Model comparison
Phi-4 Mini vs Qwen3-1.7B
Phi-4 Mini is the stronger model overall, scoring 30.9 to 26.6 on the Noometry Index.
Last verified . 0 shared benchmarks.
Microsoft
Alibaba (Qwen)Summary
- The widest gap is in knowledge, where Phi-4 Mini leads 25.3 to 19.6.
Side by side
| Phi-4 Mini | Qwen3-1.7B | |
|---|---|---|
| Provider | Microsoft | Alibaba (Qwen) |
| Noometry Index | 30.9 | 26.6 |
| 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 | 4 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Not comparable
Phi-4 Mini: 28.1 (#317), Qwen3-1.7B: —
| Benchmark | Phi-4 Mini | Qwen3-1.7B |
|---|---|---|
| SciCode | 10.8% | — |
Agentic & Tool Use Not comparable
Phi-4 Mini: —, Qwen3-1.7B: 24.7 (#115)
| Benchmark | Phi-4 Mini | Qwen3-1.7B |
|---|---|---|
| Berkeley Function Calling Leaderboard | — | 28.4% |
Reasoning Phi-4 Mini leads
Phi-4 Mini: 22.4 (#195), Qwen3-1.7B: 19.2 (#267)
| Benchmark | Phi-4 Mini | Qwen3-1.7B |
|---|---|---|
| CritPt | 0% | — |
| Chess Puzzles | — | 0% |
Math Not comparable
Phi-4 Mini: —, Qwen3-1.7B: 16.3 (#294)
| Benchmark | Phi-4 Mini | Qwen3-1.7B |
|---|---|---|
| OTIS Mock AIME 2024-2025 | — | 8.1% |
Knowledge Phi-4 Mini leads
Phi-4 Mini: 25.3 (#262), Qwen3-1.7B: 19.6 (#278)
| Benchmark | Phi-4 Mini | Qwen3-1.7B |
|---|---|---|
| GPQA Diamond | — | 38% |
| Vectara Hallucination Rate | 23.5% | — |
Frequently asked questions
Is Phi-4 Mini better than Qwen3-1.7B?
Phi-4 Mini is the stronger model overall, scoring 30.9 to 26.6 on the Noometry Index.
How many benchmarks do Phi-4 Mini and Qwen3-1.7B share?
0 benchmarks have published results for both models. Phi-4 Mini has 3 scored results on Noometry and Qwen3-1.7B has 4.