Model comparison
Phi 3 Mini 128k Instruct vs Qwen1.5-14B
Qwen1.5-14B is the stronger model overall, scoring 32.1 to 29.1 on the Noometry Index.
Last verified . 16 shared benchmarks.
Microsoft
Alibaba (Qwen)Summary
- They share 16 benchmarks with published results for both. Phi 3 Mini 128k Instruct scores higher in 0 categories and Qwen1.5-14B in 8 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Qwen1.5-14B leads 33.7 to 27.3.
Side by side
| Phi 3 Mini 128k Instruct | 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 | 19 | 17 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Qwen1.5-14B leads
Phi 3 Mini 128k Instruct: 28.3 (#307), Qwen1.5-14B: 32.5 (#259)
| Benchmark | Phi 3 Mini 128k Instruct | Qwen1.5-14B |
|---|---|---|
| LMArena Coding | 1040 | 1138 |
| BigCodeBench Instruct | 29.6% | — |
| BigCodeBench Complete | 40.6% | — |
Reasoning Qwen1.5-14B leads
Phi 3 Mini 128k Instruct: 18.7 (#254), Qwen1.5-14B: 20.5 (#217)
| Benchmark | Phi 3 Mini 128k Instruct | Qwen1.5-14B |
|---|---|---|
| LMArena Hard Prompts | 1028 | 1113 |
Math Too close to call
Phi 3 Mini 128k Instruct: 29.2 (#220), Qwen1.5-14B: 29.9 (#214)
| Benchmark | Phi 3 Mini 128k Instruct | Qwen1.5-14B |
|---|---|---|
| LMArena Math | 1089 | 1125 |
Knowledge Qwen1.5-14B leads
Phi 3 Mini 128k Instruct: 26.3 (#251), Qwen1.5-14B: 29.3 (#230)
| Benchmark | Phi 3 Mini 128k Instruct | Qwen1.5-14B |
|---|---|---|
| LMArena Expert | 984 | 1094 |
| MMLU | — | 68.6% |
Multilingual Qwen1.5-14B leads
Phi 3 Mini 128k Instruct: 25.4 (#280), Qwen1.5-14B: 30.8 (#257)
| Benchmark | Phi 3 Mini 128k Instruct | Qwen1.5-14B |
|---|---|---|
| LMArena Non-English | 1000 | 1095 |
| LMArena Chinese | 1016 | 1147 |
| LMArena French | 1038 | 1115 |
| LMArena German | 1006 | 1043 |
| LMArena Japanese | 899 | 1019 |
| LMArena Russian | 1004 | 1046 |
| LMArena Spanish | 1058 | 1085 |
| LMArena Korean | 856 | — |
Instruction Following Qwen1.5-14B leads
Phi 3 Mini 128k Instruct: 52.1 (#289), Qwen1.5-14B: 57.1 (#266)
| Benchmark | Phi 3 Mini 128k Instruct | Qwen1.5-14B |
|---|---|---|
| LMArena Instruction Following | 1023 | 1102 |
Long Context Qwen1.5-14B leads
Phi 3 Mini 128k Instruct: 30.3 (#284), Qwen1.5-14B: 33.7 (#252)
| Benchmark | Phi 3 Mini 128k Instruct | Qwen1.5-14B |
|---|---|---|
| LMArena Longer Query | 996 | 1113 |
Writing & Preference Qwen1.5-14B leads
Phi 3 Mini 128k Instruct: 27.3 (#296), Qwen1.5-14B: 33.7 (#270)
| Benchmark | Phi 3 Mini 128k Instruct | Qwen1.5-14B |
|---|---|---|
| LMArena Text | 1050 | 1128 |
| LMArena Creative Writing | 1024 | 1091 |
| LMArena Multi-Turn | 989 | 1110 |
Frequently asked questions
Is Phi 3 Mini 128k Instruct 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 Mini 128k Instruct or Qwen1.5-14B better for coding?
Qwen1.5-14B scores higher on coding benchmarks: 32.5 versus 28.3 in the Noometry coding category.
How many benchmarks do Phi 3 Mini 128k Instruct and Qwen1.5-14B share?
16 benchmarks have published results for both models. Phi 3 Mini 128k Instruct has 19 scored results on Noometry and Qwen1.5-14B has 17.