# Phi 3 Mini 128k Instruct vs Qwen3.8 27B

> Qwen3.8 27B is the stronger model overall, scoring 45.3 to 29.1 on the Noometry Index.

- Canonical page: https://noometry.com/compare/phi-3-mini-128k-instruct-vs-qwen3-8-27b
- Last updated: 2026-10-10
- Shared benchmarks: 17

## Summary

- They share 17 benchmarks with published results for both. Phi 3 Mini 128k Instruct scores higher in 0 categories and Qwen3.8 27B in 8 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Qwen3.8 27B leads 65.9 to 27.3.

## Snapshot

| | Phi 3 Mini 128k Instruct | Qwen3.8 27B |
|---|---|---|
| Provider | Microsoft | Alibaba (Qwen) |
| Noometry Index | 29.1 | 45.3 |
| Rank | 303 | 64 |
| Context | — | 262K |
| Input $/M | — | $0.99 |
| Output $/M | — | $1.49 |
| Weights | Open | Open |

## Coding

- Phi 3 Mini 128k Instruct: 28.3 (#307)
- Qwen3.8 27B: 50.3 (#42)

| Benchmark | Phi 3 Mini 128k Instruct | Qwen3.8 27B |
|---|---|---|
| LMArena Coding | 1040 | 1487 |
| LMArena WebDev | — | 1592 |
| SciCode | — | 46.6% |
| BigCodeBench Instruct | 29.6% | — |
| BigCodeBench Complete | 40.6% | — |

## Reasoning

- Phi 3 Mini 128k Instruct: 18.7 (#254)
- Qwen3.8 27B: 31.5 (#71)

| Benchmark | Phi 3 Mini 128k Instruct | Qwen3.8 27B |
|---|---|---|
| LMArena Hard Prompts | 1028 | 1459 |
| NYT Connections (extended) | — | 54.5% |
| CritPt | — | 5.4% |
| DTBench | — | 88% |
| LMCA | — | 41.4% |
| Surface Evolver Bench | — | 45% |
| Epoch Capabilities Index | — | 149.38 |

## Math

- Phi 3 Mini 128k Instruct: 29.2 (#220)
- Qwen3.8 27B: 35.7 (#139)

| Benchmark | Phi 3 Mini 128k Instruct | Qwen3.8 27B |
|---|---|---|
| LMArena Math | 1089 | 1453 |
| ProofBench | — | 16% |

## Knowledge

- Phi 3 Mini 128k Instruct: 26.3 (#251)
- Qwen3.8 27B: 40.9 (#105)

| Benchmark | Phi 3 Mini 128k Instruct | Qwen3.8 27B |
|---|---|---|
| LMArena Expert | 984 | 1482 |

## Multimodal

- Phi 3 Mini 128k Instruct: —
- Qwen3.8 27B: 40.5 (#36)

| Benchmark | Phi 3 Mini 128k Instruct | Qwen3.8 27B |
|---|---|---|
| LMArena Vision | — | 1270 |

## Multilingual

- Phi 3 Mini 128k Instruct: 25.4 (#280)
- Qwen3.8 27B: 54.0 (#54)

| Benchmark | Phi 3 Mini 128k Instruct | Qwen3.8 27B |
|---|---|---|
| LMArena Non-English | 1000 | 1431 |
| LMArena Chinese | 1016 | 1504 |
| LMArena French | 1038 | 1468 |
| LMArena German | 1006 | 1435 |
| LMArena Japanese | 899 | 1392 |
| LMArena Korean | 856 | 1389 |
| LMArena Russian | 1004 | 1421 |
| LMArena Spanish | 1058 | 1444 |

## Instruction Following

- Phi 3 Mini 128k Instruct: 52.1 (#289)
- Qwen3.8 27B: 75.8 (#54)

| Benchmark | Phi 3 Mini 128k Instruct | Qwen3.8 27B |
|---|---|---|
| LMArena Instruction Following | 1023 | 1436 |

## Long Context

- Phi 3 Mini 128k Instruct: 30.3 (#284)
- Qwen3.8 27B: 44.3 (#66)

| Benchmark | Phi 3 Mini 128k Instruct | Qwen3.8 27B |
|---|---|---|
| LMArena Longer Query | 996 | 1448 |

## Writing & Preference

- Phi 3 Mini 128k Instruct: 27.3 (#296)
- Qwen3.8 27B: 65.9 (#41)

| Benchmark | Phi 3 Mini 128k Instruct | Qwen3.8 27B |
|---|---|---|
| LMArena Text | 1050 | 1441 |
| LMArena Creative Writing | 1024 | 1382 |
| LMArena Multi-Turn | 989 | 1443 |
| EQ-Bench Creative Writing | — | 1671 |

## FAQ

### Is Phi 3 Mini 128k Instruct better than Qwen3.8 27B?

Qwen3.8 27B is the stronger model overall, scoring 45.3 to 29.1 on the Noometry Index.

### Is Phi 3 Mini 128k Instruct or Qwen3.8 27B better for coding?

Qwen3.8 27B scores higher on coding benchmarks: 50.3 versus 28.3 in the Noometry coding category.

### How many benchmarks do Phi 3 Mini 128k Instruct and Qwen3.8 27B share?

17 benchmarks have published results for both models. Phi 3 Mini 128k Instruct has 19 scored results on Noometry and Qwen3.8 27B has 28.