Model comparison
Phi 3 Medium 4k Instruct vs Qwen1.5-14B
Phi 3 Medium 4k Instruct and Qwen1.5-14B score almost the same on the Noometry Index (32.4 vs 32.1), so choose on price, context window or the category you care about most.
Last verified . 16 shared benchmarks.
Microsoft
Alibaba (Qwen)Summary
- They share 16 benchmarks with published results for both. Phi 3 Medium 4k Instruct scores higher in 6 categories and Qwen1.5-14B in 2 categories, but none of those gaps is larger than the uncertainty.
Side by side
| Phi 3 Medium 4k Instruct | Qwen1.5-14B | |
|---|---|---|
| Provider | Microsoft | Alibaba (Qwen) |
| Noometry Index | 32.4 | 32.1 |
| Released | — | 2024-02-04 |
| Weights | Open | Open |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 17 | 17 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Too close to call
Phi 3 Medium 4k Instruct: 32.3 (#263), Qwen1.5-14B: 32.5 (#259)
| Benchmark | Phi 3 Medium 4k Instruct | Qwen1.5-14B |
|---|---|---|
| LMArena Coding | 1130 | 1138 |
Reasoning Too close to call
Phi 3 Medium 4k Instruct: 20.8 (#214), Qwen1.5-14B: 20.5 (#217)
| Benchmark | Phi 3 Medium 4k Instruct | Qwen1.5-14B |
|---|---|---|
| LMArena Hard Prompts | 1127 | 1113 |
Math Too close to call
Phi 3 Medium 4k Instruct: 30.9 (#202), Qwen1.5-14B: 29.9 (#214)
| Benchmark | Phi 3 Medium 4k Instruct | Qwen1.5-14B |
|---|---|---|
| LMArena Math | 1173 | 1125 |
Knowledge Too close to call
Phi 3 Medium 4k Instruct: 29.6 (#226), Qwen1.5-14B: 29.3 (#230)
| Benchmark | Phi 3 Medium 4k Instruct | Qwen1.5-14B |
|---|---|---|
| LMArena Expert | 1108 | 1094 |
| MMLU | — | 68.6% |
Multilingual Too close to call
Phi 3 Medium 4k Instruct: 30.8 (#258), Qwen1.5-14B: 30.8 (#257)
| Benchmark | Phi 3 Medium 4k Instruct | Qwen1.5-14B |
|---|---|---|
| LMArena Non-English | 1094 | 1095 |
| LMArena Chinese | 1108 | 1147 |
| LMArena French | 1109 | 1115 |
| LMArena German | 1101 | 1043 |
| LMArena Japanese | 1042 | 1019 |
| LMArena Russian | 1145 | 1046 |
| LMArena Spanish | 1095 | 1085 |
| LMArena Korean | 954 | — |
Instruction Following Too close to call
Phi 3 Medium 4k Instruct: 57.8 (#263), Qwen1.5-14B: 57.1 (#266)
| Benchmark | Phi 3 Medium 4k Instruct | Qwen1.5-14B |
|---|---|---|
| LMArena Instruction Following | 1114 | 1102 |
Long Context Too close to call
Phi 3 Medium 4k Instruct: 33.9 (#250), Qwen1.5-14B: 33.7 (#252)
| Benchmark | Phi 3 Medium 4k Instruct | Qwen1.5-14B |
|---|---|---|
| LMArena Longer Query | 1120 | 1113 |
Writing & Preference Too close to call
Phi 3 Medium 4k Instruct: 34.3 (#267), Qwen1.5-14B: 33.7 (#270)
| Benchmark | Phi 3 Medium 4k Instruct | Qwen1.5-14B |
|---|---|---|
| LMArena Text | 1138 | 1128 |
| LMArena Creative Writing | 1106 | 1091 |
| LMArena Multi-Turn | 1088 | 1110 |
Frequently asked questions
Is Phi 3 Medium 4k Instruct better than Qwen1.5-14B?
Phi 3 Medium 4k Instruct and Qwen1.5-14B score almost the same on the Noometry Index (32.4 vs 32.1), so choose on price, context window or the category you care about most.
Is Phi 3 Medium 4k Instruct or Qwen1.5-14B better for coding?
They score almost the same on coding (32.3 vs 32.5); test both on your own repository before choosing.
How many benchmarks do Phi 3 Medium 4k Instruct and Qwen1.5-14B share?
16 benchmarks have published results for both models. Phi 3 Medium 4k Instruct has 17 scored results on Noometry and Qwen1.5-14B has 17.