Model comparison
Phi-4 Mini vs Qwen1.5-14B
Qwen1.5-14B is the stronger model overall, scoring 32.7 to 30.9 on the Noometry Index.
Last verified . 0 shared benchmarks.
Microsoft
Alibaba (Qwen)Summary
- The widest gap is in coding, where Qwen1.5-14B leads 33.1 to 28.1.
Side by side
| Phi-4 Mini | Qwen1.5-14B | |
|---|---|---|
| Provider | Microsoft | Alibaba (Qwen) |
| Noometry Index | 30.9 | 32.7 |
| Released | 2024-12-11 | 2024-02-04 |
| Weights | Open | Open |
| Context window | 128K | — |
| Max output | 4K | — |
| Input $ / M tokens | $0.075 | — |
| Output $ / M tokens | $0.30 | — |
| Results tracked | 3 | 17 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Qwen1.5-14B leads
Phi-4 Mini: 28.1 (#317), Qwen1.5-14B: 33.1 (#263)
| Benchmark | Phi-4 Mini | Qwen1.5-14B |
|---|---|---|
| SciCode | 10.8% | — |
| LMArena Coding | — | 1138 |
Reasoning Phi-4 Mini leads
Phi-4 Mini: 22.4 (#195), Qwen1.5-14B: 21.4 (#223)
| Benchmark | Phi-4 Mini | Qwen1.5-14B |
|---|---|---|
| CritPt | 0% | — |
| LMArena Hard Prompts | — | 1113 |
Math Not comparable
Phi-4 Mini: —, Qwen1.5-14B: 32.4 (#215)
| Benchmark | Phi-4 Mini | Qwen1.5-14B |
|---|---|---|
| LMArena Math | — | 1125 |
Knowledge Qwen1.5-14B leads
Phi-4 Mini: 25.3 (#262), Qwen1.5-14B: 29.8 (#232)
| Benchmark | Phi-4 Mini | Qwen1.5-14B |
|---|---|---|
| Vectara Hallucination Rate | 23.5% | — |
| LMArena Expert | — | 1094 |
| MMLU | — | 68.6% |
Multilingual Not comparable
Phi-4 Mini: —, Qwen1.5-14B: 30.7 (#262)
| Benchmark | Phi-4 Mini | Qwen1.5-14B |
|---|---|---|
| LMArena Non-English | — | 1095 |
| LMArena Chinese | — | 1147 |
| LMArena French | — | 1116 |
| LMArena German | — | 1043 |
| LMArena Japanese | — | 1019 |
| LMArena Russian | — | 1046 |
| LMArena Spanish | — | 1085 |
Instruction Following Not comparable
Phi-4 Mini: —, Qwen1.5-14B: 56.8 (#271)
| Benchmark | Phi-4 Mini | Qwen1.5-14B |
|---|---|---|
| LMArena Instruction Following | — | 1102 |
Long Context Not comparable
Phi-4 Mini: —, Qwen1.5-14B: 33.7 (#257)
| Benchmark | Phi-4 Mini | Qwen1.5-14B |
|---|---|---|
| LMArena Longer Query | — | 1113 |
Writing & Preference Not comparable
Phi-4 Mini: —, Qwen1.5-14B: 33.6 (#276)
| Benchmark | Phi-4 Mini | Qwen1.5-14B |
|---|---|---|
| LMArena Text | — | 1128 |
| LMArena Creative Writing | — | 1091 |
| LMArena Multi-Turn | — | 1110 |
Frequently asked questions
Is Phi-4 Mini better than Qwen1.5-14B?
Qwen1.5-14B is the stronger model overall, scoring 32.7 to 30.9 on the Noometry Index.
Is Phi-4 Mini or Qwen1.5-14B better for coding?
Qwen1.5-14B scores higher on coding benchmarks: 33.1 versus 28.1 in the Noometry coding category.
How many benchmarks do Phi-4 Mini and Qwen1.5-14B share?
0 benchmarks have published results for both models. Phi-4 Mini has 3 scored results on Noometry and Qwen1.5-14B has 17.