Model comparison
Phi 3 Mini 4k Instruct vs Qwen Max
Qwen Max is the stronger model overall, scoring 34.7 to 27.9 on the Noometry Index.
Last verified . 17 shared benchmarks.
Microsoft
Alibaba (Qwen)Summary
- They share 17 benchmarks with published results for both. Phi 3 Mini 4k Instruct scores higher in 1 category and Qwen Max in 7 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Qwen Max leads 47.8 to 27.6.
- Phi 3 Mini 4k Instruct has downloadable open weights; the other is API-only.
Side by side
| Phi 3 Mini 4k Instruct | Qwen Max | |
|---|---|---|
| Provider | Microsoft | Alibaba (Qwen) |
| Noometry Index | 27.9 | 34.7 |
| Released | 2024-04-23 | 2024-04-03 |
| Weights | Open | Proprietary |
| Context window | — | 33K |
| Max output | — | 8K |
| Input $ / M tokens | — | $1.60 |
| Output $ / M tokens | — | $6.40 |
| Results tracked | 35 | 23 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Qwen Max leads
Phi 3 Mini 4k Instruct: 26.6 (#323), Qwen Max: 30.7 (#292)
| Benchmark | Phi 3 Mini 4k Instruct | Qwen Max |
|---|---|---|
| LMArena Coding | 1093 | 1288 |
| Aider Polyglot | — | 21.8% |
| LiveBench Coding | 15.5% | — |
| HumanEval+ | 59.1% | — |
| MBPP+ | 54.2% | — |
Reasoning Qwen Max leads
Phi 3 Mini 4k Instruct: 14.1 (#328), Qwen Max: 25.1 (#151)
| Benchmark | Phi 3 Mini 4k Instruct | Qwen Max |
|---|---|---|
| LMArena Hard Prompts | 1072 | 1269 |
| Chess Puzzles | 0% | — |
| LiveBench Reasoning | 26.8% | — |
| LiveBench Data Analysis | 34.7% | — |
| Adversarial NLI | 52.8% | — |
| BIG-Bench Hard | 71.7% | — |
| HellaSwag | 76.7% | — |
| LiveBench | 22.4% | — |
| WinoGrande | 70.8% | — |
Math Phi 3 Mini 4k Instruct leads
Phi 3 Mini 4k Instruct: 26.6 (#257), Qwen Max: 22.3 (#276)
| Benchmark | Phi 3 Mini 4k Instruct | Qwen Max |
|---|---|---|
| LMArena Math | 1111 | 1275 |
| OTIS Mock AIME 2024-2025 | — | 16.1% |
| LiveBench Math | 15.7% | — |
| MATH Level 5 | — | 67.2% |
| FrontierMath (Feb 2025 set) | — | 1% |
Knowledge Qwen Max leads
Phi 3 Mini 4k Instruct: 28.5 (#246), Qwen Max: 30.3 (#228)
| Benchmark | Phi 3 Mini 4k Instruct | Qwen Max |
|---|---|---|
| LMArena Expert | 1045 | 1248 |
| GPQA Diamond | — | 56.1% |
| ARC (AI2) Challenge | 84.9% | — |
| MMLU | 68.8% | — |
| OpenBookQA | 88% | — |
| TriviaQA | 64% | — |
Multilingual Qwen Max leads
Phi 3 Mini 4k Instruct: 26.3 (#280), Qwen Max: 41.8 (#202)
| Benchmark | Phi 3 Mini 4k Instruct | Qwen Max |
|---|---|---|
| LMArena Non-English | 1021 | 1263 |
| LMArena Chinese | 1021 | 1254 |
| LMArena French | 1076 | 1330 |
| LMArena German | 1044 | 1254 |
| LMArena Japanese | 935 | 1205 |
| LMArena Korean | 905 | 1142 |
| LMArena Russian | 1022 | 1274 |
| LMArena Spanish | 1085 | 1290 |
Instruction Following Qwen Max leads
Phi 3 Mini 4k Instruct: 47.7 (#303), Qwen Max: 66.5 (#208)
| Benchmark | Phi 3 Mini 4k Instruct | Qwen Max |
|---|---|---|
| LMArena Instruction Following | 1053 | 1262 |
| LiveBench Instruction Following | 39.1% | — |
Long Context Qwen Max leads
Phi 3 Mini 4k Instruct: 31.7 (#276), Qwen Max: 39.4 (#180)
| Benchmark | Phi 3 Mini 4k Instruct | Qwen Max |
|---|---|---|
| LMArena Longer Query | 1044 | 1288 |
| Fiction.LiveBench | — | 66.7% |
Writing & Preference Qwen Max leads
Phi 3 Mini 4k Instruct: 27.6 (#300), Qwen Max: 47.8 (#205)
| Benchmark | Phi 3 Mini 4k Instruct | Qwen Max |
|---|---|---|
| LMArena Text | 1073 | 1282 |
| LMArena Creative Writing | 1037 | 1248 |
| LMArena Multi-Turn | 1018 | 1277 |
| LiveBench Language | 9.2% | — |
Frequently asked questions
Is Phi 3 Mini 4k Instruct better than Qwen Max?
Qwen Max is the stronger model overall, scoring 34.7 to 27.9 on the Noometry Index.
Is Phi 3 Mini 4k Instruct or Qwen Max better for coding?
Qwen Max scores higher on coding benchmarks: 30.7 versus 26.6 in the Noometry coding category.
How many benchmarks do Phi 3 Mini 4k Instruct and Qwen Max share?
17 benchmarks have published results for both models. Phi 3 Mini 4k Instruct has 35 scored results on Noometry and Qwen Max has 23.