Model comparison
Phi 3 Mini 4k Instruct vs Qwen3.7 Max
Qwen3.7 Max is the stronger model overall, scoring 51.5 to 27.9 on the Noometry Index.
Last verified . 13 shared benchmarks.
Microsoft
Alibaba (Qwen)Summary
- They share 13 benchmarks with published results for both. Phi 3 Mini 4k 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 65.0 to 27.6.
- The biggest single-benchmark swing is Chess Puzzles: 0% for Phi 3 Mini 4k Instruct and 19% for Qwen3.7 Max.
- Phi 3 Mini 4k Instruct has downloadable open weights; the other is API-only.
Side by side
| Phi 3 Mini 4k Instruct | Qwen3.7 Max | |
|---|---|---|
| Provider | Microsoft | Alibaba (Qwen) |
| Noometry Index | 27.9 | 51.5 |
| Released | 2024-04-23 | 2026-05-19 |
| Weights | Open | Proprietary |
| Context window | — | 1M |
| Max output | — | 131K |
| Input $ / M tokens | — | $2.50 |
| Output $ / M tokens | — | $7.50 |
| Results tracked | 35 | 33 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Qwen3.7 Max leads
Phi 3 Mini 4k Instruct: 26.6 (#323), Qwen3.7 Max: 50.4 (#45)
| Benchmark | Phi 3 Mini 4k Instruct | Qwen3.7 Max |
|---|---|---|
| LMArena Coding | 1093 | 1498 |
| SWE-bench Verified | — | 77.3% |
| LMArena WebDev | — | 1515 |
| SciCode | — | 48.8% |
| LiveBench Coding | 15.5% | — |
| ALE-Bench | — | 1,189 |
| HumanEval+ | 59.1% | — |
| MBPP+ | 54.2% | — |
Agentic & Tool Use Not comparable
Phi 3 Mini 4k Instruct: —, Qwen3.7 Max: 22.1 (#135)
| Benchmark | Phi 3 Mini 4k Instruct | Qwen3.7 Max |
|---|---|---|
| GBAEval | — | 0.4% |
Reasoning Qwen3.7 Max leads
Phi 3 Mini 4k Instruct: 14.1 (#328), Qwen3.7 Max: 49.2 (#38)
| Benchmark | Phi 3 Mini 4k Instruct | Qwen3.7 Max |
|---|---|---|
| Chess Puzzles | 0% | 19% |
| LMArena Hard Prompts | 1072 | 1483 |
| SimpleBench | — | 70.4% |
| NYT Connections (extended) | — | 85.1% |
| CritPt | — | 13.4% |
| EBR-Bench | — | 9.5% |
| LiveBench Reasoning | 26.8% | — |
| Mystery Game Puzzles | — | 32% |
| DTBench | — | 92.3% |
| LiveBench Data Analysis | 34.7% | — |
| LMCA | — | 44% |
| Adversarial NLI | 52.8% | — |
| BIG-Bench Hard | 71.7% | — |
| Epoch Capabilities Index | — | 153.68 |
| HellaSwag | 76.7% | — |
| LiveBench | 22.4% | — |
| WinoGrande | 70.8% | — |
Math Qwen3.7 Max leads
Phi 3 Mini 4k Instruct: 26.6 (#257), Qwen3.7 Max: 62.4 (#32)
| Benchmark | Phi 3 Mini 4k Instruct | Qwen3.7 Max |
|---|---|---|
| LMArena Math | 1111 | 1490 |
| FrontierMath (Tiers 1-3) | — | 64.6% |
| FrontierMath Tier 4 | — | 34.1% |
| OTIS Mock AIME 2024-2025 | — | 95.6% |
| ProofBench | — | 26% |
| LiveBench Math | 15.7% | — |
Knowledge Qwen3.7 Max leads
Phi 3 Mini 4k Instruct: 28.5 (#246), Qwen3.7 Max: 61.6 (#28)
| Benchmark | Phi 3 Mini 4k Instruct | Qwen3.7 Max |
|---|---|---|
| LMArena Expert | 1045 | 1488 |
| GPQA Diamond | — | 90.9% |
| SimpleQA Verified | — | 55.8% |
| ARC (AI2) Challenge | 84.9% | — |
| MMLU | 68.8% | — |
| OpenBookQA | 88% | — |
| TriviaQA | 64% | — |
Multilingual Qwen3.7 Max leads
Phi 3 Mini 4k Instruct: 26.3 (#280), Qwen3.7 Max: 56.9 (#15)
| Benchmark | Phi 3 Mini 4k Instruct | Qwen3.7 Max |
|---|---|---|
| LMArena Non-English | 1021 | 1474 |
| LMArena Chinese | 1021 | 1530 |
| LMArena Russian | 1022 | 1484 |
| LMArena French | 1076 | — |
| LMArena German | 1044 | — |
| LMArena Japanese | 935 | — |
| LMArena Korean | 905 | — |
| LMArena Spanish | 1085 | — |
Instruction Following Qwen3.7 Max leads
Phi 3 Mini 4k Instruct: 47.7 (#303), Qwen3.7 Max: 76.7 (#38)
| Benchmark | Phi 3 Mini 4k Instruct | Qwen3.7 Max |
|---|---|---|
| LMArena Instruction Following | 1053 | 1460 |
| LiveBench Instruction Following | 39.1% | — |
Long Context Qwen3.7 Max leads
Phi 3 Mini 4k Instruct: 31.7 (#276), Qwen3.7 Max: 45.4 (#40)
| Benchmark | Phi 3 Mini 4k Instruct | Qwen3.7 Max |
|---|---|---|
| LMArena Longer Query | 1044 | 1482 |
Writing & Preference Qwen3.7 Max leads
Phi 3 Mini 4k Instruct: 27.6 (#300), Qwen3.7 Max: 65.0 (#54)
| Benchmark | Phi 3 Mini 4k Instruct | Qwen3.7 Max |
|---|---|---|
| LMArena Text | 1073 | 1476 |
| LMArena Creative Writing | 1037 | 1449 |
| LMArena Multi-Turn | 1018 | 1481 |
| EQ-Bench 4 | — | 1110 |
| LiveBench Language | 9.2% | — |
Frequently asked questions
Is Phi 3 Mini 4k Instruct better than Qwen3.7 Max?
Qwen3.7 Max is the stronger model overall, scoring 51.5 to 27.9 on the Noometry Index.
Is Phi 3 Mini 4k Instruct or Qwen3.7 Max better for coding?
Qwen3.7 Max scores higher on coding benchmarks: 50.4 versus 26.6 in the Noometry coding category.
How many benchmarks do Phi 3 Mini 4k Instruct and Qwen3.7 Max share?
13 benchmarks have published results for both models. Phi 3 Mini 4k Instruct has 35 scored results on Noometry and Qwen3.7 Max has 33.