Model comparison
Phi-1.5 vs Qwen3-4B
Qwen3-4B has enough public results to be ranked (#261); Phi-1.5 does not yet, so treat this comparison as directional.
Last verified . 0 shared benchmarks.
Microsoft
Alibaba (Qwen)Side by side
| Phi-1.5 | Qwen3-4B | |
|---|---|---|
| Provider | Microsoft | Alibaba (Qwen) |
| Noometry Index | — | 31.5 |
| Released | 2023-09-11 | 2025-04-29 |
| Weights | Open | Open |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 7 | 6 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Agentic & Tool Use Not comparable
Phi-1.5: —, Qwen3-4B: 27.3 (#94)
| Benchmark | Phi-1.5 | Qwen3-4B |
|---|---|---|
| Berkeley Function Calling Leaderboard | — | 35.7% |
Reasoning Not comparable
Phi-1.5: —, Qwen3-4B: 18.5 (#264)
| Benchmark | Phi-1.5 | Qwen3-4B |
|---|---|---|
| Chess Puzzles | — | 4% |
| Epoch Capabilities Index | 90.82 | — |
| HellaSwag | 47.6% | — |
| WinoGrande | 73.4% | — |
Math Not comparable
Phi-1.5: —, Qwen3-4B: 28.5 (#228)
| Benchmark | Phi-1.5 | Qwen3-4B |
|---|---|---|
| MathArena Final-Answer Competitions | — | 38.5% |
| OTIS Mock AIME 2024-2025 | — | 52.2% |
Knowledge Not comparable
Phi-1.5: —, Qwen3-4B: 33.0 (#198)
| Benchmark | Phi-1.5 | Qwen3-4B |
|---|---|---|
| GPQA Diamond | — | 52.3% |
| Vectara Hallucination Rate | — | 5.7% |
| ARC (AI2) Challenge | 44.4% | — |
| BoolQ | 75.8% | — |
| MMLU | 37.6% | — |
| OpenBookQA | 37.2% | — |
Frequently asked questions
Is Phi-1.5 better than Qwen3-4B?
Qwen3-4B has enough public results to be ranked (#261); Phi-1.5 does not yet, so treat this comparison as directional.
How many benchmarks do Phi-1.5 and Qwen3-4B share?
0 benchmarks have published results for both models. Phi-1.5 has 7 scored results on Noometry and Qwen3-4B has 6.