Model comparison
Phi-2 vs Qwen Max
Qwen Max has enough public results to be ranked (#230); Phi-2 does not yet, so treat this comparison as directional.
Last verified . 0 shared benchmarks.
Microsoft
Alibaba (Qwen)Summary
- Phi-2 has downloadable open weights; the other is API-only.
Side by side
| Phi-2 | Qwen Max | |
|---|---|---|
| Provider | Microsoft | Alibaba (Qwen) |
| Noometry Index | — | 34.7 |
| Released | 2023-12-12 | 2024-04-03 |
| Weights | Open | Proprietary |
| Context window | — | 33K |
| Max output | — | 8K |
| Input $ / M tokens | — | $1.60 |
| Output $ / M tokens | — | $6.40 |
| Results tracked | 11 | 23 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Not comparable
Phi-2: —, Qwen Max: 30.7 (#292)
| Benchmark | Phi-2 | Qwen Max |
|---|---|---|
| Aider Polyglot | — | 21.8% |
| LMArena Coding | — | 1288 |
| HumanEval+ | 45.1% | — |
| MBPP+ | 54.2% | — |
Reasoning Not comparable
Phi-2: —, Qwen Max: 25.1 (#151)
| Benchmark | Phi-2 | Qwen Max |
|---|---|---|
| LMArena Hard Prompts | — | 1269 |
| Adversarial NLI | 42.5% | — |
| BIG-Bench Hard | 59.4% | — |
| Epoch Capabilities Index | 107.94 | — |
| HellaSwag | 53.6% | — |
| WinoGrande | 54.7% | — |
Math Not comparable
Phi-2: —, Qwen Max: 22.3 (#276)
| Benchmark | Phi-2 | Qwen Max |
|---|---|---|
| OTIS Mock AIME 2024-2025 | — | 16.1% |
| LMArena Math | — | 1275 |
| MATH Level 5 | — | 67.2% |
| FrontierMath (Feb 2025 set) | — | 1% |
Knowledge Not comparable
Phi-2: —, Qwen Max: 30.3 (#228)
| Benchmark | Phi-2 | Qwen Max |
|---|---|---|
| GPQA Diamond | — | 56.1% |
| LMArena Expert | — | 1248 |
| ARC (AI2) Challenge | 75.9% | — |
| MMLU | 58.4% | — |
| OpenBookQA | 73.6% | — |
| TriviaQA | 45.2% | — |
Multilingual Not comparable
Phi-2: —, Qwen Max: 41.8 (#202)
| Benchmark | Phi-2 | Qwen Max |
|---|---|---|
| LMArena Non-English | — | 1263 |
| LMArena Chinese | — | 1254 |
| LMArena French | — | 1330 |
| LMArena German | — | 1254 |
| LMArena Japanese | — | 1205 |
| LMArena Korean | — | 1142 |
| LMArena Russian | — | 1274 |
| LMArena Spanish | — | 1290 |
Instruction Following Not comparable
Phi-2: —, Qwen Max: 66.5 (#208)
| Benchmark | Phi-2 | Qwen Max |
|---|---|---|
| LMArena Instruction Following | — | 1262 |
Long Context Not comparable
Phi-2: —, Qwen Max: 39.4 (#180)
| Benchmark | Phi-2 | Qwen Max |
|---|---|---|
| Fiction.LiveBench | — | 66.7% |
| LMArena Longer Query | — | 1288 |
Writing & Preference Not comparable
Phi-2: —, Qwen Max: 47.8 (#205)
| Benchmark | Phi-2 | Qwen Max |
|---|---|---|
| LMArena Text | — | 1282 |
| LMArena Creative Writing | — | 1248 |
| LMArena Multi-Turn | — | 1277 |
Frequently asked questions
Is Phi-2 better than Qwen Max?
Qwen Max has enough public results to be ranked (#230); Phi-2 does not yet, so treat this comparison as directional.
How many benchmarks do Phi-2 and Qwen Max share?
0 benchmarks have published results for both models. Phi-2 has 11 scored results on Noometry and Qwen Max has 23.