Model comparison
phi-3-medium 14B vs Qwen1.5-14B
Qwen1.5-14B is the stronger model overall, scoring 32.1 to 29.1 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 1 category and Qwen1.5-14B in 2 categories; 3 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Qwen1.5-14B leads 29.3 to 9.1.
Side by side
| phi-3-medium 14B | Qwen1.5-14B | |
|---|---|---|
| Provider | Microsoft | Alibaba (Qwen) |
| Noometry Index | 29.1 | 32.1 |
| Released | 2024-04-23 | 2024-02-04 |
| Weights | Open | Open |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 13 | 17 |
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: 36.3 (#198), Qwen1.5-14B: 32.5 (#259)
| Benchmark | phi-3-medium 14B | Qwen1.5-14B |
|---|---|---|
| BigCodeBench Instruct | 37.6% | — |
| LMArena Coding | — | 1138 |
| BigCodeBench Complete | 48.7% | — |
Reasoning Not comparable
phi-3-medium 14B: —, Qwen1.5-14B: 20.5 (#217)
| Benchmark | phi-3-medium 14B | Qwen1.5-14B |
|---|---|---|
| LMArena Hard Prompts | — | 1113 |
| Adversarial NLI | 55.8% | — |
| BIG-Bench Hard | 81.4% | — |
| Epoch Capabilities Index | 121.18 | — |
| HellaSwag | 82.4% | — |
| WinoGrande | 81.5% | — |
Math Qwen1.5-14B leads
phi-3-medium 14B: 25.2 (#249), Qwen1.5-14B: 29.9 (#214)
| Benchmark | phi-3-medium 14B | Qwen1.5-14B |
|---|---|---|
| LMArena Math | — | 1125 |
| MATH Level 5 | 17.6% | — |
Knowledge Qwen1.5-14B leads
phi-3-medium 14B: 9.1 (#301), Qwen1.5-14B: 29.3 (#230)
| Benchmark | phi-3-medium 14B | Qwen1.5-14B |
|---|---|---|
| MMLU | 78% | 68.6% |
| GPQA Diamond | 27.6% | — |
| LMArena Expert | — | 1094 |
| ARC (AI2) Challenge | 91.6% | — |
| OpenBookQA | 87.4% | — |
| TriviaQA | 73.9% | — |
Multilingual Not comparable
phi-3-medium 14B: —, Qwen1.5-14B: 30.8 (#257)
| Benchmark | phi-3-medium 14B | Qwen1.5-14B |
|---|---|---|
| LMArena Non-English | — | 1095 |
| LMArena Chinese | — | 1147 |
| LMArena French | — | 1115 |
| LMArena German | — | 1043 |
| LMArena Japanese | — | 1019 |
| LMArena Russian | — | 1046 |
| LMArena Spanish | — | 1085 |
Instruction Following Not comparable
phi-3-medium 14B: —, Qwen1.5-14B: 57.1 (#266)
| Benchmark | phi-3-medium 14B | Qwen1.5-14B |
|---|---|---|
| LMArena Instruction Following | — | 1102 |
Long Context Not comparable
phi-3-medium 14B: —, Qwen1.5-14B: 33.7 (#252)
| Benchmark | phi-3-medium 14B | Qwen1.5-14B |
|---|---|---|
| LMArena Longer Query | — | 1113 |
Writing & Preference Not comparable
phi-3-medium 14B: —, Qwen1.5-14B: 33.7 (#270)
| Benchmark | phi-3-medium 14B | Qwen1.5-14B |
|---|---|---|
| LMArena Text | — | 1128 |
| LMArena Creative Writing | — | 1091 |
| LMArena Multi-Turn | — | 1110 |
Frequently asked questions
Is phi-3-medium 14B better than Qwen1.5-14B?
Qwen1.5-14B is the stronger model overall, scoring 32.1 to 29.1 on the Noometry Index.
Is phi-3-medium 14B or Qwen1.5-14B better for coding?
phi-3-medium 14B scores higher on coding benchmarks: 36.3 versus 32.5 in the Noometry coding category.
How many benchmarks do phi-3-medium 14B and Qwen1.5-14B share?
1 benchmark has published results for both models. phi-3-medium 14B has 13 scored results on Noometry and Qwen1.5-14B has 17.