Model comparison
Phi 3 Small 8k Instruct vs Qwen1.5 4b Chat
Phi 3 Small 8k Instruct and Qwen1.5 4b Chat score almost the same on the Noometry Index (29.3 vs 28.8), so choose on price, context window or the category you care about most.
Last verified . 13 shared benchmarks.
Microsoft
Alibaba (Qwen)Summary
- They share 13 benchmarks with published results for both. Phi 3 Small 8k Instruct scores higher in 5 categories and Qwen1.5 4b Chat in 3 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Phi 3 Small 8k Instruct leads 31.1 to 23.8.
Side by side
| Phi 3 Small 8k Instruct | Qwen1.5 4b Chat | |
|---|---|---|
| Provider | Microsoft | Alibaba (Qwen) |
| Noometry Index | 29.3 | 28.8 |
| Released | 2024-04-23 | — |
| Weights | Open | Open |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 32 | 13 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Qwen1.5 4b Chat leads
Phi 3 Small 8k Instruct: 27.9 (#318), Qwen1.5 4b Chat: 29.1 (#308)
| Benchmark | Phi 3 Small 8k Instruct | Qwen1.5 4b Chat |
|---|---|---|
| LMArena Coding | 1101 | 999 |
| LiveBench Coding | 20.3% | — |
Reasoning Qwen1.5 4b Chat leads
Phi 3 Small 8k Instruct: 14.8 (#323), Qwen1.5 4b Chat: 18.5 (#279)
| Benchmark | Phi 3 Small 8k Instruct | Qwen1.5 4b Chat |
|---|---|---|
| LMArena Hard Prompts | 1100 | 976 |
| 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 4b Chat leads
Phi 3 Small 8k Instruct: 27.6 (#248), Qwen1.5 4b Chat: 30.4 (#234)
| Benchmark | Phi 3 Small 8k Instruct | Qwen1.5 4b Chat |
|---|---|---|
| LMArena Math | 1151 | 1026 |
| LiveBench Math | 17.6% | — |
Knowledge Phi 3 Small 8k Instruct leads
Phi 3 Small 8k Instruct: 29.1 (#240), Qwen1.5 4b Chat: 26.7 (#255)
| Benchmark | Phi 3 Small 8k Instruct | Qwen1.5 4b Chat |
|---|---|---|
| LMArena Expert | 1067 | 980 |
| ARC (AI2) Challenge | 90.7% | — |
| MMLU | 75.7% | — |
| OpenBookQA | 88% | — |
| TriviaQA | 58.1% | — |
Multilingual Phi 3 Small 8k Instruct leads
Phi 3 Small 8k Instruct: 28.5 (#272), Qwen1.5 4b Chat: 24.1 (#290)
| Benchmark | Phi 3 Small 8k Instruct | Qwen1.5 4b Chat |
|---|---|---|
| LMArena Non-English | 1058 | 979 |
| LMArena Chinese | 1061 | 1024 |
| LMArena German | 1080 | 902 |
| LMArena Russian | 1111 | 952 |
| LMArena French | 1135 | — |
| LMArena Japanese | 966 | — |
| LMArena Korean | 894 | — |
| LMArena Spanish | 1111 | — |
Instruction Following Phi 3 Small 8k Instruct leads
Phi 3 Small 8k Instruct: 51.9 (#292), Qwen1.5 4b Chat: 49.0 (#300)
| Benchmark | Phi 3 Small 8k Instruct | Qwen1.5 4b Chat |
|---|---|---|
| LMArena Instruction Following | 1087 | 978 |
| LiveBench Instruction Following | 47.2% | — |
Long Context Phi 3 Small 8k Instruct leads
Phi 3 Small 8k Instruct: 33.0 (#267), Qwen1.5 4b Chat: 30.1 (#290)
| Benchmark | Phi 3 Small 8k Instruct | Qwen1.5 4b Chat |
|---|---|---|
| LMArena Longer Query | 1088 | 988 |
Writing & Preference Phi 3 Small 8k Instruct leads
Phi 3 Small 8k Instruct: 31.1 (#284), Qwen1.5 4b Chat: 23.8 (#309)
| Benchmark | Phi 3 Small 8k Instruct | Qwen1.5 4b Chat |
|---|---|---|
| LMArena Text | 1110 | 997 |
| LMArena Creative Writing | 1083 | 969 |
| LMArena Multi-Turn | 1068 | 977 |
| LiveBench Language | 12.9% | — |
Frequently asked questions
Is Phi 3 Small 8k Instruct better than Qwen1.5 4b Chat?
Phi 3 Small 8k Instruct and Qwen1.5 4b Chat score almost the same on the Noometry Index (29.3 vs 28.8), so choose on price, context window or the category you care about most.
Is Phi 3 Small 8k Instruct or Qwen1.5 4b Chat better for coding?
Qwen1.5 4b Chat scores higher on coding benchmarks: 29.1 versus 27.9 in the Noometry coding category.
How many benchmarks do Phi 3 Small 8k Instruct and Qwen1.5 4b Chat share?
13 benchmarks have published results for both models. Phi 3 Small 8k Instruct has 32 scored results on Noometry and Qwen1.5 4b Chat has 13.