# Phi 3 Small 8k Instruct vs Qwen2.5-Max

> Qwen2.5-Max is the stronger model overall, scoring 40.1 to 28.8 on the Noometry Index.

- Canonical page: https://noometry.com/compare/phi-3-small-8k-instruct-vs-qwen2-5-max
- Last updated: 2026-10-10
- Shared benchmarks: 24

## Summary

- They share 24 benchmarks with published results for both. Phi 3 Small 8k Instruct scores higher in 0 categories and Qwen2.5-Max in 8 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Qwen2.5-Max leads 55.6 to 31.3.
- The biggest single-benchmark swing is LiveBench Coding: 20.3% for Phi 3 Small 8k Instruct and 64.4% for Qwen2.5-Max.
- Phi 3 Small 8k Instruct has downloadable open weights; the other is API-only.

## Snapshot

| | Phi 3 Small 8k Instruct | Qwen2.5-Max |
|---|---|---|
| Provider | Microsoft | Alibaba (Qwen) |
| Noometry Index | 28.8 | 40.1 |
| Rank | 310 | 142 |
| Context | — | — |
| Input $/M | — | — |
| Output $/M | — | — |
| Weights | Open | Proprietary |

## Coding

- Phi 3 Small 8k Instruct: 27.4 (#313)
- Qwen2.5-Max: 41.2 (#118)

| Benchmark | Phi 3 Small 8k Instruct | Qwen2.5-Max |
|---|---|---|
| LiveBench Coding | 20.3% | 64.4% |
| LMArena Coding | 1102 | 1359 |

## Reasoning

- Phi 3 Small 8k Instruct: 14.2 (#319)
- Qwen2.5-Max: 24.6 (#144)

| Benchmark | Phi 3 Small 8k Instruct | Qwen2.5-Max |
|---|---|---|
| LiveBench Reasoning | 15.9% | 51.4% |
| LMArena Hard Prompts | 1100 | 1360 |
| LiveBench Data Analysis | 30.3% | 67.9% |
| LiveBench | 24% | 62.3% |
| Adversarial NLI | 58.1% | — |
| BIG-Bench Hard | 79.1% | — |
| Epoch Capabilities Index | — | 132.54 |
| HellaSwag | 77% | — |
| WinoGrande | 81.5% | — |

## Math

- Phi 3 Small 8k Instruct: 25.4 (#247)
- Qwen2.5-Max: 34.3 (#162)

| Benchmark | Phi 3 Small 8k Instruct | Qwen2.5-Max |
|---|---|---|
| LiveBench Math | 17.6% | 58.4% |
| LMArena Math | 1151 | 1369 |

## Knowledge

- Phi 3 Small 8k Instruct: 28.5 (#237)
- Qwen2.5-Max: 34.8 (#181)

| Benchmark | Phi 3 Small 8k Instruct | Qwen2.5-Max |
|---|---|---|
| LMArena Expert | 1067 | 1337 |
| Confabulations | — | 21.8% |
| ARC (AI2) Challenge | 90.7% | — |
| MMLU | 75.7% | — |
| OpenBookQA | 88% | — |
| TriviaQA | 58.1% | — |

## Multilingual

- Phi 3 Small 8k Instruct: 28.6 (#267)
- Qwen2.5-Max: 48.3 (#140)

| Benchmark | Phi 3 Small 8k Instruct | Qwen2.5-Max |
|---|---|---|
| LMArena Non-English | 1058 | 1352 |
| LMArena Chinese | 1061 | 1382 |
| LMArena French | 1134 | 1396 |
| LMArena German | 1080 | 1350 |
| LMArena Japanese | 966 | 1299 |
| LMArena Korean | 894 | 1304 |
| LMArena Russian | 1111 | 1353 |
| LMArena Spanish | 1111 | 1377 |

## Instruction Following

- Phi 3 Small 8k Instruct: 52.2 (#287)
- Qwen2.5-Max: 71.5 (#147)

| Benchmark | Phi 3 Small 8k Instruct | Qwen2.5-Max |
|---|---|---|
| LiveBench Instruction Following | 47.2% | 75.3% |
| LMArena Instruction Following | 1087 | 1335 |

## Long Context

- Phi 3 Small 8k Instruct: 33.0 (#262)
- Qwen2.5-Max: 41.3 (#137)

| Benchmark | Phi 3 Small 8k Instruct | Qwen2.5-Max |
|---|---|---|
| LMArena Longer Query | 1088 | 1358 |

## Writing & Preference

- Phi 3 Small 8k Instruct: 31.3 (#279)
- Qwen2.5-Max: 55.6 (#141)

| Benchmark | Phi 3 Small 8k Instruct | Qwen2.5-Max |
|---|---|---|
| LMArena Text | 1110 | 1367 |
| LMArena Creative Writing | 1083 | 1339 |
| LMArena Multi-Turn | 1068 | 1364 |
| LiveBench Language | 12.9% | 56.3% |
| Short-Story Creative Writing | — | 72.9% |

## FAQ

### Is Phi 3 Small 8k Instruct better than Qwen2.5-Max?

Qwen2.5-Max is the stronger model overall, scoring 40.1 to 28.8 on the Noometry Index.

### Is Phi 3 Small 8k Instruct or Qwen2.5-Max better for coding?

Qwen2.5-Max scores higher on coding benchmarks: 41.2 versus 27.4 in the Noometry coding category.

### How many benchmarks do Phi 3 Small 8k Instruct and Qwen2.5-Max share?

24 benchmarks have published results for both models. Phi 3 Small 8k Instruct has 32 scored results on Noometry and Qwen2.5-Max has 27.