Model comparison
Phi-4 Mini vs Qwen2-72B
Phi-4 Mini and Qwen2-72B score almost the same on the Noometry Index (30.9 vs 30.0), 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 knowledge, where Phi-4 Mini leads 25.3 to 21.2.
Side by side
| Phi-4 Mini | Qwen2-72B | |
|---|---|---|
| Provider | Microsoft | Alibaba (Qwen) |
| Noometry Index | 30.9 | 30.0 |
| Released | 2024-12-11 | 2024-06-07 |
| Weights | Open | Open |
| Context window | 128K | — |
| Max output | 4K | — |
| Input $ / M tokens | $0.075 | — |
| Output $ / M tokens | $0.30 | — |
| Results tracked | 3 | 26 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Too close to call
Phi-4 Mini: 28.1 (#317), Qwen2-72B: 29.1 (#310)
| Benchmark | Phi-4 Mini | Qwen2-72B |
|---|---|---|
| SciCode | 10.8% | — |
| WeirdML | — | 11.3% |
| BigCodeBench Instruct | — | 38.5% |
| LMArena Coding | — | 1196 |
| BigCodeBench Complete | — | 54% |
Agentic & Tool Use Not comparable
Phi-4 Mini: —, Qwen2-72B: 17.0 (#146)
| Benchmark | Phi-4 Mini | Qwen2-72B |
|---|---|---|
| TheAgentCompany | — | 1.1% |
| METR Time Horizons | — | 29.9% |
Reasoning Too close to call
Phi-4 Mini: 22.4 (#195), Qwen2-72B: 23.2 (#181)
| Benchmark | Phi-4 Mini | Qwen2-72B |
|---|---|---|
| CritPt | 0% | — |
| LMArena Hard Prompts | — | 1191 |
| Epoch Capabilities Index | — | 125.28 |
Math Not comparable
Phi-4 Mini: —, Qwen2-72B: 30.2 (#236)
| Benchmark | Phi-4 Mini | Qwen2-72B |
|---|---|---|
| LMArena Math | — | 1235 |
| MATH Level 5 | — | 39.1% |
Knowledge Phi-4 Mini leads
Phi-4 Mini: 25.3 (#262), Qwen2-72B: 21.2 (#275)
| Benchmark | Phi-4 Mini | Qwen2-72B |
|---|---|---|
| GPQA Diamond | — | 40.8% |
| Vectara Hallucination Rate | 23.5% | — |
| LMArena Expert | — | 1171 |
| MMLU | — | 82.4% |
Multilingual Not comparable
Phi-4 Mini: —, Qwen2-72B: 35.9 (#244)
| Benchmark | Phi-4 Mini | Qwen2-72B |
|---|---|---|
| LMArena Non-English | — | 1176 |
| LMArena Chinese | — | 1240 |
| LMArena French | — | 1170 |
| LMArena German | — | 1151 |
| LMArena Japanese | — | 1111 |
| LMArena Korean | — | 1083 |
| LMArena Russian | — | 1169 |
| LMArena Spanish | — | 1169 |
Instruction Following Not comparable
Phi-4 Mini: —, Qwen2-72B: 61.7 (#241)
| Benchmark | Phi-4 Mini | Qwen2-72B |
|---|---|---|
| LMArena Instruction Following | — | 1181 |
Long Context Not comparable
Phi-4 Mini: —, Qwen2-72B: 36.1 (#235)
| Benchmark | Phi-4 Mini | Qwen2-72B |
|---|---|---|
| LMArena Longer Query | — | 1192 |
Writing & Preference Not comparable
Phi-4 Mini: —, Qwen2-72B: 40.8 (#241)
| Benchmark | Phi-4 Mini | Qwen2-72B |
|---|---|---|
| LMArena Text | — | 1203 |
| LMArena Creative Writing | — | 1181 |
| LMArena Multi-Turn | — | 1196 |
Frequently asked questions
Is Phi-4 Mini better than Qwen2-72B?
Phi-4 Mini and Qwen2-72B score almost the same on the Noometry Index (30.9 vs 30.0), so choose on price, context window or the category you care about most.
Is Phi-4 Mini or Qwen2-72B better for coding?
They score almost the same on coding (28.1 vs 29.1); test both on your own repository before choosing.
How many benchmarks do Phi-4 Mini and Qwen2-72B share?
0 benchmarks have published results for both models. Phi-4 Mini has 3 scored results on Noometry and Qwen2-72B has 26.