Model comparison
Phi-4 Mini vs Qwen2.5 72B Instruct
Qwen2.5 72B Instruct is the stronger model overall, scoring 31.5 to 30.4 on the Noometry Index. Phi-4 Mini costs 19× less per token, which makes it the better buy when Qwen2.5 72B Instruct's lead doesn't matter for your workload.
Last verified . 0 shared benchmarks.
Microsoft
Alibaba (Qwen)Summary
- The widest gap is in coding, where Qwen2.5 72B Instruct leads 32.8 to 27.6.
- Phi-4 Mini is cheaper at $0.075 / $0.30 per million input/output tokens, against $1.40 / $5.60 for Qwen2.5 72B Instruct.
- Qwen2.5 72B Instruct accepts more context: 131K tokens versus 128K.
Side by side
| Phi-4 Mini | Qwen2.5 72B Instruct | |
|---|---|---|
| Provider | Microsoft | Alibaba (Qwen) |
| Noometry Index | 30.4 | 31.5 |
| Released | 2024-12-11 | 2024-09 |
| Weights | Open | Open |
| Context window | 128K | 131K |
| Max output | 4K | 8K |
| Input $ / M tokens | $0.075 | $1.40 |
| Output $ / M tokens | $0.30 | $5.60 |
| Results tracked | 3 | 43 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Qwen2.5 72B Instruct leads
Phi-4 Mini: 27.6 (#312), Qwen2.5 72B Instruct: 32.8 (#256)
| Benchmark | Phi-4 Mini | Qwen2.5 72B Instruct |
|---|---|---|
| SciCode | 10.8% | — |
| WeirdML | — | 16% |
| BigCodeBench Instruct | — | 45.8% |
| LMArena Coding | — | 1293 |
| BigCodeBench Complete | — | 55.9% |
Agentic & Tool Use Not comparable
Phi-4 Mini: —, Qwen2.5 72B Instruct: 22.0 (#124)
| Benchmark | Phi-4 Mini | Qwen2.5 72B Instruct |
|---|---|---|
| TheAgentCompany | — | 5.7% |
| BALROG | — | 16.2% |
| METR Time Horizons | — | 35.8% |
Reasoning Too close to call
Phi-4 Mini: 21.7 (#190), Qwen2.5 72B Instruct: 21.4 (#197)
| Benchmark | Phi-4 Mini | Qwen2.5 72B Instruct |
|---|---|---|
| CritPt | 0% | — |
| LMArena Hard Prompts | — | 1271 |
| DTBench | — | 62.9% |
| LMCA | — | 13.4% |
| BIG-Bench Hard | — | 79.8% |
| Epoch Capabilities Index | — | 129.01 |
| ForecastBench | — | 57.5 |
| HellaSwag | — | 84.8% |
| PIQA | — | 82.6% |
| WinoGrande | — | 82.3% |
Math Not comparable
Phi-4 Mini: —, Qwen2.5 72B Instruct: 18.1 (#281)
| Benchmark | Phi-4 Mini | Qwen2.5 72B Instruct |
|---|---|---|
| OTIS Mock AIME 2024-2025 | — | 8.1% |
| Omni-MATH | — | 33% |
| LMArena Math | — | 1283 |
| MATH Level 5 | — | 63.2% |
Knowledge Qwen2.5 72B Instruct leads
Phi-4 Mini: 24.8 (#261), Qwen2.5 72B Instruct: 26.9 (#247)
| Benchmark | Phi-4 Mini | Qwen2.5 72B Instruct |
|---|---|---|
| GPQA Diamond | — | 49.1% |
| MMLU-Pro | — | 63.1% |
| Confabulations | — | 19.1% |
| Vectara Hallucination Rate | 23.5% | — |
| GPQA (HELM) | — | 42.6% |
| LMArena Expert | — | 1245 |
| ARC (AI2) Challenge | — | 94.5% |
| MMLU | — | 85.3% |
| TriviaQA | — | 71.9% |
Multilingual Not comparable
Phi-4 Mini: —, Qwen2.5 72B Instruct: 41.2 (#208)
| Benchmark | Phi-4 Mini | Qwen2.5 72B Instruct |
|---|---|---|
| LMArena Non-English | — | 1252 |
| LMArena Chinese | — | 1272 |
| LMArena French | — | 1279 |
| LMArena German | — | 1234 |
| LMArena Japanese | — | 1180 |
| LMArena Korean | — | 1188 |
| LMArena Russian | — | 1264 |
| LMArena Spanish | — | 1255 |
Instruction Following Not comparable
Phi-4 Mini: —, Qwen2.5 72B Instruct: 65.7 (#216)
| Benchmark | Phi-4 Mini | Qwen2.5 72B Instruct |
|---|---|---|
| IFEval | — | 80.6% |
| LMArena Instruction Following | — | 1254 |
Long Context Not comparable
Phi-4 Mini: —, Qwen2.5 72B Instruct: 38.9 (#183)
| Benchmark | Phi-4 Mini | Qwen2.5 72B Instruct |
|---|---|---|
| LMArena Longer Query | — | 1282 |
Writing & Preference Not comparable
Phi-4 Mini: —, Qwen2.5 72B Instruct: 46.9 (#210)
| Benchmark | Phi-4 Mini | Qwen2.5 72B Instruct |
|---|---|---|
| LMArena Text | — | 1269 |
| LMArena Creative Writing | — | 1221 |
| WildBench | — | 80.2% |
| LMArena Multi-Turn | — | 1272 |
Frequently asked questions
Is Phi-4 Mini better than Qwen2.5 72B Instruct?
Qwen2.5 72B Instruct is the stronger model overall, scoring 31.5 to 30.4 on the Noometry Index. Phi-4 Mini costs 19× less per token, which makes it the better buy when Qwen2.5 72B Instruct's lead doesn't matter for your workload.
Which is cheaper, Phi-4 Mini or Qwen2.5 72B Instruct?
Phi-4 Mini is cheaper. It lists at $0.075 per million input tokens and $0.30 per million output tokens; Qwen2.5 72B Instruct lists at $1.40 and $5.60.
Is Phi-4 Mini or Qwen2.5 72B Instruct better for coding?
Qwen2.5 72B Instruct scores higher on coding benchmarks: 32.8 versus 27.6 in the Noometry coding category.
Which has the bigger context window?
Qwen2.5 72B Instruct does, with 131K tokens against 128K.
How many benchmarks do Phi-4 Mini and Qwen2.5 72B Instruct share?
0 benchmarks have published results for both models. Phi-4 Mini has 3 scored results on Noometry and Qwen2.5 72B Instruct has 43.