Model comparison
Qwen-14B vs Qwen1.5-110B
Qwen1.5-110B is the stronger model overall, scoring 33.6 to 30.8 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 0 categories and Qwen1.5-110B in 7 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Qwen1.5-110B leads 38.1 to 27.8.
Side by side
| Qwen-14B | Qwen1.5-110B | |
|---|---|---|
| Provider | Alibaba (Qwen) | Alibaba (Qwen) |
| Noometry Index | 30.8 | 33.6 |
| Released | 2023-09-24 | 2024-04-25 |
| Weights | Open | Open |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 18 | 20 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Qwen1.5-110B leads
Qwen-14B: 30.6 (#283), Qwen1.5-110B: 32.4 (#260)
| Benchmark | Qwen-14B | Qwen1.5-110B |
|---|---|---|
| LMArena Coding | 1072 | 1184 |
| BigCodeBench Instruct | — | 35% |
| BigCodeBench Complete | — | 44.4% |
Reasoning Qwen1.5-110B leads
Qwen-14B: 18.7 (#255), Qwen1.5-110B: 21.7 (#192)
| Benchmark | Qwen-14B | Qwen1.5-110B |
|---|---|---|
| LMArena Hard Prompts | 1027 | 1168 |
| BIG-Bench Hard | 55% | — |
| Epoch Capabilities Index | 112.8 | — |
| ForecastBench | — | 57.7 |
| LAMBADA | 71.1% | — |
| PIQA | 79.9% | — |
Math Qwen1.5-110B leads
Qwen-14B: 28.7 (#224), Qwen1.5-110B: 31.1 (#199)
| Benchmark | Qwen-14B | Qwen1.5-110B |
|---|---|---|
| LMArena Math | 1068 | 1185 |
| GSM8K | 61.3% | — |
Knowledge Not comparable
Qwen-14B: —, Qwen1.5-110B: 30.7 (#217)
| Benchmark | Qwen-14B | Qwen1.5-110B |
|---|---|---|
| LMArena Expert | — | 1144 |
| ARC (AI2) Challenge | 84.4% | — |
| BoolQ | 86.2% | — |
| MMLU | 66.3% | — |
Multilingual Qwen1.5-110B leads
Qwen-14B: 27.7 (#270), Qwen1.5-110B: 33.8 (#245)
| Benchmark | Qwen-14B | Qwen1.5-110B |
|---|---|---|
| LMArena Non-English | 1042 | 1142 |
| LMArena Chinese | 1077 | 1206 |
| LMArena French | — | 1150 |
| LMArena German | — | 1123 |
| LMArena Japanese | — | 1074 |
| LMArena Korean | — | 1044 |
| LMArena Russian | — | 1118 |
| LMArena Spanish | — | 1141 |
Instruction Following Qwen1.5-110B leads
Qwen-14B: 52.6 (#284), Qwen1.5-110B: 60.6 (#247)
| Benchmark | Qwen-14B | Qwen1.5-110B |
|---|---|---|
| LMArena Instruction Following | 1031 | 1158 |
Long Context Qwen1.5-110B leads
Qwen-14B: 31.3 (#276), Qwen1.5-110B: 35.0 (#237)
| Benchmark | Qwen-14B | Qwen1.5-110B |
|---|---|---|
| LMArena Longer Query | 1029 | 1157 |
Writing & Preference Qwen1.5-110B leads
Qwen-14B: 27.8 (#294), Qwen1.5-110B: 38.1 (#250)
| Benchmark | Qwen-14B | Qwen1.5-110B |
|---|---|---|
| LMArena Text | 1051 | 1175 |
| LMArena Creative Writing | 1028 | 1148 |
| LMArena Multi-Turn | 1022 | 1160 |
Frequently asked questions
Is Qwen-14B better than Qwen1.5-110B?
Qwen1.5-110B is the stronger model overall, scoring 33.6 to 30.8 on the Noometry Index.
Is Qwen-14B or Qwen1.5-110B better for coding?
Qwen1.5-110B scores higher on coding benchmarks: 32.4 versus 30.6 in the Noometry coding category.
How many benchmarks do Qwen-14B and Qwen1.5-110B share?
10 benchmarks have published results for both models. Qwen-14B has 18 scored results on Noometry and Qwen1.5-110B has 20.