Model comparison
phi-3-medium 14B vs Qwen1.5-110B
Qwen1.5-110B is the stronger model overall, scoring 34.2 to 29.7 on the Noometry Index.
Last verified . 2 shared benchmarks.
Microsoft
Alibaba (Qwen)Summary
- They share 2 benchmarks with published results for both. phi-3-medium 14B scores higher in 1 category and Qwen1.5-110B in 2 categories; 3 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Qwen1.5-110B leads 31.2 to 9.1.
Side by side
| phi-3-medium 14B | Qwen1.5-110B | |
|---|---|---|
| Provider | Microsoft | Alibaba (Qwen) |
| Noometry Index | 29.7 | 34.2 |
| Released | 2024-04-23 | 2024-04-25 |
| Weights | Open | Open |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 13 | 20 |
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), Qwen1.5-110B: 33.0 (#264)
| Benchmark | phi-3-medium 14B | Qwen1.5-110B |
|---|---|---|
| BigCodeBench Instruct | 37.6% | 35% |
| BigCodeBench Complete | 48.7% | 44.4% |
| LMArena Coding | — | 1184 |
Reasoning Not comparable
phi-3-medium 14B: —, Qwen1.5-110B: 22.7 (#189)
| Benchmark | phi-3-medium 14B | Qwen1.5-110B |
|---|---|---|
| LMArena Hard Prompts | — | 1168 |
| Adversarial NLI | 55.8% | — |
| BIG-Bench Hard | 81.4% | — |
| Epoch Capabilities Index | 121.23 | — |
| ForecastBench | — | 57.7 |
| HellaSwag | 82.4% | — |
| WinoGrande | 81.5% | — |
Math Qwen1.5-110B leads
phi-3-medium 14B: 27.3 (#250), Qwen1.5-110B: 33.7 (#201)
| Benchmark | phi-3-medium 14B | Qwen1.5-110B |
|---|---|---|
| LMArena Math | — | 1185 |
| MATH Level 5 | 17.6% | — |
Knowledge Qwen1.5-110B leads
phi-3-medium 14B: 9.1 (#306), Qwen1.5-110B: 31.2 (#219)
| Benchmark | phi-3-medium 14B | Qwen1.5-110B |
|---|---|---|
| GPQA Diamond | 27.6% | — |
| LMArena Expert | — | 1144 |
| ARC (AI2) Challenge | 91.6% | — |
| MMLU | 78% | — |
| OpenBookQA | 87.4% | — |
| TriviaQA | 73.9% | — |
Multilingual Not comparable
phi-3-medium 14B: —, Qwen1.5-110B: 33.6 (#250)
| Benchmark | phi-3-medium 14B | Qwen1.5-110B |
|---|---|---|
| LMArena Non-English | — | 1142 |
| LMArena Chinese | — | 1206 |
| LMArena French | — | 1151 |
| LMArena German | — | 1123 |
| LMArena Japanese | — | 1074 |
| LMArena Korean | — | 1044 |
| LMArena Russian | — | 1118 |
| LMArena Spanish | — | 1142 |
Instruction Following Not comparable
phi-3-medium 14B: —, Qwen1.5-110B: 60.3 (#252)
| Benchmark | phi-3-medium 14B | Qwen1.5-110B |
|---|---|---|
| LMArena Instruction Following | — | 1158 |
Long Context Not comparable
phi-3-medium 14B: —, Qwen1.5-110B: 35.1 (#242)
| Benchmark | phi-3-medium 14B | Qwen1.5-110B |
|---|---|---|
| LMArena Longer Query | — | 1157 |
Writing & Preference Not comparable
phi-3-medium 14B: —, Qwen1.5-110B: 38.0 (#255)
| Benchmark | phi-3-medium 14B | Qwen1.5-110B |
|---|---|---|
| LMArena Text | — | 1175 |
| LMArena Creative Writing | — | 1148 |
| LMArena Multi-Turn | — | 1160 |
Frequently asked questions
Is phi-3-medium 14B better than Qwen1.5-110B?
Qwen1.5-110B is the stronger model overall, scoring 34.2 to 29.7 on the Noometry Index.
Is phi-3-medium 14B or Qwen1.5-110B better for coding?
phi-3-medium 14B scores higher on coding benchmarks: 36.8 versus 33.0 in the Noometry coding category.
How many benchmarks do phi-3-medium 14B and Qwen1.5-110B share?
2 benchmarks have published results for both models. phi-3-medium 14B has 13 scored results on Noometry and Qwen1.5-110B has 20.