# Phi 3 Mini 128k Instruct vs Qwen3.7 Max

> Qwen3.7 Max is the stronger model overall, scoring 51.4 to 29.1 on the Noometry Index.

- Canonical page: https://noometry.com/compare/phi-3-mini-128k-instruct-vs-qwen3-7-max
- Last updated: 2026-10-10
- Shared benchmarks: 12

## Summary

- They share 12 benchmarks with published results for both. Phi 3 Mini 128k Instruct scores higher in 0 categories and Qwen3.7 Max in 8 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Qwen3.7 Max leads 65.2 to 27.3.
- Phi 3 Mini 128k Instruct has downloadable open weights; the other is API-only.

## Snapshot

| | Phi 3 Mini 128k Instruct | Qwen3.7 Max |
|---|---|---|
| Provider | Microsoft | Alibaba (Qwen) |
| Noometry Index | 29.1 | 51.4 |
| Rank | 303 | 35 |
| Context | — | 1M |
| Input $/M | — | $2.50 |
| Output $/M | — | $7.50 |
| Weights | Open | Proprietary |

## Coding

- Phi 3 Mini 128k Instruct: 28.3 (#307)
- Qwen3.7 Max: 50.2 (#43)

| Benchmark | Phi 3 Mini 128k Instruct | Qwen3.7 Max |
|---|---|---|
| LMArena Coding | 1040 | 1498 |
| SWE-bench Verified | — | 77.3% |
| LMArena WebDev | — | 1515 |
| SciCode | — | 48.8% |
| BigCodeBench Instruct | 29.6% | — |
| BigCodeBench Complete | 40.6% | — |
| ALE-Bench | — | 1,189 |

## Agentic & Tool Use

- Phi 3 Mini 128k Instruct: —
- Qwen3.7 Max: 21.8 (#129)

| Benchmark | Phi 3 Mini 128k Instruct | Qwen3.7 Max |
|---|---|---|
| GBAEval | — | 0.4% |

## Reasoning

- Phi 3 Mini 128k Instruct: 18.7 (#254)
- Qwen3.7 Max: 48.4 (#36)

| Benchmark | Phi 3 Mini 128k Instruct | Qwen3.7 Max |
|---|---|---|
| LMArena Hard Prompts | 1028 | 1483 |
| SimpleBench | — | 70.4% |
| NYT Connections (extended) | — | 85.1% |
| CritPt | — | 13.4% |
| Chess Puzzles | — | 19% |
| EBR-Bench | — | 9.5% |
| Mystery Game Puzzles | — | 32% |
| DTBench | — | 92.3% |
| LMCA | — | 44% |
| Epoch Capabilities Index | — | 153.74 |

## Math

- Phi 3 Mini 128k Instruct: 29.2 (#220)
- Qwen3.7 Max: 62.3 (#26)

| Benchmark | Phi 3 Mini 128k Instruct | Qwen3.7 Max |
|---|---|---|
| LMArena Math | 1089 | 1488 |
| FrontierMath (Tiers 1-3) | — | 64.6% |
| FrontierMath Tier 4 | — | 34.1% |
| OTIS Mock AIME 2024-2025 | — | 95.6% |
| ProofBench | — | 26% |

## Knowledge

- Phi 3 Mini 128k Instruct: 26.3 (#251)
- Qwen3.7 Max: 61.7 (#24)

| Benchmark | Phi 3 Mini 128k Instruct | Qwen3.7 Max |
|---|---|---|
| LMArena Expert | 984 | 1488 |
| GPQA Diamond | — | 90.9% |
| SimpleQA Verified | — | 55.8% |

## Multilingual

- Phi 3 Mini 128k Instruct: 25.4 (#280)
- Qwen3.7 Max: 57.1 (#13)

| Benchmark | Phi 3 Mini 128k Instruct | Qwen3.7 Max |
|---|---|---|
| LMArena Non-English | 1000 | 1475 |
| LMArena Chinese | 1016 | 1533 |
| LMArena Russian | 1004 | 1482 |
| LMArena French | 1038 | — |
| LMArena German | 1006 | — |
| LMArena Japanese | 899 | — |
| LMArena Korean | 856 | — |
| LMArena Spanish | 1058 | — |

## Instruction Following

- Phi 3 Mini 128k Instruct: 52.1 (#289)
- Qwen3.7 Max: 76.9 (#34)

| Benchmark | Phi 3 Mini 128k Instruct | Qwen3.7 Max |
|---|---|---|
| LMArena Instruction Following | 1023 | 1460 |

## Long Context

- Phi 3 Mini 128k Instruct: 30.3 (#284)
- Qwen3.7 Max: 45.4 (#34)

| Benchmark | Phi 3 Mini 128k Instruct | Qwen3.7 Max |
|---|---|---|
| LMArena Longer Query | 996 | 1484 |

## Writing & Preference

- Phi 3 Mini 128k Instruct: 27.3 (#296)
- Qwen3.7 Max: 65.2 (#52)

| Benchmark | Phi 3 Mini 128k Instruct | Qwen3.7 Max |
|---|---|---|
| LMArena Text | 1050 | 1476 |
| LMArena Creative Writing | 1024 | 1450 |
| LMArena Multi-Turn | 989 | 1482 |
| EQ-Bench 4 | — | 1110 |

## FAQ

### Is Phi 3 Mini 128k Instruct better than Qwen3.7 Max?

Qwen3.7 Max is the stronger model overall, scoring 51.4 to 29.1 on the Noometry Index.

### Is Phi 3 Mini 128k Instruct or Qwen3.7 Max better for coding?

Qwen3.7 Max scores higher on coding benchmarks: 50.2 versus 28.3 in the Noometry coding category.

### How many benchmarks do Phi 3 Mini 128k Instruct and Qwen3.7 Max share?

12 benchmarks have published results for both models. Phi 3 Mini 128k Instruct has 19 scored results on Noometry and Qwen3.7 Max has 33.