Model comparison
Phi-4 vs Qwen3-4B
Phi-4 and Qwen3-4B score almost the same on the Noometry Index (31.2 vs 31.9), so choose on price, context window or the category you care about most.
Last verified . 5 shared benchmarks.
Microsoft
Alibaba (Qwen)Summary
- They share 5 benchmarks with published results for both. Phi-4 scores higher in 0 categories and Qwen3-4B in 4 categories; 3 gaps are clear of the uncertainty.
- The widest gap is in math, where Qwen3-4B leads 29.7 to 20.8.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 13.8% for Phi-4 and 52.2% for Qwen3-4B.
Side by side
| Phi-4 | Qwen3-4B | |
|---|---|---|
| Provider | Microsoft | Alibaba (Qwen) |
| Noometry Index | 31.2 | 31.9 |
| Released | 2024-12-11 | 2025-04-29 |
| Weights | Open | Open |
| Context window | 128K | — |
| Max output | 4K | — |
| Input $ / M tokens | $0.07 | — |
| Output $ / M tokens | $0.14 | — |
| Results tracked | 37 | 6 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Not comparable
Phi-4: 34.4 (#239), Qwen3-4B: —
| Benchmark | Phi-4 | Qwen3-4B |
|---|---|---|
| BigCodeBench Instruct | 45.5% | — |
| LiveBench Coding | 30.7% | — |
| LMArena Coding | 1231 | — |
| BigCodeBench Complete | 55.4% | — |
Agentic & Tool Use Qwen3-4B leads
Phi-4: 22.8 (#128), Qwen3-4B: 27.6 (#100)
| Benchmark | Phi-4 | Qwen3-4B |
|---|---|---|
| Berkeley Function Calling Leaderboard | 28.8% | 35.7% |
| BALROG | 11.6% | — |
Reasoning Qwen3-4B leads
Phi-4: 17.7 (#291), Qwen3-4B: 19.2 (#268)
| Benchmark | Phi-4 | Qwen3-4B |
|---|---|---|
| Chess Puzzles | 1% | 4% |
| LiveBench Reasoning | 47.8% | — |
| LMArena Hard Prompts | 1220 | — |
| LiveBench Data Analysis | 45.2% | — |
| Epoch Capabilities Index | 130.42 | — |
| LiveBench | 41.6% | — |
Math Qwen3-4B leads
Phi-4: 20.8 (#285), Qwen3-4B: 29.7 (#240)
| Benchmark | Phi-4 | Qwen3-4B |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 13.8% | 52.2% |
| MathArena Final-Answer Competitions | — | 38.5% |
| LiveBench Math | 42% | — |
| LMArena Math | 1246 | — |
| MATH Level 5 | 64.9% | — |
Knowledge Too close to call
Phi-4: 32.6 (#209), Qwen3-4B: 33.0 (#208)
| Benchmark | Phi-4 | Qwen3-4B |
|---|---|---|
| GPQA Diamond | 56.1% | 52.3% |
| Vectara Hallucination Rate | 3.7% | 5.7% |
| Confabulations | 29.4% | — |
| LMArena Expert | 1203 | — |
| MMLU | 84.8% | — |
Multilingual Not comparable
Phi-4: 37.2 (#237), Qwen3-4B: —
| Benchmark | Phi-4 | Qwen3-4B |
|---|---|---|
| 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), Qwen3-4B: —
| Benchmark | Phi-4 | Qwen3-4B |
|---|---|---|
| LiveBench Instruction Following | 58.4% | — |
| LMArena Instruction Following | 1201 | — |
Long Context Not comparable
Phi-4: 36.9 (#226), Qwen3-4B: —
| Benchmark | Phi-4 | Qwen3-4B |
|---|---|---|
| LMArena Longer Query | 1217 | — |
Writing & Preference Not comparable
Phi-4: 40.5 (#244), Qwen3-4B: —
| Benchmark | Phi-4 | Qwen3-4B |
|---|---|---|
| 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 Qwen3-4B?
Phi-4 and Qwen3-4B score almost the same on the Noometry Index (31.2 vs 31.9), so choose on price, context window or the category you care about most.
How many benchmarks do Phi-4 and Qwen3-4B share?
5 benchmarks have published results for both models. Phi-4 has 37 scored results on Noometry and Qwen3-4B has 6.