Model comparison
Phi-4 vs Qwen3 14B
Qwen3 14B is the stronger model overall, scoring 35.5 to 31.2 on the Noometry Index. Phi-4 costs 7.0× less per token, which makes it the better buy when Qwen3 14B's lead doesn't matter for your workload.
Last verified . 6 shared benchmarks.
Microsoft
Alibaba (Qwen)Summary
- They share 6 benchmarks with published results for both. Phi-4 scores higher in 0 categories and Qwen3 14B in 6 categories; 5 gaps are clear of the uncertainty.
- The widest gap is in math, where Qwen3 14B leads 38.6 to 20.8.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 13.8% for Phi-4 and 66.4% for Qwen3 14B.
- Phi-4 is cheaper at $0.07 / $0.14 per million input/output tokens, against $0.35 / $1.40 for Qwen3 14B.
- Qwen3 14B accepts more context: 131K tokens versus 128K.
Side by side
| Phi-4 | Qwen3 14B | |
|---|---|---|
| Provider | Microsoft | Alibaba (Qwen) |
| Noometry Index | 31.2 | 35.5 |
| Released | 2024-12-11 | 2025-04 |
| Weights | Open | Open |
| Context window | 128K | 131K |
| Max output | 4K | 8K |
| Input $ / M tokens | $0.07 | $0.35 |
| Output $ / M tokens | $0.14 | $1.40 |
| Results tracked | 37 | 12 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Qwen3 14B leads
Phi-4: 34.4 (#239), Qwen3 14B: 37.3 (#195)
| Benchmark | Phi-4 | Qwen3 14B |
|---|---|---|
| SciCode | — | 31.6% |
| BigCodeBench Instruct | 45.5% | — |
| LiveBench Coding | 30.7% | — |
| LMArena Coding | 1231 | — |
| BigCodeBench Complete | 55.4% | — |
Agentic & Tool Use Qwen3 14B leads
Phi-4: 22.8 (#128), Qwen3 14B: 29.6 (#83)
| Benchmark | Phi-4 | Qwen3 14B |
|---|---|---|
| Berkeley Function Calling Leaderboard | 28.8% | 41% |
| BALROG | 11.6% | — |
Reasoning Too close to call
Phi-4: 17.7 (#291), Qwen3 14B: 18.5 (#280)
| Benchmark | Phi-4 | Qwen3 14B |
|---|---|---|
| Chess Puzzles | 1% | 4% |
| Epoch Capabilities Index | 130.42 | 138.23 |
| Kagi LLM Benchmark | — | 49.1% |
| CritPt | — | 0% |
| LiveBench Reasoning | 47.8% | — |
| LMArena Hard Prompts | 1220 | — |
| DTBench | — | 64% |
| LiveBench Data Analysis | 45.2% | — |
| LMCA | — | 18.2% |
| LiveBench | 41.6% | — |
Math Qwen3 14B leads
Phi-4: 20.8 (#285), Qwen3 14B: 38.6 (#133)
| Benchmark | Phi-4 | Qwen3 14B |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 13.8% | 66.4% |
| LiveBench Math | 42% | — |
| LMArena Math | 1246 | — |
| MATH Level 5 | 64.9% | — |
Knowledge Qwen3 14B leads
Phi-4: 32.6 (#209), Qwen3 14B: 39.3 (#134)
| Benchmark | Phi-4 | Qwen3 14B |
|---|---|---|
| GPQA Diamond | 56.1% | 63.8% |
| Vectara Hallucination Rate | 3.7% | 5.4% |
| Confabulations | 29.4% | — |
| LMArena Expert | 1203 | — |
| MMLU | 84.8% | — |
Multilingual Not comparable
Phi-4: 37.2 (#237), Qwen3 14B: —
| Benchmark | Phi-4 | Qwen3 14B |
|---|---|---|
| LMArena Non-English | 1197 | — |
| LMArena Chinese | 1212 | — |
| LMArena French | 1224 | — |
| LMArena German | 1222 | — |
| LMArena Japanese | 1158 | — |
| LMArena Korean | 1151 | — |
| LMArena Russian | 1209 | — |
| LMArena Spanish | 1234 | — |
Instruction Following Not comparable
Phi-4: 60.4 (#251), Qwen3 14B: —
| Benchmark | Phi-4 | Qwen3 14B |
|---|---|---|
| LiveBench Instruction Following | 58.4% | — |
| LMArena Instruction Following | 1201 | — |
Long Context Qwen3 14B leads
Phi-4: 36.9 (#226), Qwen3 14B: 38.1 (#204)
| Benchmark | Phi-4 | Qwen3 14B |
|---|---|---|
| Fiction.LiveBench | — | 62.5% |
| LMArena Longer Query | 1217 | — |
Writing & Preference Not comparable
Phi-4: 40.5 (#244), Qwen3 14B: —
| Benchmark | Phi-4 | Qwen3 14B |
|---|---|---|
| LMArena Text | 1217 | — |
| LMArena Creative Writing | 1182 | — |
| Short-Story Creative Writing | 62.6% | — |
| LMArena Multi-Turn | 1206 | — |
| LiveBench Language | 25.6% | — |
Frequently asked questions
Is Phi-4 better than Qwen3 14B?
Qwen3 14B is the stronger model overall, scoring 35.5 to 31.2 on the Noometry Index. Phi-4 costs 7.0× less per token, which makes it the better buy when Qwen3 14B's lead doesn't matter for your workload.
Which is cheaper, Phi-4 or Qwen3 14B?
Phi-4 is cheaper. It lists at $0.07 per million input tokens and $0.14 per million output tokens; Qwen3 14B lists at $0.35 and $1.40.
Is Phi-4 or Qwen3 14B better for coding?
Qwen3 14B scores higher on coding benchmarks: 37.3 versus 34.4 in the Noometry coding category.
Which has the bigger context window?
Qwen3 14B does, with 131K tokens against 128K.
How many benchmarks do Phi-4 and Qwen3 14B share?
6 benchmarks have published results for both models. Phi-4 has 37 scored results on Noometry and Qwen3 14B has 12.