Model comparison
Phi-4 Mini vs Qwen3-4B
Qwen3-4B is the stronger model overall, scoring 31.9 to 30.9 on the Noometry Index.
Last verified . 1 shared benchmarks.
Microsoft
Alibaba (Qwen)Summary
- They share 1 benchmark with published results for both. Phi-4 Mini scores higher in 1 category and Qwen3-4B in 1 category; 2 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Qwen3-4B leads 33.0 to 25.3.
- The biggest single-benchmark swing is Vectara Hallucination Rate: 23.5% for Phi-4 Mini and 5.7% for Qwen3-4B.
Side by side
| Phi-4 Mini | Qwen3-4B | |
|---|---|---|
| Provider | Microsoft | Alibaba (Qwen) |
| Noometry Index | 30.9 | 31.9 |
| Released | 2024-12-11 | 2025-04-29 |
| Weights | Open | Open |
| Context window | 128K | — |
| Max output | 4K | — |
| Input $ / M tokens | $0.075 | — |
| Output $ / M tokens | $0.30 | — |
| Results tracked | 3 | 6 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Not comparable
Phi-4 Mini: 28.1 (#317), Qwen3-4B: —
| Benchmark | Phi-4 Mini | Qwen3-4B |
|---|---|---|
| SciCode | 10.8% | — |
Agentic & Tool Use Not comparable
Phi-4 Mini: —, Qwen3-4B: 27.6 (#100)
| Benchmark | Phi-4 Mini | Qwen3-4B |
|---|---|---|
| Berkeley Function Calling Leaderboard | — | 35.7% |
Reasoning Phi-4 Mini leads
Phi-4 Mini: 22.4 (#195), Qwen3-4B: 19.2 (#268)
| Benchmark | Phi-4 Mini | Qwen3-4B |
|---|---|---|
| CritPt | 0% | — |
| Chess Puzzles | — | 4% |
Math Not comparable
Phi-4 Mini: —, Qwen3-4B: 29.7 (#240)
| Benchmark | Phi-4 Mini | Qwen3-4B |
|---|---|---|
| MathArena Final-Answer Competitions | — | 38.5% |
| OTIS Mock AIME 2024-2025 | — | 52.2% |
Knowledge Qwen3-4B leads
Phi-4 Mini: 25.3 (#262), Qwen3-4B: 33.0 (#208)
| Benchmark | Phi-4 Mini | Qwen3-4B |
|---|---|---|
| Vectara Hallucination Rate | 23.5% | 5.7% |
| GPQA Diamond | — | 52.3% |
Frequently asked questions
Is Phi-4 Mini better than Qwen3-4B?
Qwen3-4B is the stronger model overall, scoring 31.9 to 30.9 on the Noometry Index.
How many benchmarks do Phi-4 Mini and Qwen3-4B share?
1 benchmark has published results for both models. Phi-4 Mini has 3 scored results on Noometry and Qwen3-4B has 6.