Model comparison
Qwen1.5-110B vs Qwen1.5-14B
Qwen1.5-110B is the stronger model overall, scoring 34.2 to 32.7 on the Noometry Index.
Last verified . 16 shared benchmarks.
Alibaba (Qwen)Summary
- They share 16 benchmarks with published results for both. Qwen1.5-110B scores higher in 7 categories and Qwen1.5-14B in 1 category; 7 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Qwen1.5-110B leads 38.0 to 33.6.
Side by side
| Qwen1.5-110B | Qwen1.5-14B | |
|---|---|---|
| Provider | Alibaba (Qwen) | Alibaba (Qwen) |
| Noometry Index | 34.2 | 32.7 |
| Released | 2024-04-25 | 2024-02-04 |
| Weights | Open | Open |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 20 | 17 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Too close to call
Qwen1.5-110B: 33.0 (#264), Qwen1.5-14B: 33.1 (#263)
| Benchmark | Qwen1.5-110B | Qwen1.5-14B |
|---|---|---|
| LMArena Coding | 1184 | 1138 |
| BigCodeBench Instruct | 35% | — |
| BigCodeBench Complete | 44.4% | — |
Reasoning Qwen1.5-110B leads
Qwen1.5-110B: 22.7 (#189), Qwen1.5-14B: 21.4 (#223)
| Benchmark | Qwen1.5-110B | Qwen1.5-14B |
|---|---|---|
| LMArena Hard Prompts | 1168 | 1113 |
| ForecastBench | 57.7 | — |
Math Qwen1.5-110B leads
Qwen1.5-110B: 33.7 (#201), Qwen1.5-14B: 32.4 (#215)
| Benchmark | Qwen1.5-110B | Qwen1.5-14B |
|---|---|---|
| LMArena Math | 1185 | 1125 |
Knowledge Qwen1.5-110B leads
Qwen1.5-110B: 31.2 (#219), Qwen1.5-14B: 29.8 (#232)
| Benchmark | Qwen1.5-110B | Qwen1.5-14B |
|---|---|---|
| LMArena Expert | 1144 | 1094 |
| MMLU | — | 68.6% |
Multilingual Qwen1.5-110B leads
Qwen1.5-110B: 33.6 (#250), Qwen1.5-14B: 30.7 (#262)
| Benchmark | Qwen1.5-110B | Qwen1.5-14B |
|---|---|---|
| LMArena Non-English | 1142 | 1095 |
| LMArena Chinese | 1206 | 1147 |
| LMArena French | 1151 | 1116 |
| LMArena German | 1123 | 1043 |
| LMArena Japanese | 1074 | 1019 |
| LMArena Russian | 1118 | 1046 |
| LMArena Spanish | 1142 | 1085 |
| LMArena Korean | 1044 | — |
Instruction Following Qwen1.5-110B leads
Qwen1.5-110B: 60.3 (#252), Qwen1.5-14B: 56.8 (#271)
| Benchmark | Qwen1.5-110B | Qwen1.5-14B |
|---|---|---|
| LMArena Instruction Following | 1158 | 1102 |
Long Context Qwen1.5-110B leads
Qwen1.5-110B: 35.1 (#242), Qwen1.5-14B: 33.7 (#257)
| Benchmark | Qwen1.5-110B | Qwen1.5-14B |
|---|---|---|
| LMArena Longer Query | 1157 | 1113 |
Writing & Preference Qwen1.5-110B leads
Qwen1.5-110B: 38.0 (#255), Qwen1.5-14B: 33.6 (#276)
| Benchmark | Qwen1.5-110B | Qwen1.5-14B |
|---|---|---|
| LMArena Text | 1175 | 1128 |
| LMArena Creative Writing | 1148 | 1091 |
| LMArena Multi-Turn | 1160 | 1110 |
Frequently asked questions
Is Qwen1.5-110B better than Qwen1.5-14B?
Qwen1.5-110B is the stronger model overall, scoring 34.2 to 32.7 on the Noometry Index.
Is Qwen1.5-110B or Qwen1.5-14B better for coding?
They score almost the same on coding (33.0 vs 33.1); test both on your own repository before choosing.
How many benchmarks do Qwen1.5-110B and Qwen1.5-14B share?
16 benchmarks have published results for both models. Qwen1.5-110B has 20 scored results on Noometry and Qwen1.5-14B has 17.