Model comparison
Phi 3 Mini 4k Instruct vs Qwen1.5-110B
Qwen1.5-110B is the stronger model overall, scoring 34.2 to 27.9 on the Noometry Index.
Last verified . 17 shared benchmarks.
Microsoft
Alibaba (Qwen)Summary
- They share 17 benchmarks with published results for both. Phi 3 Mini 4k Instruct scores higher in 0 categories and Qwen1.5-110B in 8 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in instruction following, where Qwen1.5-110B leads 60.3 to 47.7.
Side by side
| Phi 3 Mini 4k Instruct | Qwen1.5-110B | |
|---|---|---|
| Provider | Microsoft | Alibaba (Qwen) |
| Noometry Index | 27.9 | 34.2 |
| Released | 2024-04-23 | 2024-04-25 |
| Weights | Open | Open |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 35 | 20 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Qwen1.5-110B leads
Phi 3 Mini 4k Instruct: 26.6 (#323), Qwen1.5-110B: 33.0 (#264)
| Benchmark | Phi 3 Mini 4k Instruct | Qwen1.5-110B |
|---|---|---|
| LMArena Coding | 1093 | 1184 |
| BigCodeBench Instruct | — | 35% |
| LiveBench Coding | 15.5% | — |
| BigCodeBench Complete | — | 44.4% |
| HumanEval+ | 59.1% | — |
| MBPP+ | 54.2% | — |
Reasoning Qwen1.5-110B leads
Phi 3 Mini 4k Instruct: 14.1 (#328), Qwen1.5-110B: 22.7 (#189)
| Benchmark | Phi 3 Mini 4k Instruct | Qwen1.5-110B |
|---|---|---|
| LMArena Hard Prompts | 1072 | 1168 |
| Chess Puzzles | 0% | — |
| LiveBench Reasoning | 26.8% | — |
| LiveBench Data Analysis | 34.7% | — |
| Adversarial NLI | 52.8% | — |
| BIG-Bench Hard | 71.7% | — |
| ForecastBench | — | 57.7 |
| HellaSwag | 76.7% | — |
| LiveBench | 22.4% | — |
| WinoGrande | 70.8% | — |
Math Qwen1.5-110B leads
Phi 3 Mini 4k Instruct: 26.6 (#257), Qwen1.5-110B: 33.7 (#201)
| Benchmark | Phi 3 Mini 4k Instruct | Qwen1.5-110B |
|---|---|---|
| LMArena Math | 1111 | 1185 |
| LiveBench Math | 15.7% | — |
Knowledge Qwen1.5-110B leads
Phi 3 Mini 4k Instruct: 28.5 (#246), Qwen1.5-110B: 31.2 (#219)
| Benchmark | Phi 3 Mini 4k Instruct | Qwen1.5-110B |
|---|---|---|
| LMArena Expert | 1045 | 1144 |
| ARC (AI2) Challenge | 84.9% | — |
| MMLU | 68.8% | — |
| OpenBookQA | 88% | — |
| TriviaQA | 64% | — |
Multilingual Qwen1.5-110B leads
Phi 3 Mini 4k Instruct: 26.3 (#280), Qwen1.5-110B: 33.6 (#250)
| Benchmark | Phi 3 Mini 4k Instruct | Qwen1.5-110B |
|---|---|---|
| LMArena Non-English | 1021 | 1142 |
| LMArena Chinese | 1021 | 1206 |
| LMArena French | 1076 | 1151 |
| LMArena German | 1044 | 1123 |
| LMArena Japanese | 935 | 1074 |
| LMArena Korean | 905 | 1044 |
| LMArena Russian | 1022 | 1118 |
| LMArena Spanish | 1085 | 1142 |
Instruction Following Qwen1.5-110B leads
Phi 3 Mini 4k Instruct: 47.7 (#303), Qwen1.5-110B: 60.3 (#252)
| Benchmark | Phi 3 Mini 4k Instruct | Qwen1.5-110B |
|---|---|---|
| LMArena Instruction Following | 1053 | 1158 |
| LiveBench Instruction Following | 39.1% | — |
Long Context Qwen1.5-110B leads
Phi 3 Mini 4k Instruct: 31.7 (#276), Qwen1.5-110B: 35.1 (#242)
| Benchmark | Phi 3 Mini 4k Instruct | Qwen1.5-110B |
|---|---|---|
| LMArena Longer Query | 1044 | 1157 |
Writing & Preference Qwen1.5-110B leads
Phi 3 Mini 4k Instruct: 27.6 (#300), Qwen1.5-110B: 38.0 (#255)
| Benchmark | Phi 3 Mini 4k Instruct | Qwen1.5-110B |
|---|---|---|
| LMArena Text | 1073 | 1175 |
| LMArena Creative Writing | 1037 | 1148 |
| LMArena Multi-Turn | 1018 | 1160 |
| LiveBench Language | 9.2% | — |
Frequently asked questions
Is Phi 3 Mini 4k Instruct better than Qwen1.5-110B?
Qwen1.5-110B is the stronger model overall, scoring 34.2 to 27.9 on the Noometry Index.
Is Phi 3 Mini 4k Instruct or Qwen1.5-110B better for coding?
Qwen1.5-110B scores higher on coding benchmarks: 33.0 versus 26.6 in the Noometry coding category.
How many benchmarks do Phi 3 Mini 4k Instruct and Qwen1.5-110B share?
17 benchmarks have published results for both models. Phi 3 Mini 4k Instruct has 35 scored results on Noometry and Qwen1.5-110B has 20.