# Phi 3 Mini 4k Instruct vs Qwen1.5 4b Chat

> Phi 3 Mini 4k Instruct and Qwen1.5 4b Chat score almost the same on the Noometry Index (27.4 vs 28.3), so choose on price, context window or the category you care about most.

- Canonical page: https://noometry.com/compare/phi-3-mini-4k-instruct-vs-qwen1-5-4b-chat
- Last updated: 2026-10-10
- Shared benchmarks: 13

## Summary

- They share 13 benchmarks with published results for both. Phi 3 Mini 4k Instruct scores higher in 4 categories and Qwen1.5 4b Chat in 4 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Qwen1.5 4b Chat leads 17.7 to 13.6.

## Snapshot

| | Phi 3 Mini 4k Instruct | Qwen1.5 4b Chat |
|---|---|---|
| Provider | Microsoft | Alibaba (Qwen) |
| Noometry Index | 27.4 | 28.3 |
| Rank | 324 | 319 |
| Context | — | — |
| Input $/M | — | — |
| Output $/M | — | — |
| Weights | Open | Open |

## Coding

- Phi 3 Mini 4k Instruct: 26.1 (#319)
- Qwen1.5 4b Chat: 28.6 (#305)

| Benchmark | Phi 3 Mini 4k Instruct | Qwen1.5 4b Chat |
|---|---|---|
| LMArena Coding | 1093 | 999 |
| LiveBench Coding | 15.5% | — |
| HumanEval+ | 59.1% | — |
| MBPP+ | 54.2% | — |

## Reasoning

- Phi 3 Mini 4k Instruct: 13.6 (#326)
- Qwen1.5 4b Chat: 17.7 (#277)

| Benchmark | Phi 3 Mini 4k Instruct | Qwen1.5 4b Chat |
|---|---|---|
| LMArena Hard Prompts | 1072 | 976 |
| Chess Puzzles | 0% | — |
| LiveBench Reasoning | 26.8% | — |
| LiveBench Data Analysis | 34.7% | — |
| Adversarial NLI | 52.8% | — |
| BIG-Bench Hard | 71.7% | — |
| HellaSwag | 76.7% | — |
| LiveBench | 22.4% | — |
| WinoGrande | 70.8% | — |

## Math

- Phi 3 Mini 4k Instruct: 24.5 (#258)
- Qwen1.5 4b Chat: 27.9 (#233)

| Benchmark | Phi 3 Mini 4k Instruct | Qwen1.5 4b Chat |
|---|---|---|
| LMArena Math | 1111 | 1026 |
| LiveBench Math | 15.7% | — |

## Knowledge

- Phi 3 Mini 4k Instruct: 27.9 (#241)
- Qwen1.5 4b Chat: 26.2 (#252)

| Benchmark | Phi 3 Mini 4k Instruct | Qwen1.5 4b Chat |
|---|---|---|
| LMArena Expert | 1045 | 980 |
| ARC (AI2) Challenge | 84.9% | — |
| MMLU | 68.8% | — |
| OpenBookQA | 88% | — |
| TriviaQA | 64% | — |

## Multilingual

- Phi 3 Mini 4k Instruct: 26.5 (#275)
- Qwen1.5 4b Chat: 24.2 (#285)

| Benchmark | Phi 3 Mini 4k Instruct | Qwen1.5 4b Chat |
|---|---|---|
| LMArena Non-English | 1021 | 979 |
| LMArena Chinese | 1021 | 1024 |
| LMArena German | 1044 | 902 |
| LMArena Russian | 1022 | 952 |
| LMArena French | 1075 | — |
| LMArena Japanese | 935 | — |
| LMArena Korean | 905 | — |
| LMArena Spanish | 1084 | — |

## Instruction Following

- Phi 3 Mini 4k Instruct: 48.0 (#298)
- Qwen1.5 4b Chat: 49.3 (#295)

| Benchmark | Phi 3 Mini 4k Instruct | Qwen1.5 4b Chat |
|---|---|---|
| LMArena Instruction Following | 1053 | 979 |
| LiveBench Instruction Following | 39.1% | — |

## Long Context

- Phi 3 Mini 4k Instruct: 31.7 (#271)
- Qwen1.5 4b Chat: 30.1 (#285)

| Benchmark | Phi 3 Mini 4k Instruct | Qwen1.5 4b Chat |
|---|---|---|
| LMArena Longer Query | 1044 | 988 |

## Writing & Preference

- Phi 3 Mini 4k Instruct: 27.7 (#295)
- Qwen1.5 4b Chat: 23.9 (#304)

| Benchmark | Phi 3 Mini 4k Instruct | Qwen1.5 4b Chat |
|---|---|---|
| LMArena Text | 1073 | 997 |
| LMArena Creative Writing | 1037 | 969 |
| LMArena Multi-Turn | 1018 | 977 |
| LiveBench Language | 9.2% | — |

## FAQ

### Is Phi 3 Mini 4k Instruct better than Qwen1.5 4b Chat?

Phi 3 Mini 4k Instruct and Qwen1.5 4b Chat score almost the same on the Noometry Index (27.4 vs 28.3), so choose on price, context window or the category you care about most.

### Is Phi 3 Mini 4k Instruct or Qwen1.5 4b Chat better for coding?

Qwen1.5 4b Chat scores higher on coding benchmarks: 28.6 versus 26.1 in the Noometry coding category.

### How many benchmarks do Phi 3 Mini 4k Instruct and Qwen1.5 4b Chat share?

13 benchmarks have published results for both models. Phi 3 Mini 4k Instruct has 35 scored results on Noometry and Qwen1.5 4b Chat has 13.