Model comparison
phi-3-medium 14B vs Qwen3-4B
Qwen3-4B is the stronger model overall, scoring 31.9 to 29.7 on the Noometry Index.
Last verified . 1 shared benchmarks.
Microsoft
Alibaba (Qwen)Summary
- They share 1 benchmark with published results for both. phi-3-medium 14B scores higher in 0 categories and Qwen3-4B in 2 categories; 2 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Qwen3-4B leads 33.0 to 9.1.
- The biggest single-benchmark swing is GPQA Diamond: 27.6% for phi-3-medium 14B and 52.3% for Qwen3-4B.
Side by side
| phi-3-medium 14B | Qwen3-4B | |
|---|---|---|
| Provider | Microsoft | Alibaba (Qwen) |
| Noometry Index | 29.7 | 31.9 |
| Released | 2024-04-23 | 2025-04-29 |
| Weights | Open | Open |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 13 | 6 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Not comparable
phi-3-medium 14B: 36.8 (#201), Qwen3-4B: —
| Benchmark | phi-3-medium 14B | Qwen3-4B |
|---|---|---|
| BigCodeBench Instruct | 37.6% | — |
| BigCodeBench Complete | 48.7% | — |
Agentic & Tool Use Not comparable
phi-3-medium 14B: —, Qwen3-4B: 27.6 (#100)
| Benchmark | phi-3-medium 14B | Qwen3-4B |
|---|---|---|
| Berkeley Function Calling Leaderboard | — | 35.7% |
Reasoning Not comparable
phi-3-medium 14B: —, Qwen3-4B: 19.2 (#268)
| Benchmark | phi-3-medium 14B | Qwen3-4B |
|---|---|---|
| Chess Puzzles | — | 4% |
| Adversarial NLI | 55.8% | — |
| BIG-Bench Hard | 81.4% | — |
| Epoch Capabilities Index | 121.23 | — |
| HellaSwag | 82.4% | — |
| WinoGrande | 81.5% | — |
Math Qwen3-4B leads
phi-3-medium 14B: 27.3 (#250), Qwen3-4B: 29.7 (#240)
| Benchmark | phi-3-medium 14B | Qwen3-4B |
|---|---|---|
| MathArena Final-Answer Competitions | — | 38.5% |
| OTIS Mock AIME 2024-2025 | — | 52.2% |
| MATH Level 5 | 17.6% | — |
Knowledge Qwen3-4B leads
phi-3-medium 14B: 9.1 (#306), Qwen3-4B: 33.0 (#208)
| Benchmark | phi-3-medium 14B | Qwen3-4B |
|---|---|---|
| GPQA Diamond | 27.6% | 52.3% |
| Vectara Hallucination Rate | — | 5.7% |
| ARC (AI2) Challenge | 91.6% | — |
| MMLU | 78% | — |
| OpenBookQA | 87.4% | — |
| TriviaQA | 73.9% | — |
Frequently asked questions
Is phi-3-medium 14B better than Qwen3-4B?
Qwen3-4B is the stronger model overall, scoring 31.9 to 29.7 on the Noometry Index.
How many benchmarks do phi-3-medium 14B and Qwen3-4B share?
1 benchmark has published results for both models. phi-3-medium 14B has 13 scored results on Noometry and Qwen3-4B has 6.