)
- Phi 3 Small 8k Instruct: 14.8 (#323)

| Benchmark | MiniMax-M2.5 | Phi 3 Small 8k Instruct |
|---|---|---|
| LMArena Hard Prompts | 1372 | 1100 |
| ARC-AGI-2 | 4.9% | — |
| Kagi LLM Benchmark | 55.2% | — |
| NYT Connections (extended) | 16.8% | — |
| ARC-AGI-1 | 63.7% | — |
| LiveBench Reasoning | — | 15.9% |
| LiveBench Data Analysis | — | 30.3% |
| Adversarial NLI | — | 58.1% |
| BIG-Bench Hard | — | 79.1% |
| Epoch Capabilities Index | 146.68 | — |
| HellaSwag | — | 77% |
| LiveBench | — | 24% |
| WinoGrande | — | 81.5% |

## Math

- MiniMax-M2.5: 26.9 (#253)
- Phi 3 Small 8k Instruct: 27.6 (#248)

| Benchmark | MiniMax-M2.5 | Phi 3 Small 8k Instruct |
|---|---|---|
| LMArena Math | 1378 | 1151 |
| ProofBench | 4% | — |
| LiveBench Math | — | 17.6% |

## Knowledge

- MiniMax-M2.5: 39.2 (#135)
- Phi 3 Small 8k Instruct: 29.1 (#240)

| Benchmark | MiniMax-M2.5 | Phi 3 Small 8k Instruct |
|---|---|---|
| LMArena Expert | 1379 | 1067 |
| Vectara Hallucination Rate | 9.1% | — |
| ARC (AI2) Challenge | — | 90.7% |
| MMLU | — | 75.7% |
| OpenBookQA | — | 88% |
| TriviaQA | — | 58.1% |

## Multilingual

- MiniMax-M2.5: 47.1 (#152)
- Phi 3 Small 8k Instruct: 28.5 (#272)

| Benchmark | MiniMax-M2.5 | Phi 3 Small 8k Instruct |
|---|---|---|
| LMArena Non-English | 1338 | 1058 |
| LMArena Chinese | 1393 | 1061 |
| LMArena French | 1362 | 1135 |
| LMArena German | 1362 | 1080 |
| LMArena Japanese | 1171 | 966 |
| LMArena Korean | 1232 | 894 |
| LMArena Russian | 1358 | 1111 |
| LMArena Spanish | 1354 | 1111 |

## Instruction Following

- MiniMax-M2.5: 71.5 (#148)
- Phi 3 Small 8k Instruct: 51.9 (#292)

| Benchmark | MiniMax-M2.5 | Phi 3 Small 8k Instruct |
|---|---|---|
| LMArena Instruction Following | 1353 | 1087 |
| LiveBench Instruction Following | — | 47.2% |

## Long Context

- MiniMax-M2.5: 37.5 (#216)
- Phi 3 Small 8k Instruct: 33.0 (#267)

| Benchmark | MiniMax-M2.5 | Phi 3 Small 8k Instruct |
|---|---|---|
| LMArena Longer Query | 1366 | 1088 |
| CL-bench | 11.4% | — |
| CL-bench Life | 6.3% | — |

## Writing & Preference

- MiniMax-M2.5: 53.9 (#153)
- Phi 3 Small 8k Instruct: 31.1 (#284)

| Benchmark | MiniMax-M2.5 | Phi 3 Small 8k Instruct |
|---|---|---|
| LMArena Text | 1359 | 1110 |
| LMArena Creative Writing | 1331 | 1083 |
| LMArena Multi-Turn | 1364 | 1068 |
| EQ-Bench Creative Writing | 1361 | — |
| LiveBench Language | — | 12.9% |

## FAQ

### Is MiniMax-M2.5 better than Phi 3 Small 8k Instruct?

MiniMax-M2.5 is the stronger model overall, scoring 38.3 to 29.3 on the Noometry Index.

### Is MiniMax-M2.5 or Phi 3 Small 8k Instruct better for coding?

MiniMax-M2.5 scores higher on coding benchmarks: 48.1 versus 27.9 in the Noometry coding category.

### How many benchmarks do MiniMax-M2.5 and Phi 3 Small 8k Instruct share?

17 benchmarks have published results for both models. MiniMax-M2.5 has 33 scored results on Noometry and Phi 3 Small 8k Instruct has 32.