Model comparison
Qwen-14B vs Qwen1.5-72B
Qwen-14B and Qwen1.5-72B score almost the same on the Noometry Index (31.4 vs 30.8), so choose on price, context window or the category you care about most.
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 Qwen1.5-72B in 7 categories; 6 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Qwen1.5-72B leads 37.3 to 27.6.
Side by side
| Qwen-14B | Qwen1.5-72B | |
|---|---|---|
| Provider | Alibaba (Qwen) | Alibaba (Qwen) |
| Noometry Index | 31.4 | 30.8 |
| Released | 2023-09-24 | 2024-02-04 |
| Weights | Open | Open |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 18 | 22 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Too close to call
Qwen-14B: 31.2 (#288), Qwen1.5-72B: 31.9 (#277)
| Benchmark | Qwen-14B | Qwen1.5-72B |
|---|---|---|
| LMArena Coding | 1071 | 1165 |
| BigCodeBench Instruct | — | 33.2% |
| BigCodeBench Complete | — | 40.3% |
| HumanEval+ | — | 59.1% |
| MBPP+ | — | 61.6% |
Reasoning Qwen1.5-72B leads
Qwen-14B: 19.6 (#257), Qwen1.5-72B: 22.2 (#203)
| Benchmark | Qwen-14B | Qwen1.5-72B |
|---|---|---|
| LMArena Hard Prompts | 1027 | 1148 |
| BIG-Bench Hard | 55% | — |
| Epoch Capabilities Index | 113.03 | — |
| LAMBADA | 71.1% | — |
| PIQA | 79.9% | — |
Math Qwen1.5-72B leads
Qwen-14B: 31.2 (#227), Qwen1.5-72B: 33.2 (#205)
| Benchmark | Qwen-14B | Qwen1.5-72B |
|---|---|---|
| LMArena Math | 1068 | 1164 |
| GSM8K | 61.3% | — |
Knowledge Not comparable
Qwen-14B: —, Qwen1.5-72B: 11.5 (#300)
| Benchmark | Qwen-14B | Qwen1.5-72B |
|---|---|---|
| GPQA Diamond | — | 28.8% |
| LMArena Expert | — | 1136 |
| ARC (AI2) Challenge | 84.4% | — |
| BoolQ | 86.2% | — |
| MMLU | 66.3% | — |
Multilingual Qwen1.5-72B leads
Qwen-14B: 27.5 (#275), Qwen1.5-72B: 33.2 (#253)
| Benchmark | Qwen-14B | Qwen1.5-72B |
|---|---|---|
| LMArena Non-English | 1041 | 1135 |
| LMArena Chinese | 1077 | 1186 |
| LMArena French | — | 1159 |
| LMArena German | — | 1084 |
| LMArena Japanese | — | 1061 |
| LMArena Korean | — | 1050 |
| LMArena Russian | — | 1104 |
| LMArena Spanish | — | 1110 |
Instruction Following Qwen1.5-72B leads
Qwen-14B: 52.4 (#289), Qwen1.5-72B: 59.3 (#256)
| Benchmark | Qwen-14B | Qwen1.5-72B |
|---|---|---|
| LMArena Instruction Following | 1031 | 1141 |
Long Context Qwen1.5-72B leads
Qwen-14B: 31.3 (#280), Qwen1.5-72B: 35.1 (#243)
| Benchmark | Qwen-14B | Qwen1.5-72B |
|---|---|---|
| LMArena Longer Query | 1028 | 1157 |
Writing & Preference Qwen1.5-72B leads
Qwen-14B: 27.6 (#299), Qwen1.5-72B: 37.3 (#258)
| Benchmark | Qwen-14B | Qwen1.5-72B |
|---|---|---|
| LMArena Text | 1051 | 1166 |
| LMArena Creative Writing | 1028 | 1137 |
| LMArena Multi-Turn | 1022 | 1160 |
Frequently asked questions
Is Qwen-14B better than Qwen1.5-72B?
Qwen-14B and Qwen1.5-72B score almost the same on the Noometry Index (31.4 vs 30.8), so choose on price, context window or the category you care about most.
Is Qwen-14B or Qwen1.5-72B better for coding?
They score almost the same on coding (31.2 vs 31.9); test both on your own repository before choosing.
How many benchmarks do Qwen-14B and Qwen1.5-72B share?
10 benchmarks have published results for both models. Qwen-14B has 18 scored results on Noometry and Qwen1.5-72B has 22.