Model comparison
Phi-4 Mini vs Qwen2.5 7B Instruct
Phi-4 Mini is the stronger model overall, scoring 30.4 to 28.6 on the Noometry Index.
Last verified . 0 shared benchmarks.
Microsoft
Alibaba (Qwen)Summary
- The widest gap is in coding, where Qwen2.5 7B Instruct leads 35.9 to 27.6.
- Phi-4 Mini is cheaper at $0.075 / $0.30 per million input/output tokens, against $0.17 / $0.70 for Qwen2.5 7B Instruct.
- Qwen2.5 7B Instruct accepts more context: 131K tokens versus 128K.
Side by side
| Phi-4 Mini | Qwen2.5 7B Instruct | |
|---|---|---|
| Provider | Microsoft | Alibaba (Qwen) |
| Noometry Index | 30.4 | 28.6 |
| Released | 2024-12-11 | 2024-09 |
| Weights | Open | Open |
| Context window | 128K | 131K |
| Max output | 4K | 8K |
| Input $ / M tokens | $0.075 | $0.17 |
| Output $ / M tokens | $0.30 | $0.70 |
| Results tracked | 3 | 15 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Qwen2.5 7B Instruct leads
Phi-4 Mini: 27.6 (#312), Qwen2.5 7B Instruct: 35.9 (#204)
| Benchmark | Phi-4 Mini | Qwen2.5 7B Instruct |
|---|---|---|
| SciCode | 10.8% | — |
| BigCodeBench Instruct | — | 37.6% |
| BigCodeBench Complete | — | 46.1% |
Agentic & Tool Use Not comparable
Phi-4 Mini: —, Qwen2.5 7B Instruct: 23.5 (#117)
| Benchmark | Phi-4 Mini | Qwen2.5 7B Instruct |
|---|---|---|
| BALROG | — | 7.8% |
Reasoning Phi-4 Mini leads
Phi-4 Mini: 21.7 (#190), Qwen2.5 7B Instruct: 14.3 (#317)
| Benchmark | Phi-4 Mini | Qwen2.5 7B Instruct |
|---|---|---|
| CritPt | 0% | — |
| Chess Puzzles | — | 0% |
| DTBench | — | 47.7% |
| LMCA | — | 6.4% |
| Epoch Capabilities Index | — | 118.44 |
Math Not comparable
Phi-4 Mini: —, Qwen2.5 7B Instruct: 11.8 (#300)
| Benchmark | Phi-4 Mini | Qwen2.5 7B Instruct |
|---|---|---|
| OTIS Mock AIME 2024-2025 | — | 2.5% |
| Omni-MATH | — | 29.4% |
Knowledge Phi-4 Mini leads
Phi-4 Mini: 24.8 (#261), Qwen2.5 7B Instruct: 17.0 (#281)
| Benchmark | Phi-4 Mini | Qwen2.5 7B Instruct |
|---|---|---|
| GPQA Diamond | — | 35.5% |
| MMLU-Pro | — | 53.9% |
| Vectara Hallucination Rate | 23.5% | — |
| GPQA (HELM) | — | 34.1% |
| MMLU | — | 72.9% |
Instruction Following Not comparable
Phi-4 Mini: —, Qwen2.5 7B Instruct: 63.4 (#226)
| Benchmark | Phi-4 Mini | Qwen2.5 7B Instruct |
|---|---|---|
| IFEval | — | 74.1% |
Writing & Preference Not comparable
Phi-4 Mini: —, Qwen2.5 7B Instruct: 48.8 (#194)
| Benchmark | Phi-4 Mini | Qwen2.5 7B Instruct |
|---|---|---|
| WildBench | — | 73.1% |
Frequently asked questions
Is Phi-4 Mini better than Qwen2.5 7B Instruct?
Phi-4 Mini is the stronger model overall, scoring 30.4 to 28.6 on the Noometry Index.
Which is cheaper, Phi-4 Mini or Qwen2.5 7B Instruct?
Phi-4 Mini is cheaper. It lists at $0.075 per million input tokens and $0.30 per million output tokens; Qwen2.5 7B Instruct lists at $0.17 and $0.70.
Is Phi-4 Mini or Qwen2.5 7B Instruct better for coding?
Qwen2.5 7B Instruct scores higher on coding benchmarks: 35.9 versus 27.6 in the Noometry coding category.
Which has the bigger context window?
Qwen2.5 7B Instruct does, with 131K tokens against 128K.
How many benchmarks do Phi-4 Mini and Qwen2.5 7B Instruct share?
0 benchmarks have published results for both models. Phi-4 Mini has 3 scored results on Noometry and Qwen2.5 7B Instruct has 15.