Model comparison
Phi-3.5-mini vs Qwen-14B
Qwen-14B has enough public results to be ranked (#275); Phi-3.5-mini does not yet, so treat this comparison as directional.
Last verified . 3 shared benchmarks.
Microsoft
Alibaba (Qwen)Summary
- They share 3 benchmarks with published results for both. Phi-3.5-mini scores higher in 1 category and Qwen-14B in 0 categories; one gap is clear of the uncertainty.
- The widest gap is in coding, where Phi-3.5-mini leads 34.6 to 31.2.
Side by side
| Phi-3.5-mini | Qwen-14B | |
|---|---|---|
| Provider | Microsoft | Alibaba (Qwen) |
| Noometry Index | 36.9 | 31.4 |
| Released | 2024-08-16 | 2023-09-24 |
| Weights | Open | Open |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 5 | 18 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Phi-3.5-mini leads
Phi-3.5-mini: 34.6 (#232), Qwen-14B: 31.2 (#288)
| Benchmark | Phi-3.5-mini | Qwen-14B |
|---|---|---|
| BigCodeBench Instruct | 32.8% | — |
| LMArena Coding | — | 1071 |
| BigCodeBench Complete | 38.5% | — |
Reasoning Not comparable
Phi-3.5-mini: —, Qwen-14B: 19.6 (#257)
| Benchmark | Phi-3.5-mini | Qwen-14B |
|---|---|---|
| PIQA | 81% | 79.9% |
| LMArena Hard Prompts | — | 1027 |
| BIG-Bench Hard | — | 55% |
| Epoch Capabilities Index | — | 113.03 |
| LAMBADA | — | 71.1% |
Math Not comparable
Phi-3.5-mini: —, Qwen-14B: 31.2 (#227)
| Benchmark | Phi-3.5-mini | Qwen-14B |
|---|---|---|
| GSM8K | 86.2% | 61.3% |
| LMArena Math | — | 1068 |
Knowledge Not comparable
Phi-3.5-mini: —, Qwen-14B: —
| Benchmark | Phi-3.5-mini | Qwen-14B |
|---|---|---|
| BoolQ | 78% | 86.2% |
| ARC (AI2) Challenge | — | 84.4% |
| MMLU | — | 66.3% |
Multilingual Not comparable
Phi-3.5-mini: —, Qwen-14B: 27.5 (#275)
| Benchmark | Phi-3.5-mini | Qwen-14B |
|---|---|---|
| LMArena Non-English | — | 1041 |
| LMArena Chinese | — | 1077 |
Instruction Following Not comparable
Phi-3.5-mini: —, Qwen-14B: 52.4 (#289)
| Benchmark | Phi-3.5-mini | Qwen-14B |
|---|---|---|
| LMArena Instruction Following | — | 1031 |
Long Context Not comparable
Phi-3.5-mini: —, Qwen-14B: 31.3 (#280)
| Benchmark | Phi-3.5-mini | Qwen-14B |
|---|---|---|
| LMArena Longer Query | — | 1028 |
Writing & Preference Not comparable
Phi-3.5-mini: —, Qwen-14B: 27.6 (#299)
| Benchmark | Phi-3.5-mini | Qwen-14B |
|---|---|---|
| LMArena Text | — | 1051 |
| LMArena Creative Writing | — | 1028 |
| LMArena Multi-Turn | — | 1022 |
Frequently asked questions
Is Phi-3.5-mini better than Qwen-14B?
Qwen-14B has enough public results to be ranked (#275); Phi-3.5-mini does not yet, so treat this comparison as directional.
Is Phi-3.5-mini or Qwen-14B better for coding?
Phi-3.5-mini scores higher on coding benchmarks: 34.6 versus 31.2 in the Noometry coding category.
How many benchmarks do Phi-3.5-mini and Qwen-14B share?
3 benchmarks have published results for both models. Phi-3.5-mini has 5 scored results on Noometry and Qwen-14B has 18.