Model comparison
Qwen-14B vs Qwen1.5 4b Chat
Qwen-14B is the stronger model overall, scoring 31.4 to 28.8 on the Noometry Index.
Last verified . 10 shared benchmarks.
Alibaba (Qwen)Summary
- They share 10 benchmarks with published results for both. Qwen-14B scores higher in 7 categories and Qwen1.5 4b Chat in 0 categories; 6 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Qwen-14B leads 27.6 to 23.8.
Side by side
| Qwen-14B | Qwen1.5 4b Chat | |
|---|---|---|
| Provider | Alibaba (Qwen) | Alibaba (Qwen) |
| Noometry Index | 31.4 | 28.8 |
| Released | 2023-09-24 | — |
| Weights | Open | Open |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 18 | 13 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Qwen-14B leads
Qwen-14B: 31.2 (#288), Qwen1.5 4b Chat: 29.1 (#308)
| Benchmark | Qwen-14B | Qwen1.5 4b Chat |
|---|---|---|
| LMArena Coding | 1071 | 999 |
Reasoning Qwen-14B leads
Qwen-14B: 19.6 (#257), Qwen1.5 4b Chat: 18.5 (#279)
| Benchmark | Qwen-14B | Qwen1.5 4b Chat |
|---|---|---|
| LMArena Hard Prompts | 1027 | 976 |
| BIG-Bench Hard | 55% | — |
| Epoch Capabilities Index | 113.03 | — |
| LAMBADA | 71.1% | — |
| PIQA | 79.9% | — |
Math Too close to call
Qwen-14B: 31.2 (#227), Qwen1.5 4b Chat: 30.4 (#234)
| Benchmark | Qwen-14B | Qwen1.5 4b Chat |
|---|---|---|
| LMArena Math | 1068 | 1026 |
| GSM8K | 61.3% | — |
Knowledge Not comparable
Qwen-14B: —, Qwen1.5 4b Chat: 26.7 (#255)
| Benchmark | Qwen-14B | Qwen1.5 4b Chat |
|---|---|---|
| LMArena Expert | — | 980 |
| ARC (AI2) Challenge | 84.4% | — |
| BoolQ | 86.2% | — |
| MMLU | 66.3% | — |
Multilingual Qwen-14B leads
Qwen-14B: 27.5 (#275), Qwen1.5 4b Chat: 24.1 (#290)
| Benchmark | Qwen-14B | Qwen1.5 4b Chat |
|---|---|---|
| LMArena Non-English | 1041 | 979 |
| LMArena Chinese | 1077 | 1024 |
| LMArena German | — | 902 |
| LMArena Russian | — | 952 |
Instruction Following Qwen-14B leads
Qwen-14B: 52.4 (#289), Qwen1.5 4b Chat: 49.0 (#300)
| Benchmark | Qwen-14B | Qwen1.5 4b Chat |
|---|---|---|
| LMArena Instruction Following | 1031 | 978 |
Long Context Qwen-14B leads
Qwen-14B: 31.3 (#280), Qwen1.5 4b Chat: 30.1 (#290)
| Benchmark | Qwen-14B | Qwen1.5 4b Chat |
|---|---|---|
| LMArena Longer Query | 1028 | 988 |
Writing & Preference Qwen-14B leads
Qwen-14B: 27.6 (#299), Qwen1.5 4b Chat: 23.8 (#309)
| Benchmark | Qwen-14B | Qwen1.5 4b Chat |
|---|---|---|
| LMArena Text | 1051 | 997 |
| LMArena Creative Writing | 1028 | 969 |
| LMArena Multi-Turn | 1022 | 977 |
Frequently asked questions
Is Qwen-14B better than Qwen1.5 4b Chat?
Qwen-14B is the stronger model overall, scoring 31.4 to 28.8 on the Noometry Index.
Is Qwen-14B or Qwen1.5 4b Chat better for coding?
Qwen-14B scores higher on coding benchmarks: 31.2 versus 29.1 in the Noometry coding category.
How many benchmarks do Qwen-14B and Qwen1.5 4b Chat share?
10 benchmarks have published results for both models. Qwen-14B has 18 scored results on Noometry and Qwen1.5 4b Chat has 13.