Model comparison
Phi-4 vs Qwen-14B
Phi-4 and Qwen-14B score almost the same on the Noometry Index (31.2 vs 31.4), so choose on price, context window or the category you care about most.
Last verified . 12 shared benchmarks.
Microsoft
Alibaba (Qwen)Summary
- They share 12 benchmarks with published results for both. Phi-4 scores higher in 5 categories and Qwen-14B in 2 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Phi-4 leads 40.5 to 27.6.
Side by side
| Phi-4 | Qwen-14B | |
|---|---|---|
| Provider | Microsoft | Alibaba (Qwen) |
| Noometry Index | 31.2 | 31.4 |
| Released | 2024-12-11 | 2023-09-24 |
| Weights | Open | Open |
| Context window | 128K | — |
| Max output | 4K | — |
| Input $ / M tokens | $0.07 | — |
| Output $ / M tokens | $0.14 | — |
| Results tracked | 37 | 18 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Phi-4 leads
Phi-4: 34.4 (#239), Qwen-14B: 31.2 (#288)
| Benchmark | Phi-4 | Qwen-14B |
|---|---|---|
| LMArena Coding | 1231 | 1071 |
| BigCodeBench Instruct | 45.5% | — |
| LiveBench Coding | 30.7% | — |
| BigCodeBench Complete | 55.4% | — |
Agentic & Tool Use Not comparable
Phi-4: 22.8 (#128), Qwen-14B: —
| Benchmark | Phi-4 | Qwen-14B |
|---|---|---|
| Berkeley Function Calling Leaderboard | 28.8% | — |
| BALROG | 11.6% | — |
Reasoning Qwen-14B leads
Phi-4: 17.7 (#291), Qwen-14B: 19.6 (#257)
| Benchmark | Phi-4 | Qwen-14B |
|---|---|---|
| LMArena Hard Prompts | 1220 | 1027 |
| Epoch Capabilities Index | 130.42 | 113.03 |
| Chess Puzzles | 1% | — |
| LiveBench Reasoning | 47.8% | — |
| LiveBench Data Analysis | 45.2% | — |
| BIG-Bench Hard | — | 55% |
| LAMBADA | — | 71.1% |
| LiveBench | 41.6% | — |
| PIQA | — | 79.9% |
Math Qwen-14B leads
Phi-4: 20.8 (#285), Qwen-14B: 31.2 (#227)
| Benchmark | Phi-4 | Qwen-14B |
|---|---|---|
| LMArena Math | 1246 | 1068 |
| OTIS Mock AIME 2024-2025 | 13.8% | — |
| LiveBench Math | 42% | — |
| MATH Level 5 | 64.9% | — |
| GSM8K | — | 61.3% |
Knowledge Not comparable
Phi-4: 32.6 (#209), Qwen-14B: —
| Benchmark | Phi-4 | Qwen-14B |
|---|---|---|
| MMLU | 84.8% | 66.3% |
| GPQA Diamond | 56.1% | — |
| Confabulations | 29.4% | — |
| Vectara Hallucination Rate | 3.7% | — |
| LMArena Expert | 1203 | — |
| ARC (AI2) Challenge | — | 84.4% |
| BoolQ | — | 86.2% |
Multilingual Phi-4 leads
Phi-4: 37.2 (#237), Qwen-14B: 27.5 (#275)
| Benchmark | Phi-4 | Qwen-14B |
|---|---|---|
| LMArena Non-English | 1197 | 1041 |
| LMArena Chinese | 1212 | 1077 |
| LMArena French | 1224 | — |
| LMArena German | 1222 | — |
| LMArena Japanese | 1158 | — |
| LMArena Korean | 1151 | — |
| LMArena Russian | 1209 | — |
| LMArena Spanish | 1234 | — |
Instruction Following Phi-4 leads
Phi-4: 60.4 (#251), Qwen-14B: 52.4 (#289)
| Benchmark | Phi-4 | Qwen-14B |
|---|---|---|
| LMArena Instruction Following | 1201 | 1031 |
| LiveBench Instruction Following | 58.4% | — |
Long Context Phi-4 leads
Phi-4: 36.9 (#226), Qwen-14B: 31.3 (#280)
| Benchmark | Phi-4 | Qwen-14B |
|---|---|---|
| LMArena Longer Query | 1217 | 1028 |
Writing & Preference Phi-4 leads
Phi-4: 40.5 (#244), Qwen-14B: 27.6 (#299)
| Benchmark | Phi-4 | Qwen-14B |
|---|---|---|
| LMArena Text | 1217 | 1051 |
| LMArena Creative Writing | 1182 | 1028 |
| LMArena Multi-Turn | 1206 | 1022 |
| Short-Story Creative Writing | 62.6% | — |
| LiveBench Language | 25.6% | — |
Frequently asked questions
Is Phi-4 better than Qwen-14B?
Phi-4 and Qwen-14B score almost the same on the Noometry Index (31.2 vs 31.4), so choose on price, context window or the category you care about most.
Is Phi-4 or Qwen-14B better for coding?
Phi-4 scores higher on coding benchmarks: 34.4 versus 31.2 in the Noometry coding category.
How many benchmarks do Phi-4 and Qwen-14B share?
12 benchmarks have published results for both models. Phi-4 has 37 scored results on Noometry and Qwen-14B has 18.