Model comparison
phi-3-medium 14B vs Qwen2-72B
phi-3-medium 14B and Qwen2-72B score almost the same on the Noometry Index (29.7 vs 30.0), so choose on price, context window or the category you care about most.
Last verified . 6 shared benchmarks.
Microsoft
Alibaba (Qwen)Summary
- They share 6 benchmarks with published results for both. phi-3-medium 14B scores higher in 1 category and Qwen2-72B in 2 categories; 3 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Qwen2-72B leads 21.2 to 9.1.
- The biggest single-benchmark swing is MATH Level 5: 17.6% for phi-3-medium 14B and 39.1% for Qwen2-72B.
Side by side
| phi-3-medium 14B | Qwen2-72B | |
|---|---|---|
| Provider | Microsoft | Alibaba (Qwen) |
| Noometry Index | 29.7 | 30.0 |
| Released | 2024-04-23 | 2024-06-07 |
| Weights | Open | Open |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 13 | 26 |
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), Qwen2-72B: 29.1 (#310)
| Benchmark | phi-3-medium 14B | Qwen2-72B |
|---|---|---|
| BigCodeBench Instruct | 37.6% | 38.5% |
| BigCodeBench Complete | 48.7% | 54% |
| WeirdML | — | 11.3% |
| LMArena Coding | — | 1196 |
Agentic & Tool Use Not comparable
phi-3-medium 14B: —, Qwen2-72B: 17.0 (#146)
| Benchmark | phi-3-medium 14B | Qwen2-72B |
|---|---|---|
| TheAgentCompany | — | 1.1% |
| METR Time Horizons | — | 29.9% |
Reasoning Not comparable
phi-3-medium 14B: —, Qwen2-72B: 23.2 (#181)
| Benchmark | phi-3-medium 14B | Qwen2-72B |
|---|---|---|
| Epoch Capabilities Index | 121.23 | 125.28 |
| LMArena Hard Prompts | — | 1191 |
| Adversarial NLI | 55.8% | — |
| BIG-Bench Hard | 81.4% | — |
| HellaSwag | 82.4% | — |
| WinoGrande | 81.5% | — |
Math Qwen2-72B leads
phi-3-medium 14B: 27.3 (#250), Qwen2-72B: 30.2 (#236)
| Benchmark | phi-3-medium 14B | Qwen2-72B |
|---|---|---|
| MATH Level 5 | 17.6% | 39.1% |
| LMArena Math | — | 1235 |
Knowledge Qwen2-72B leads
phi-3-medium 14B: 9.1 (#306), Qwen2-72B: 21.2 (#275)
| Benchmark | phi-3-medium 14B | Qwen2-72B |
|---|---|---|
| GPQA Diamond | 27.6% | 40.8% |
| MMLU | 78% | 82.4% |
| LMArena Expert | — | 1171 |
| ARC (AI2) Challenge | 91.6% | — |
| OpenBookQA | 87.4% | — |
| TriviaQA | 73.9% | — |
Multilingual Not comparable
phi-3-medium 14B: —, Qwen2-72B: 35.9 (#244)
| Benchmark | phi-3-medium 14B | Qwen2-72B |
|---|---|---|
| LMArena Non-English | — | 1176 |
| LMArena Chinese | — | 1240 |
| LMArena French | — | 1170 |
| LMArena German | — | 1151 |
| LMArena Japanese | — | 1111 |
| LMArena Korean | — | 1083 |
| LMArena Russian | — | 1169 |
| LMArena Spanish | — | 1169 |
Instruction Following Not comparable
phi-3-medium 14B: —, Qwen2-72B: 61.7 (#241)
| Benchmark | phi-3-medium 14B | Qwen2-72B |
|---|---|---|
| LMArena Instruction Following | — | 1181 |
Long Context Not comparable
phi-3-medium 14B: —, Qwen2-72B: 36.1 (#235)
| Benchmark | phi-3-medium 14B | Qwen2-72B |
|---|---|---|
| LMArena Longer Query | — | 1192 |
Writing & Preference Not comparable
phi-3-medium 14B: —, Qwen2-72B: 40.8 (#241)
| Benchmark | phi-3-medium 14B | Qwen2-72B |
|---|---|---|
| LMArena Text | — | 1203 |
| LMArena Creative Writing | — | 1181 |
| LMArena Multi-Turn | — | 1196 |
Frequently asked questions
Is phi-3-medium 14B better than Qwen2-72B?
phi-3-medium 14B and Qwen2-72B score almost the same on the Noometry Index (29.7 vs 30.0), so choose on price, context window or the category you care about most.
Is phi-3-medium 14B or Qwen2-72B better for coding?
phi-3-medium 14B scores higher on coding benchmarks: 36.8 versus 29.1 in the Noometry coding category.
How many benchmarks do phi-3-medium 14B and Qwen2-72B share?
6 benchmarks have published results for both models. phi-3-medium 14B has 13 scored results on Noometry and Qwen2-72B has 26.