# Phi 3 Mini 4k Instruct vs Qwen3-30B-A3B

> Qwen3-30B-A3B is the stronger model overall, scoring 38.5 to 27.4 on the Noometry Index.

- Canonical page: https://noometry.com/compare/phi-3-mini-4k-instruct-vs-qwen3-30b-a3b
- 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 1 category and Qwen3-30B-A3B in 7 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Qwen3-30B-A3B leads 55.9 to 27.7.
- The biggest single-benchmark swing is Chess Puzzles: 0% for Phi 3 Mini 4k Instruct and 8% for Qwen3-30B-A3B.

## Snapshot

| | Phi 3 Mini 4k Instruct | Qwen3-30B-A3B |
|---|---|---|
| Provider | Microsoft | Alibaba (Qwen) |
| Noometry Index | 27.4 | 38.5 |
| Rank | 324 | 174 |
| Context | — | 41K |
| Input $/M | — | $0.12 |
| Output $/M | — | $0.50 |
| Weights | Open | Open |

## Coding

- Phi 3 Mini 4k Instruct: 26.1 (#319)
- Qwen3-30B-A3B: 37.0 (#188)

| Benchmark | Phi 3 Mini 4k Instruct | Qwen3-30B-A3B |
|---|---|---|
| LMArena Coding | 1093 | 1416 |
| SciCode | — | 33.3% |
| WeirdML | — | 29.8% |
| LiveBench Coding | 15.5% | — |
| HumanEval+ | 59.1% | — |
| MBPP+ | 54.2% | — |

## Agentic & Tool Use

- Phi 3 Mini 4k Instruct: —
- Qwen3-30B-A3B: 29.5 (#75)

| Benchmark | Phi 3 Mini 4k Instruct | Qwen3-30B-A3B |
|---|---|---|
| Berkeley Function Calling Leaderboard | — | 41.4% |

## Reasoning

- Phi 3 Mini 4k Instruct: 13.6 (#326)
- Qwen3-30B-A3B: 21.6 (#193)

| Benchmark | Phi 3 Mini 4k Instruct | Qwen3-30B-A3B |
|---|---|---|
| Chess Puzzles | 0% | 8% |
| LMArena Hard Prompts | 1072 | 1398 |
| Kagi LLM Benchmark | — | 54.9% |
| CritPt | — | 0.3% |
| LiveBench Reasoning | 26.8% | — |
| DTBench | — | 69.3% |
| LiveBench Data Analysis | 34.7% | — |
| LMCA | — | 22.4% |
| Adversarial NLI | 52.8% | — |
| BIG-Bench Hard | 71.7% | — |
| Epoch Capabilities Index | — | 139.63 |
| HellaSwag | 76.7% | — |
| LiveBench | 22.4% | — |
| WinoGrande | 70.8% | — |

## Math

- Phi 3 Mini 4k Instruct: 24.5 (#258)
- Qwen3-30B-A3B: 36.0 (#133)

| Benchmark | Phi 3 Mini 4k Instruct | Qwen3-30B-A3B |
|---|---|---|
| LMArena Math | 1111 | 1394 |
| MathArena Final-Answer Competitions | — | 47.8% |
| OTIS Mock AIME 2024-2025 | — | 70.3% |
| LiveBench Math | 15.7% | — |

## Knowledge

- Phi 3 Mini 4k Instruct: 27.9 (#241)
- Qwen3-30B-A3B: 41.7 (#96)

| Benchmark | Phi 3 Mini 4k Instruct | Qwen3-30B-A3B |
|---|---|---|
| LMArena Expert | 1045 | 1395 |
| GPQA Diamond | — | 70.1% |
| Confabulations | — | 12.3% |
| ARC (AI2) Challenge | 84.9% | — |
| MMLU | 68.8% | — |
| OpenBookQA | 88% | — |
| TriviaQA | 64% | — |

## Multilingual

- Phi 3 Mini 4k Instruct: 26.5 (#275)
- Qwen3-30B-A3B: 49.8 (#126)

| Benchmark | Phi 3 Mini 4k Instruct | Qwen3-30B-A3B |
|---|---|---|
| LMArena Non-English | 1021 | 1372 |
| LMArena Chinese | 1021 | 1434 |
| LMArena French | 1075 | 1419 |
| LMArena German | 1044 | 1379 |
| LMArena Japanese | 935 | 1338 |
| LMArena Korean | 905 | 1333 |
| LMArena Russian | 1022 | 1369 |
| LMArena Spanish | 1084 | 1403 |

## Instruction Following

- Phi 3 Mini 4k Instruct: 48.0 (#298)
- Qwen3-30B-A3B: 72.2 (#137)

| Benchmark | Phi 3 Mini 4k Instruct | Qwen3-30B-A3B |
|---|---|---|
| LMArena Instruction Following | 1053 | 1364 |
| LiveBench Instruction Following | 39.1% | — |

## Long Context

- Phi 3 Mini 4k Instruct: 31.7 (#271)
- Qwen3-30B-A3B: 31.0 (#278)

| Benchmark | Phi 3 Mini 4k Instruct | Qwen3-30B-A3B |
|---|---|---|
| LMArena Longer Query | 1044 | 1379 |
| Fiction.LiveBench | — | 40.6% |

## Writing & Preference

- Phi 3 Mini 4k Instruct: 27.7 (#295)
- Qwen3-30B-A3B: 55.9 (#138)

| Benchmark | Phi 3 Mini 4k Instruct | Qwen3-30B-A3B |
|---|---|---|
| LMArena Text | 1073 | 1384 |
| LMArena Creative Writing | 1037 | 1318 |
| LMArena Multi-Turn | 1018 | 1378 |
| Short-Story Creative Writing | — | 75.3% |
| LiveBench Language | 9.2% | — |

## FAQ

### Is Phi 3 Mini 4k Instruct better than Qwen3-30B-A3B?

Qwen3-30B-A3B is the stronger model overall, scoring 38.5 to 27.4 on the Noometry Index.

### Is Phi 3 Mini 4k Instruct or Qwen3-30B-A3B better for coding?

Qwen3-30B-A3B scores higher on coding benchmarks: 37.0 versus 26.1 in the Noometry coding category.

### How many benchmarks do Phi 3 Mini 4k Instruct and Qwen3-30B-A3B share?

18 benchmarks have published results for both models. Phi 3 Mini 4k Instruct has 35 scored results on Noometry and Qwen3-30B-A3B has 32.