# Phi 3 Mini 4k Instruct vs Qwen3.8 Max

> Qwen3.8 Max is the stronger model overall, scoring 56.8 to 27.9 on the Noometry Index.

- Canonical page: https://noometry.com/compare/phi-3-mini-4k-instruct-vs-qwen3-8-max
- Last updated: 2026-10-10
- Shared benchmarks: 18

## Summary

- They share 18 benchmarks with published results for both. Phi 3 Mini 4k Instruct scores higher in 0 categories and Qwen3.8 Max in 8 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in math, where Qwen3.8 Max leads 73.2 to 26.6.
- The biggest single-benchmark swing is Chess Puzzles: 0% for Phi 3 Mini 4k Instruct and 40% for Qwen3.8 Max.
- Phi 3 Mini 4k Instruct has downloadable open weights; the other is API-only.

## Snapshot

| | Phi 3 Mini 4k Instruct | Qwen3.8 Max |
|---|---|---|
| Provider | Microsoft | Alibaba (Qwen) |
| Noometry Index | 27.9 | 56.8 |
| Rank | 328 | 22 |
| Context | — | 1M |
| Input $/M | — | $2 |
| Output $/M | — | $6 |
| Weights | Open | Proprietary |

## Coding

- Phi 3 Mini 4k Instruct: 26.6 (#323)
- Qwen3.8 Max: 53.5 (#29)

| Benchmark | Phi 3 Mini 4k Instruct | Qwen3.8 Max |
|---|---|---|
| LMArena Coding | 1093 | 1502 |
| DeepSWE | — | 57.5% |
| LMArena WebDev | — | 1674 |
| FrontierSWE | — | 17.8% |
| SciCode | — | 53.2% |
| LiveBench Coding | 15.5% | — |
| HumanEval+ | 59.1% | — |
| MBPP+ | 54.2% | — |

## Agentic & Tool Use

- Phi 3 Mini 4k Instruct: —
- Qwen3.8 Max: 45.4 (#14)

| Benchmark | Phi 3 Mini 4k Instruct | Qwen3.8 Max |
|---|---|---|
| APEX-Agents | — | 63.3% |
| τ²-bench Banking | — | 55.1% |
| GDP.pdf | — | 23.2% |

## Reasoning

- Phi 3 Mini 4k Instruct: 14.1 (#328)
- Qwen3.8 Max: 54.4 (#26)

| Benchmark | Phi 3 Mini 4k Instruct | Qwen3.8 Max |
|---|---|---|
| Chess Puzzles | 0% | 40% |
| LMArena Hard Prompts | 1072 | 1496 |
| NYT Connections (extended) | — | 88.3% |
| CritPt | — | 20% |
| LiveBench Reasoning | 26.8% | — |
| Mystery Game Puzzles | — | 38% |
| DTBench | — | 92% |
| LiveBench Data Analysis | 34.7% | — |
| LMCA | — | 46.2% |
| Adversarial NLI | 52.8% | — |
| BIG-Bench Hard | 71.7% | — |
| Epoch Capabilities Index | — | 156.41 |
| HellaSwag | 76.7% | — |
| LiveBench | 22.4% | — |
| WinoGrande | 70.8% | — |

## Math

- Phi 3 Mini 4k Instruct: 26.6 (#257)
- Qwen3.8 Max: 73.2 (#20)

| Benchmark | Phi 3 Mini 4k Instruct | Qwen3.8 Max |
|---|---|---|
| LMArena Math | 1111 | 1499 |
| FrontierMath (Tiers 1-3) | — | 74.7% |
| FrontierMath Tier 4 | — | 46.3% |
| OTIS Mock AIME 2024-2025 | — | 100% |
| ProofBench | — | 58% |
| LiveBench Math | 15.7% | — |

## Knowledge

- Phi 3 Mini 4k Instruct: 28.5 (#246)
- Qwen3.8 Max: 61.7 (#27)

| Benchmark | Phi 3 Mini 4k Instruct | Qwen3.8 Max |
|---|---|---|
| LMArena Expert | 1045 | 1507 |
| GPQA Diamond | — | 92.7% |
| SimpleQA Verified | — | 47.3% |
| ARC (AI2) Challenge | 84.9% | — |
| MMLU | 68.8% | — |
| OpenBookQA | 88% | — |
| TriviaQA | 64% | — |

## Multimodal

- Phi 3 Mini 4k Instruct: —
- Qwen3.8 Max: 37.2 (#75)

| Benchmark | Phi 3 Mini 4k Instruct | Qwen3.8 Max |
|---|---|---|
| LMArena Vision | — | 1314 |
| Furniture Assembly | — | 20% |

## Multilingual

- Phi 3 Mini 4k Instruct: 26.3 (#280)
- Qwen3.8 Max: 56.7 (#18)

| Benchmark | Phi 3 Mini 4k Instruct | Qwen3.8 Max |
|---|---|---|
| LMArena Non-English | 1021 | 1472 |
| LMArena Chinese | 1021 | 1538 |
| LMArena French | 1076 | 1503 |
| LMArena German | 1044 | 1483 |
| LMArena Japanese | 935 | 1467 |
| LMArena Korean | 905 | 1461 |
| LMArena Russian | 1022 | 1481 |
| LMArena Spanish | 1085 | 1492 |

## Instruction Following

- Phi 3 Mini 4k Instruct: 47.7 (#303)
- Qwen3.8 Max: 77.6 (#17)

| Benchmark | Phi 3 Mini 4k Instruct | Qwen3.8 Max |
|---|---|---|
| LMArena Instruction Following | 1053 | 1479 |
| LiveBench Instruction Following | 39.1% | — |

## Long Context

- Phi 3 Mini 4k Instruct: 31.7 (#276)
- Qwen3.8 Max: 45.6 (#31)

| Benchmark | Phi 3 Mini 4k Instruct | Qwen3.8 Max |
|---|---|---|
| LMArena Longer Query | 1044 | 1489 |

## Writing & Preference

- Phi 3 Mini 4k Instruct: 27.6 (#300)
- Qwen3.8 Max: 67.1 (#30)

| Benchmark | Phi 3 Mini 4k Instruct | Qwen3.8 Max |
|---|---|---|
| LMArena Text | 1073 | 1483 |
| LMArena Creative Writing | 1037 | 1479 |
| LMArena Multi-Turn | 1018 | 1489 |
| LiveBench Language | 9.2% | — |

## FAQ

### Is Phi 3 Mini 4k Instruct better than Qwen3.8 Max?

Qwen3.8 Max is the stronger model overall, scoring 56.8 to 27.9 on the Noometry Index.

### Is Phi 3 Mini 4k Instruct or Qwen3.8 Max better for coding?

Qwen3.8 Max scores higher on coding benchmarks: 53.5 versus 26.6 in the Noometry coding category.

### How many benchmarks do Phi 3 Mini 4k Instruct and Qwen3.8 Max share?

18 benchmarks have published results for both models. Phi 3 Mini 4k Instruct has 35 scored results on Noometry and Qwen3.8 Max has 39.