Model comparison
phi-3-medium 14B vs Qwen1.5-32B
phi-3-medium 14B and Qwen1.5-32B score almost the same on the Noometry Index (29.7 vs 30.5), so choose on price, context window or the category you care about most.
Last verified . 4 shared benchmarks.
Microsoft
Alibaba (Qwen)Summary
- They share 4 benchmarks with published results for both. phi-3-medium 14B scores higher in 1 category and Qwen1.5-32B in 2 categories; 3 gaps are clear of the uncertainty.
- The widest gap is in math, where Qwen1.5-32B leads 33.0 to 27.3.
- The biggest single-benchmark swing is BigCodeBench Complete: 48.7% for phi-3-medium 14B and 42% for Qwen1.5-32B.
Side by side
| phi-3-medium 14B | Qwen1.5-32B | |
|---|---|---|
| Provider | Microsoft | Alibaba (Qwen) |
| Noometry Index | 29.7 | 30.5 |
| Released | 2024-04-23 | 2024-02-04 |
| Weights | Open | Open |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 13 | 21 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding phi-3-medium 14B leads
phi-3-medium 14B: 36.8 (#201), Qwen1.5-32B: 31.7 (#282)
| Benchmark | phi-3-medium 14B | Qwen1.5-32B |
|---|---|---|
| BigCodeBench Instruct | 37.6% | 32.3% |
| BigCodeBench Complete | 48.7% | 42% |
| LMArena Coding | — | 1155 |
Reasoning Not comparable
phi-3-medium 14B: —, Qwen1.5-32B: 21.8 (#212)
| Benchmark | phi-3-medium 14B | Qwen1.5-32B |
|---|---|---|
| LMArena Hard Prompts | — | 1130 |
| Adversarial NLI | 55.8% | — |
| BIG-Bench Hard | 81.4% | — |
| Epoch Capabilities Index | 121.23 | — |
| HellaSwag | 82.4% | — |
| WinoGrande | 81.5% | — |
Math Qwen1.5-32B leads
phi-3-medium 14B: 27.3 (#250), Qwen1.5-32B: 33.0 (#207)
| Benchmark | phi-3-medium 14B | Qwen1.5-32B |
|---|---|---|
| LMArena Math | — | 1155 |
| MATH Level 5 | 17.6% | — |
Knowledge Qwen1.5-32B leads
phi-3-medium 14B: 9.1 (#306), Qwen1.5-32B: 13.5 (#296)
| Benchmark | phi-3-medium 14B | Qwen1.5-32B |
|---|---|---|
| GPQA Diamond | 27.6% | 30.7% |
| MMLU | 78% | 74.4% |
| LMArena Expert | — | 1126 |
| ARC (AI2) Challenge | 91.6% | — |
| OpenBookQA | 87.4% | — |
| TriviaQA | 73.9% | — |
Multilingual Not comparable
phi-3-medium 14B: —, Qwen1.5-32B: 31.4 (#259)
| Benchmark | phi-3-medium 14B | Qwen1.5-32B |
|---|---|---|
| LMArena Non-English | — | 1106 |
| LMArena Chinese | — | 1177 |
| LMArena French | — | 1101 |
| LMArena German | — | 1058 |
| LMArena Japanese | — | 1027 |
| LMArena Korean | — | 1008 |
| LMArena Russian | — | 1073 |
| LMArena Spanish | — | 1089 |
Instruction Following Not comparable
phi-3-medium 14B: —, Qwen1.5-32B: 57.7 (#265)
| Benchmark | phi-3-medium 14B | Qwen1.5-32B |
|---|---|---|
| LMArena Instruction Following | — | 1116 |
Long Context Not comparable
phi-3-medium 14B: —, Qwen1.5-32B: 34.7 (#246)
| Benchmark | phi-3-medium 14B | Qwen1.5-32B |
|---|---|---|
| LMArena Longer Query | — | 1146 |
Writing & Preference Not comparable
phi-3-medium 14B: —, Qwen1.5-32B: 34.2 (#271)
| Benchmark | phi-3-medium 14B | Qwen1.5-32B |
|---|---|---|
| LMArena Text | — | 1137 |
| LMArena Creative Writing | — | 1083 |
| LMArena Multi-Turn | — | 1140 |
Frequently asked questions
Is phi-3-medium 14B better than Qwen1.5-32B?
phi-3-medium 14B and Qwen1.5-32B score almost the same on the Noometry Index (29.7 vs 30.5), so choose on price, context window or the category you care about most.
Is phi-3-medium 14B or Qwen1.5-32B better for coding?
phi-3-medium 14B scores higher on coding benchmarks: 36.8 versus 31.7 in the Noometry coding category.
How many benchmarks do phi-3-medium 14B and Qwen1.5-32B share?
4 benchmarks have published results for both models. phi-3-medium 14B has 13 scored results on Noometry and Qwen1.5-32B has 21.