Model comparison
Phi 3 Small 8k Instruct vs Qwen1.5-14B
Qwen1.5-14B is the stronger model overall, scoring 32.1 to 28.8 on the Noometry Index.
Last verified . 17 shared benchmarks.
Microsoft
Alibaba (Qwen)Summary
- They share 17 benchmarks with published results for both. Phi 3 Small 8k Instruct scores higher in 0 categories and Qwen1.5-14B in 8 categories; 6 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Qwen1.5-14B leads 20.5 to 14.2.
Side by side
| Phi 3 Small 8k Instruct | Qwen1.5-14B | |
|---|---|---|
| Provider | Microsoft | Alibaba (Qwen) |
| Noometry Index | 28.8 | 32.1 |
| Released | 2024-04-23 | 2024-02-04 |
| Weights | Open | Open |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 32 | 17 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Qwen1.5-14B leads
Phi 3 Small 8k Instruct: 27.4 (#313), Qwen1.5-14B: 32.5 (#259)
| Benchmark | Phi 3 Small 8k Instruct | Qwen1.5-14B |
|---|---|---|
| LMArena Coding | 1102 | 1138 |
| LiveBench Coding | 20.3% | — |
Reasoning Qwen1.5-14B leads
Phi 3 Small 8k Instruct: 14.2 (#319), Qwen1.5-14B: 20.5 (#217)
| Benchmark | Phi 3 Small 8k Instruct | Qwen1.5-14B |
|---|---|---|
| LMArena Hard Prompts | 1100 | 1113 |
| LiveBench Reasoning | 15.9% | — |
| LiveBench Data Analysis | 30.3% | — |
| Adversarial NLI | 58.1% | — |
| BIG-Bench Hard | 79.1% | — |
| HellaSwag | 77% | — |
| LiveBench | 24% | — |
| WinoGrande | 81.5% | — |
Math Qwen1.5-14B leads
Phi 3 Small 8k Instruct: 25.4 (#247), Qwen1.5-14B: 29.9 (#214)
| Benchmark | Phi 3 Small 8k Instruct | Qwen1.5-14B |
|---|---|---|
| LMArena Math | 1151 | 1125 |
| LiveBench Math | 17.6% | — |
Knowledge Too close to call
Phi 3 Small 8k Instruct: 28.5 (#237), Qwen1.5-14B: 29.3 (#230)
| Benchmark | Phi 3 Small 8k Instruct | Qwen1.5-14B |
|---|---|---|
| LMArena Expert | 1067 | 1094 |
| MMLU | 75.7% | 68.6% |
| ARC (AI2) Challenge | 90.7% | — |
| OpenBookQA | 88% | — |
| TriviaQA | 58.1% | — |
Multilingual Qwen1.5-14B leads
Phi 3 Small 8k Instruct: 28.6 (#267), Qwen1.5-14B: 30.8 (#257)
| Benchmark | Phi 3 Small 8k Instruct | Qwen1.5-14B |
|---|---|---|
| LMArena Non-English | 1058 | 1095 |
| LMArena Chinese | 1061 | 1147 |
| LMArena French | 1134 | 1115 |
| LMArena German | 1080 | 1043 |
| LMArena Japanese | 966 | 1019 |
| LMArena Russian | 1111 | 1046 |
| LMArena Spanish | 1111 | 1085 |
| LMArena Korean | 894 | — |
Instruction Following Qwen1.5-14B leads
Phi 3 Small 8k Instruct: 52.2 (#287), Qwen1.5-14B: 57.1 (#266)
| Benchmark | Phi 3 Small 8k Instruct | Qwen1.5-14B |
|---|---|---|
| LMArena Instruction Following | 1087 | 1102 |
| LiveBench Instruction Following | 47.2% | — |
Long Context Too close to call
Phi 3 Small 8k Instruct: 33.0 (#262), Qwen1.5-14B: 33.7 (#252)
| Benchmark | Phi 3 Small 8k Instruct | Qwen1.5-14B |
|---|---|---|
| LMArena Longer Query | 1088 | 1113 |
Writing & Preference Qwen1.5-14B leads
Phi 3 Small 8k Instruct: 31.3 (#279), Qwen1.5-14B: 33.7 (#270)
| Benchmark | Phi 3 Small 8k Instruct | Qwen1.5-14B |
|---|---|---|
| LMArena Text | 1110 | 1128 |
| LMArena Creative Writing | 1083 | 1091 |
| LMArena Multi-Turn | 1068 | 1110 |
| LiveBench Language | 12.9% | — |
Frequently asked questions
Is Phi 3 Small 8k Instruct better than Qwen1.5-14B?
Qwen1.5-14B is the stronger model overall, scoring 32.1 to 28.8 on the Noometry Index.
Is Phi 3 Small 8k Instruct or Qwen1.5-14B better for coding?
Qwen1.5-14B scores higher on coding benchmarks: 32.5 versus 27.4 in the Noometry coding category.
How many benchmarks do Phi 3 Small 8k Instruct and Qwen1.5-14B share?
17 benchmarks have published results for both models. Phi 3 Small 8k Instruct has 32 scored results on Noometry and Qwen1.5-14B has 17.