Model comparison
Phi-4 Mini vs Qwen1.5-7B
Phi-4 Mini and Qwen1.5-7B score almost the same on the Noometry Index (30.9 vs 31.4), so choose on price, context window or the category you care about most.
Last verified . 0 shared benchmarks.
Microsoft
Alibaba (Qwen)Summary
- The widest gap is in coding, where Qwen1.5-7B leads 32.2 to 28.1.
Side by side
| Phi-4 Mini | Qwen1.5-7B | |
|---|---|---|
| Provider | Microsoft | Alibaba (Qwen) |
| Noometry Index | 30.9 | 31.4 |
| 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 | 13 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Qwen1.5-7B leads
Phi-4 Mini: 28.1 (#317), Qwen1.5-7B: 32.2 (#276)
| Benchmark | Phi-4 Mini | Qwen1.5-7B |
|---|---|---|
| SciCode | 10.8% | — |
| LMArena Coding | — | 1107 |
Reasoning Phi-4 Mini leads
Phi-4 Mini: 22.4 (#195), Qwen1.5-7B: 20.4 (#240)
| Benchmark | Phi-4 Mini | Qwen1.5-7B |
|---|---|---|
| CritPt | 0% | — |
| LMArena Hard Prompts | — | 1065 |
Math Not comparable
Phi-4 Mini: —, Qwen1.5-7B: 31.4 (#224)
| Benchmark | Phi-4 Mini | Qwen1.5-7B |
|---|---|---|
| LMArena Math | — | 1080 |
Knowledge Qwen1.5-7B leads
Phi-4 Mini: 25.3 (#262), Qwen1.5-7B: 28.7 (#243)
| Benchmark | Phi-4 Mini | Qwen1.5-7B |
|---|---|---|
| Vectara Hallucination Rate | 23.5% | — |
| LMArena Expert | — | 1055 |
| MMLU | — | 62.6% |
Multilingual Not comparable
Phi-4 Mini: —, Qwen1.5-7B: 28.5 (#271)
| Benchmark | Phi-4 Mini | Qwen1.5-7B |
|---|---|---|
| LMArena Non-English | — | 1058 |
| LMArena Chinese | — | 1141 |
| LMArena Russian | — | 1006 |
Instruction Following Not comparable
Phi-4 Mini: —, Qwen1.5-7B: 54.1 (#281)
| Benchmark | Phi-4 Mini | Qwen1.5-7B |
|---|---|---|
| LMArena Instruction Following | — | 1058 |
Long Context Not comparable
Phi-4 Mini: —, Qwen1.5-7B: 33.1 (#266)
| Benchmark | Phi-4 Mini | Qwen1.5-7B |
|---|---|---|
| LMArena Longer Query | — | 1090 |
Writing & Preference Not comparable
Phi-4 Mini: —, Qwen1.5-7B: 29.6 (#293)
| Benchmark | Phi-4 Mini | Qwen1.5-7B |
|---|---|---|
| LMArena Text | — | 1083 |
| LMArena Creative Writing | — | 1035 |
| LMArena Multi-Turn | — | 1062 |
Frequently asked questions
Is Phi-4 Mini better than Qwen1.5-7B?
Phi-4 Mini and Qwen1.5-7B score almost the same on the Noometry Index (30.9 vs 31.4), so choose on price, context window or the category you care about most.
Is Phi-4 Mini or Qwen1.5-7B better for coding?
Qwen1.5-7B scores higher on coding benchmarks: 32.2 versus 28.1 in the Noometry coding category.
How many benchmarks do Phi-4 Mini and Qwen1.5-7B share?
0 benchmarks have published results for both models. Phi-4 Mini has 3 scored results on Noometry and Qwen1.5-7B has 13.