Model comparison
phi-3-medium 14B vs Qwen2.5-Coder (1.5B)
phi-3-medium 14B has enough public results to be ranked (#306); Qwen2.5-Coder (1.5B) does not yet, so treat this comparison as directional.
Last verified . 5 shared benchmarks.
Microsoft
Alibaba (Qwen)Summary
- They share 5 benchmarks with published results for both.
Side by side
| phi-3-medium 14B | Qwen2.5-Coder (1.5B) | |
|---|---|---|
| Provider | Microsoft | Alibaba (Qwen) |
| Noometry Index | 29.1 | — |
| Released | 2024-04-23 | 2024-09-18 |
| 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: 36.3 (#198), Qwen2.5-Coder (1.5B): —
| Benchmark | phi-3-medium 14B | Qwen2.5-Coder (1.5B) |
|---|---|---|
| BigCodeBench Instruct | 37.6% | — |
| BigCodeBench Complete | 48.7% | — |
Reasoning Not comparable
phi-3-medium 14B: —, Qwen2.5-Coder (1.5B): —
| Benchmark | phi-3-medium 14B | Qwen2.5-Coder (1.5B) |
|---|---|---|
| Epoch Capabilities Index | 121.18 | 112.93 |
| HellaSwag | 82.4% | 76.8% |
| WinoGrande | 81.5% | 72.9% |
| Adversarial NLI | 55.8% | — |
| BIG-Bench Hard | 81.4% | — |
Math Not comparable
phi-3-medium 14B: 25.2 (#249), Qwen2.5-Coder (1.5B): —
| Benchmark | phi-3-medium 14B | Qwen2.5-Coder (1.5B) |
|---|---|---|
| MATH Level 5 | 17.6% | — |
| GSM8K | — | 86.7% |
Knowledge Not comparable
phi-3-medium 14B: 9.1 (#301), Qwen2.5-Coder (1.5B): —
| Benchmark | phi-3-medium 14B | Qwen2.5-Coder (1.5B) |
|---|---|---|
| ARC (AI2) Challenge | 91.6% | 60.9% |
| MMLU | 78% | 68% |
| GPQA Diamond | 27.6% | — |
| OpenBookQA | 87.4% | — |
| TriviaQA | 73.9% | — |
Frequently asked questions
Is phi-3-medium 14B better than Qwen2.5-Coder (1.5B)?
phi-3-medium 14B has enough public results to be ranked (#306); Qwen2.5-Coder (1.5B) does not yet, so treat this comparison as directional.
How many benchmarks do phi-3-medium 14B and Qwen2.5-Coder (1.5B) share?
5 benchmarks have published results for both models. phi-3-medium 14B has 13 scored results on Noometry and Qwen2.5-Coder (1.5B) has 6.