Model comparison
Phi-4 vs Qwen1.5-32B
Phi-4 and Qwen1.5-32B score almost the same on the Noometry Index (31.2 vs 30.5), so choose on price, context window or the category you care about most.
Last verified . 21 shared benchmarks.
Microsoft
Alibaba (Qwen)Summary
- They share 21 benchmarks with published results for both. Phi-4 scores higher in 6 categories and Qwen1.5-32B in 2 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Phi-4 leads 32.6 to 13.5.
- The biggest single-benchmark swing is GPQA Diamond: 56.1% for Phi-4 and 30.7% for Qwen1.5-32B.
Side by side
| Phi-4 | Qwen1.5-32B | |
|---|---|---|
| Provider | Microsoft | Alibaba (Qwen) |
| Noometry Index | 31.2 | 30.5 |
| Released | 2024-12-11 | 2024-02-04 |
| Weights | Open | Open |
| Context window | 128K | — |
| Max output | 4K | — |
| Input $ / M tokens | $0.07 | — |
| Output $ / M tokens | $0.14 | — |
| Results tracked | 37 | 21 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Phi-4 leads
Phi-4: 34.4 (#239), Qwen1.5-32B: 31.7 (#282)
| Benchmark | Phi-4 | Qwen1.5-32B |
|---|---|---|
| BigCodeBench Instruct | 45.5% | 32.3% |
| LMArena Coding | 1231 | 1155 |
| BigCodeBench Complete | 55.4% | 42% |
| LiveBench Coding | 30.7% | — |
Agentic & Tool Use Not comparable
Phi-4: 22.8 (#128), Qwen1.5-32B: —
| Benchmark | Phi-4 | Qwen1.5-32B |
|---|---|---|
| Berkeley Function Calling Leaderboard | 28.8% | — |
| BALROG | 11.6% | — |
Reasoning Qwen1.5-32B leads
Phi-4: 17.7 (#291), Qwen1.5-32B: 21.8 (#212)
| Benchmark | Phi-4 | Qwen1.5-32B |
|---|---|---|
| LMArena Hard Prompts | 1220 | 1130 |
| Chess Puzzles | 1% | — |
| LiveBench Reasoning | 47.8% | — |
| LiveBench Data Analysis | 45.2% | — |
| Epoch Capabilities Index | 130.42 | — |
| LiveBench | 41.6% | — |
Math Qwen1.5-32B leads
Phi-4: 20.8 (#285), Qwen1.5-32B: 33.0 (#207)
| Benchmark | Phi-4 | Qwen1.5-32B |
|---|---|---|
| LMArena Math | 1246 | 1155 |
| OTIS Mock AIME 2024-2025 | 13.8% | — |
| LiveBench Math | 42% | — |
| MATH Level 5 | 64.9% | — |
Knowledge Phi-4 leads
Phi-4: 32.6 (#209), Qwen1.5-32B: 13.5 (#296)
| Benchmark | Phi-4 | Qwen1.5-32B |
|---|---|---|
| GPQA Diamond | 56.1% | 30.7% |
| LMArena Expert | 1203 | 1126 |
| MMLU | 84.8% | 74.4% |
| Confabulations | 29.4% | — |
| Vectara Hallucination Rate | 3.7% | — |
Multilingual Phi-4 leads
Phi-4: 37.2 (#237), Qwen1.5-32B: 31.4 (#259)
| Benchmark | Phi-4 | Qwen1.5-32B |
|---|---|---|
| LMArena Non-English | 1197 | 1106 |
| LMArena Chinese | 1212 | 1177 |
| LMArena French | 1224 | 1101 |
| LMArena German | 1222 | 1058 |
| LMArena Japanese | 1158 | 1027 |
| LMArena Korean | 1151 | 1008 |
| LMArena Russian | 1209 | 1073 |
| LMArena Spanish | 1234 | 1089 |
Instruction Following Phi-4 leads
Phi-4: 60.4 (#251), Qwen1.5-32B: 57.7 (#265)
| Benchmark | Phi-4 | Qwen1.5-32B |
|---|---|---|
| LMArena Instruction Following | 1201 | 1116 |
| LiveBench Instruction Following | 58.4% | — |
Long Context Phi-4 leads
Phi-4: 36.9 (#226), Qwen1.5-32B: 34.7 (#246)
| Benchmark | Phi-4 | Qwen1.5-32B |
|---|---|---|
| LMArena Longer Query | 1217 | 1146 |
Writing & Preference Phi-4 leads
Phi-4: 40.5 (#244), Qwen1.5-32B: 34.2 (#271)
| Benchmark | Phi-4 | Qwen1.5-32B |
|---|---|---|
| LMArena Text | 1217 | 1137 |
| LMArena Creative Writing | 1182 | 1083 |
| LMArena Multi-Turn | 1206 | 1140 |
| Short-Story Creative Writing | 62.6% | — |
| LiveBench Language | 25.6% | — |
Frequently asked questions
Is Phi-4 better than Qwen1.5-32B?
Phi-4 and Qwen1.5-32B score almost the same on the Noometry Index (31.2 vs 30.5), so choose on price, context window or the category you care about most.
Is Phi-4 or Qwen1.5-32B better for coding?
Phi-4 scores higher on coding benchmarks: 34.4 versus 31.7 in the Noometry coding category.
How many benchmarks do Phi-4 and Qwen1.5-32B share?
21 benchmarks have published results for both models. Phi-4 has 37 scored results on Noometry and Qwen1.5-32B has 21.