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

> Qwen3-30B-A3B is the stronger model overall, scoring 38.5 to 32.4 on the Noometry Index.

- Canonical page: https://noometry.com/compare/phi-3-medium-4k-instruct-vs-qwen3-30b-a3b
- Last updated: 2026-10-10
- Shared benchmarks: 17

## Summary

- They share 17 benchmarks with published results for both. Phi 3 Medium 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 34.3.

## Snapshot

| | Phi 3 Medium 4k Instruct | Qwen3-30B-A3B |
|---|---|---|
| Provider | Microsoft | Alibaba (Qwen) |
| Noometry Index | 32.4 | 38.5 |
| Rank | 246 | 174 |
| Context | — | 41K |
| Input $/M | — | $0.12 |
| Output $/M | — | $0.50 |
| Weights | Open | Open |

## Coding

- Phi 3 Medium 4k Instruct: 32.3 (#263)
- Qwen3-30B-A3B: 37.0 (#188)

| Benchmark | Phi 3 Medium 4k Instruct | Qwen3-30B-A3B |
|---|---|---|
| LMArena Coding | 1130 | 1416 |
| SciCode | — | 33.3% |
| WeirdML | — | 29.8% |

## Agentic & Tool Use

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

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

## Reasoning

- Phi 3 Medium 4k Instruct: 20.8 (#214)
- Qwen3-30B-A3B: 21.6 (#193)

| Benchmark | Phi 3 Medium 4k Instruct | Qwen3-30B-A3B |
|---|---|---|
| LMArena Hard Prompts | 1127 | 1398 |
| Kagi LLM Benchmark | — | 54.9% |
| CritPt | — | 0.3% |
| Chess Puzzles | — | 8% |
| DTBench | — | 69.3% |
| LMCA | — | 22.4% |
| Epoch Capabilities Index | — | 139.63 |

## Math

- Phi 3 Medium 4k Instruct: 30.9 (#202)
- Qwen3-30B-A3B: 36.0 (#133)

| Benchmark | Phi 3 Medium 4k Instruct | Qwen3-30B-A3B |
|---|---|---|
| LMArena Math | 1173 | 1394 |
| MathArena Final-Answer Competitions | — | 47.8% |
| OTIS Mock AIME 2024-2025 | — | 70.3% |

## Knowledge

- Phi 3 Medium 4k Instruct: 29.6 (#226)
- Qwen3-30B-A3B: 41.7 (#96)

| Benchmark | Phi 3 Medium 4k Instruct | Qwen3-30B-A3B |
|---|---|---|
| LMArena Expert | 1108 | 1395 |
| GPQA Diamond | — | 70.1% |
| Confabulations | — | 12.3% |

## Multilingual

- Phi 3 Medium 4k Instruct: 30.8 (#258)
- Qwen3-30B-A3B: 49.8 (#126)

| Benchmark | Phi 3 Medium 4k Instruct | Qwen3-30B-A3B |
|---|---|---|
| LMArena Non-English | 1094 | 1372 |
| LMArena Chinese | 1108 | 1434 |
| LMArena French | 1109 | 1419 |
| LMArena German | 1101 | 1379 |
| LMArena Japanese | 1042 | 1338 |
| LMArena Korean | 954 | 1333 |
| LMArena Russian | 1145 | 1369 |
| LMArena Spanish | 1095 | 1403 |

## Instruction Following

- Phi 3 Medium 4k Instruct: 57.8 (#263)
- Qwen3-30B-A3B: 72.2 (#137)

| Benchmark | Phi 3 Medium 4k Instruct | Qwen3-30B-A3B |
|---|---|---|
| LMArena Instruction Following | 1114 | 1364 |

## Long Context

- Phi 3 Medium 4k Instruct: 33.9 (#250)
- Qwen3-30B-A3B: 31.0 (#278)

| Benchmark | Phi 3 Medium 4k Instruct | Qwen3-30B-A3B |
|---|---|---|
| LMArena Longer Query | 1120 | 1379 |
| Fiction.LiveBench | — | 40.6% |

## Writing & Preference

- Phi 3 Medium 4k Instruct: 34.3 (#267)
- Qwen3-30B-A3B: 55.9 (#138)

| Benchmark | Phi 3 Medium 4k Instruct | Qwen3-30B-A3B |
|---|---|---|
| LMArena Text | 1138 | 1384 |
| LMArena Creative Writing | 1106 | 1318 |
| LMArena Multi-Turn | 1088 | 1378 |
| Short-Story Creative Writing | — | 75.3% |

## FAQ

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

Qwen3-30B-A3B is the stronger model overall, scoring 38.5 to 32.4 on the Noometry Index.

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

Qwen3-30B-A3B scores higher on coding benchmarks: 37.0 versus 32.3 in the Noometry coding category.

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

17 benchmarks have published results for both models. Phi 3 Medium 4k Instruct has 17 scored results on Noometry and Qwen3-30B-A3B has 32.