Model comparison
Phi 3 Mini 128k Instruct vs Qwen1.5-7B
Qwen1.5-7B is the stronger model overall, scoring 31.4 to 29.7 on the Noometry Index.
Last verified . 12 shared benchmarks.
Microsoft
Alibaba (Qwen)Summary
- They share 12 benchmarks with published results for both. Phi 3 Mini 128k Instruct scores higher in 1 category and Qwen1.5-7B in 7 categories; 6 gaps are clear of the uncertainty.
- The widest gap is in coding, where Qwen1.5-7B leads 32.2 to 28.8.
Side by side
| Phi 3 Mini 128k Instruct | Qwen1.5-7B | |
|---|---|---|
| Provider | Microsoft | Alibaba (Qwen) |
| Noometry Index | 29.7 | 31.4 |
| Released | 2024-04-23 | 2024-02-04 |
| Weights | Open | Open |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 19 | 13 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Qwen1.5-7B leads
Phi 3 Mini 128k Instruct: 28.8 (#312), Qwen1.5-7B: 32.2 (#276)
| Benchmark | Phi 3 Mini 128k Instruct | Qwen1.5-7B |
|---|---|---|
| LMArena Coding | 1039 | 1107 |
| BigCodeBench Instruct | 29.6% | — |
| BigCodeBench Complete | 40.6% | — |
Reasoning Too close to call
Phi 3 Mini 128k Instruct: 19.6 (#256), Qwen1.5-7B: 20.4 (#240)
| Benchmark | Phi 3 Mini 128k Instruct | Qwen1.5-7B |
|---|---|---|
| LMArena Hard Prompts | 1028 | 1065 |
Math Too close to call
Phi 3 Mini 128k Instruct: 31.6 (#222), Qwen1.5-7B: 31.4 (#224)
| Benchmark | Phi 3 Mini 128k Instruct | Qwen1.5-7B |
|---|---|---|
| LMArena Math | 1089 | 1080 |
Knowledge Qwen1.5-7B leads
Phi 3 Mini 128k Instruct: 26.8 (#254), Qwen1.5-7B: 28.7 (#243)
| Benchmark | Phi 3 Mini 128k Instruct | Qwen1.5-7B |
|---|---|---|
| LMArena Expert | 984 | 1055 |
| MMLU | — | 62.6% |
Multilingual Qwen1.5-7B leads
Phi 3 Mini 128k Instruct: 25.2 (#285), Qwen1.5-7B: 28.5 (#271)
| Benchmark | Phi 3 Mini 128k Instruct | Qwen1.5-7B |
|---|---|---|
| LMArena Non-English | 1000 | 1058 |
| LMArena Chinese | 1016 | 1141 |
| LMArena Russian | 1004 | 1006 |
| LMArena French | 1039 | — |
| LMArena German | 1006 | — |
| LMArena Japanese | 899 | — |
| LMArena Korean | 856 | — |
| LMArena Spanish | 1059 | — |
Instruction Following Qwen1.5-7B leads
Phi 3 Mini 128k Instruct: 51.8 (#294), Qwen1.5-7B: 54.1 (#281)
| Benchmark | Phi 3 Mini 128k Instruct | Qwen1.5-7B |
|---|---|---|
| LMArena Instruction Following | 1023 | 1058 |
Long Context Qwen1.5-7B leads
Phi 3 Mini 128k Instruct: 30.4 (#289), Qwen1.5-7B: 33.1 (#266)
| Benchmark | Phi 3 Mini 128k Instruct | Qwen1.5-7B |
|---|---|---|
| LMArena Longer Query | 996 | 1090 |
Writing & Preference Qwen1.5-7B leads
Phi 3 Mini 128k Instruct: 27.1 (#301), Qwen1.5-7B: 29.6 (#293)
| Benchmark | Phi 3 Mini 128k Instruct | Qwen1.5-7B |
|---|---|---|
| LMArena Text | 1050 | 1083 |
| LMArena Creative Writing | 1024 | 1035 |
| LMArena Multi-Turn | 989 | 1062 |
Frequently asked questions
Is Phi 3 Mini 128k Instruct better than Qwen1.5-7B?
Qwen1.5-7B is the stronger model overall, scoring 31.4 to 29.7 on the Noometry Index.
Is Phi 3 Mini 128k Instruct or Qwen1.5-7B better for coding?
Qwen1.5-7B scores higher on coding benchmarks: 32.2 versus 28.8 in the Noometry coding category.
How many benchmarks do Phi 3 Mini 128k Instruct and Qwen1.5-7B share?
12 benchmarks have published results for both models. Phi 3 Mini 128k Instruct has 19 scored results on Noometry and Qwen1.5-7B has 13.