Model comparison
Phi-2 vs Qwen2.5-Coder (1.5B)
Neither Phi-2 nor Qwen2.5-Coder (1.5B) has enough public benchmark results to be ranked yet; the rows below show what has been published.
Last verified . 5 shared benchmarks.
Microsoft
Alibaba (Qwen)Summary
- They share 5 benchmarks with published results for both.
Side by side
| Phi-2 | Qwen2.5-Coder (1.5B) | |
|---|---|---|
| Provider | Microsoft | Alibaba (Qwen) |
| Noometry Index | — | — |
| Released | 2023-12-12 | 2024-09-18 |
| Weights | Open | Open |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 11 | 6 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Not comparable
Phi-2: —, Qwen2.5-Coder (1.5B): —
| Benchmark | Phi-2 | Qwen2.5-Coder (1.5B) |
|---|---|---|
| HumanEval+ | 45.1% | — |
| MBPP+ | 54.2% | — |
Reasoning Not comparable
Phi-2: —, Qwen2.5-Coder (1.5B): —
| Benchmark | Phi-2 | Qwen2.5-Coder (1.5B) |
|---|---|---|
| Epoch Capabilities Index | 107.94 | 113.14 |
| HellaSwag | 53.6% | 76.8% |
| WinoGrande | 54.7% | 72.9% |
| Adversarial NLI | 42.5% | — |
| BIG-Bench Hard | 59.4% | — |
Math Not comparable
Phi-2: —, Qwen2.5-Coder (1.5B): —
| Benchmark | Phi-2 | Qwen2.5-Coder (1.5B) |
|---|---|---|
| GSM8K | — | 86.7% |
Knowledge Not comparable
Phi-2: —, Qwen2.5-Coder (1.5B): —
| Benchmark | Phi-2 | Qwen2.5-Coder (1.5B) |
|---|---|---|
| ARC (AI2) Challenge | 75.9% | 60.9% |
| MMLU | 58.4% | 68% |
| OpenBookQA | 73.6% | — |
| TriviaQA | 45.2% | — |
Frequently asked questions
Is Phi-2 better than Qwen2.5-Coder (1.5B)?
Neither Phi-2 nor Qwen2.5-Coder (1.5B) has enough public benchmark results to be ranked yet; the rows below show what has been published.
How many benchmarks do Phi-2 and Qwen2.5-Coder (1.5B) share?
5 benchmarks have published results for both models. Phi-2 has 11 scored results on Noometry and Qwen2.5-Coder (1.5B) has 6.