Model comparison
Phi-4 Mini vs Qwen-7B
Phi-4 Mini has enough public results to be ranked (#283); Qwen-7B does not yet, so treat this comparison as directional.
Last verified . 0 shared benchmarks.
Microsoft
Alibaba (Qwen)Side by side
| Phi-4 Mini | Qwen-7B | |
|---|---|---|
| Provider | Microsoft | Alibaba (Qwen) |
| Noometry Index | 30.9 | — |
| Released | 2024-12-11 | 2023-09-28 |
| Weights | Open | Open |
| Context window | 128K | — |
| Max output | 4K | — |
| Input $ / M tokens | $0.075 | — |
| Output $ / M tokens | $0.30 | — |
| Results tracked | 3 | 8 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Not comparable
Phi-4 Mini: 28.1 (#317), Qwen-7B: —
| Benchmark | Phi-4 Mini | Qwen-7B |
|---|---|---|
| SciCode | 10.8% | — |
Reasoning Not comparable
Phi-4 Mini: 22.4 (#195), Qwen-7B: —
| Benchmark | Phi-4 Mini | Qwen-7B |
|---|---|---|
| CritPt | 0% | — |
| BIG-Bench Hard | — | 45% |
| Epoch Capabilities Index | — | 106.83 |
| LAMBADA | — | 67.9% |
| PIQA | — | 77.9% |
Math Not comparable
Phi-4 Mini: —, Qwen-7B: —
| Benchmark | Phi-4 Mini | Qwen-7B |
|---|---|---|
| GSM8K | — | 51.7% |
Knowledge Not comparable
Phi-4 Mini: 25.3 (#262), Qwen-7B: —
| Benchmark | Phi-4 Mini | Qwen-7B |
|---|---|---|
| Vectara Hallucination Rate | 23.5% | — |
| ARC (AI2) Challenge | — | 75.3% |
| BoolQ | — | 76.4% |
| MMLU | — | 45% |
Frequently asked questions
Is Phi-4 Mini better than Qwen-7B?
Phi-4 Mini has enough public results to be ranked (#283); Qwen-7B does not yet, so treat this comparison as directional.
How many benchmarks do Phi-4 Mini and Qwen-7B share?
0 benchmarks have published results for both models. Phi-4 Mini has 3 scored results on Noometry and Qwen-7B has 8.