Model comparison
Phi 3 Mini 4k Instruct vs Qwen1.5-32B
Qwen1.5-32B is the stronger model overall, scoring 30.0 to 27.4 on the Noometry Index.
Last verified . 18 shared benchmarks.
Microsoft
Alibaba (Qwen)Summary
- They share 18 benchmarks with published results for both. Phi 3 Mini 4k Instruct scores higher in 1 category and Qwen1.5-32B in 7 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Phi 3 Mini 4k Instruct leads 27.9 to 13.5.
Side by side
| Phi 3 Mini 4k Instruct | Qwen1.5-32B | |
|---|---|---|
| Provider | Microsoft | Alibaba (Qwen) |
| Noometry Index | 27.4 | 30.0 |
| Released | 2024-04-23 | 2024-02-04 |
| Weights | Open | Open |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 35 | 21 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Qwen1.5-32B leads
Phi 3 Mini 4k Instruct: 26.1 (#319), Qwen1.5-32B: 31.1 (#278)
| Benchmark | Phi 3 Mini 4k Instruct | Qwen1.5-32B |
|---|---|---|
| LMArena Coding | 1093 | 1155 |
| BigCodeBench Instruct | — | 32.3% |
| LiveBench Coding | 15.5% | — |
| BigCodeBench Complete | — | 42% |
| HumanEval+ | 59.1% | — |
| MBPP+ | 54.2% | — |
Reasoning Qwen1.5-32B leads
Phi 3 Mini 4k Instruct: 13.6 (#326), Qwen1.5-32B: 20.9 (#210)
| Benchmark | Phi 3 Mini 4k Instruct | Qwen1.5-32B |
|---|---|---|
| LMArena Hard Prompts | 1072 | 1131 |
| Chess Puzzles | 0% | — |
| LiveBench Reasoning | 26.8% | — |
| LiveBench Data Analysis | 34.7% | — |
| Adversarial NLI | 52.8% | — |
| BIG-Bench Hard | 71.7% | — |
| HellaSwag | 76.7% | — |
| LiveBench | 22.4% | — |
| WinoGrande | 70.8% | — |
Math Qwen1.5-32B leads
Phi 3 Mini 4k Instruct: 24.5 (#258), Qwen1.5-32B: 30.5 (#207)
| Benchmark | Phi 3 Mini 4k Instruct | Qwen1.5-32B |
|---|---|---|
| LMArena Math | 1111 | 1155 |
| LiveBench Math | 15.7% | — |
Knowledge Phi 3 Mini 4k Instruct leads
Phi 3 Mini 4k Instruct: 27.9 (#241), Qwen1.5-32B: 13.5 (#291)
| Benchmark | Phi 3 Mini 4k Instruct | Qwen1.5-32B |
|---|---|---|
| LMArena Expert | 1045 | 1126 |
| MMLU | 68.8% | 74.4% |
| GPQA Diamond | — | 30.7% |
| ARC (AI2) Challenge | 84.9% | — |
| OpenBookQA | 88% | — |
| TriviaQA | 64% | — |
Multilingual Qwen1.5-32B leads
Phi 3 Mini 4k Instruct: 26.5 (#275), Qwen1.5-32B: 31.6 (#254)
| Benchmark | Phi 3 Mini 4k Instruct | Qwen1.5-32B |
|---|---|---|
| LMArena Non-English | 1021 | 1106 |
| LMArena Chinese | 1021 | 1176 |
| LMArena French | 1075 | 1100 |
| LMArena German | 1044 | 1058 |
| LMArena Japanese | 935 | 1027 |
| LMArena Korean | 905 | 1007 |
| LMArena Russian | 1022 | 1073 |
| LMArena Spanish | 1084 | 1089 |
Instruction Following Qwen1.5-32B leads
Phi 3 Mini 4k Instruct: 48.0 (#298), Qwen1.5-32B: 58.0 (#260)
| Benchmark | Phi 3 Mini 4k Instruct | Qwen1.5-32B |
|---|---|---|
| LMArena Instruction Following | 1053 | 1116 |
| LiveBench Instruction Following | 39.1% | — |
Long Context Qwen1.5-32B leads
Phi 3 Mini 4k Instruct: 31.7 (#271), Qwen1.5-32B: 34.7 (#241)
| Benchmark | Phi 3 Mini 4k Instruct | Qwen1.5-32B |
|---|---|---|
| LMArena Longer Query | 1044 | 1146 |
Writing & Preference Qwen1.5-32B leads
Phi 3 Mini 4k Instruct: 27.7 (#295), Qwen1.5-32B: 34.4 (#266)
| Benchmark | Phi 3 Mini 4k Instruct | Qwen1.5-32B |
|---|---|---|
| LMArena Text | 1073 | 1137 |
| LMArena Creative Writing | 1037 | 1083 |
| LMArena Multi-Turn | 1018 | 1140 |
| LiveBench Language | 9.2% | — |
Frequently asked questions
Is Phi 3 Mini 4k Instruct better than Qwen1.5-32B?
Qwen1.5-32B is the stronger model overall, scoring 30.0 to 27.4 on the Noometry Index.
Is Phi 3 Mini 4k Instruct or Qwen1.5-32B better for coding?
Qwen1.5-32B scores higher on coding benchmarks: 31.1 versus 26.1 in the Noometry coding category.
How many benchmarks do Phi 3 Mini 4k Instruct and Qwen1.5-32B share?
18 benchmarks have published results for both models. Phi 3 Mini 4k Instruct has 35 scored results on Noometry and Qwen1.5-32B has 21.