Model comparison
Qwen1.5-32B vs Qwen1.5-7B
Qwen1.5-32B and Qwen1.5-7B score almost the same on the Noometry Index (30.5 vs 31.4), so choose on price, context window or the category you care about most.
Last verified . 13 shared benchmarks.
Alibaba (Qwen)Summary
- They share 13 benchmarks with published results for both. Qwen1.5-32B scores higher in 6 categories and Qwen1.5-7B in 2 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Qwen1.5-7B leads 28.7 to 13.5.
Side by side
| Qwen1.5-32B | Qwen1.5-7B | |
|---|---|---|
| Provider | Alibaba (Qwen) | Alibaba (Qwen) |
| Noometry Index | 30.5 | 31.4 |
| Released | 2024-02-04 | 2024-02-04 |
| Weights | Open | Open |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 21 | 13 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Too close to call
Qwen1.5-32B: 31.7 (#282), Qwen1.5-7B: 32.2 (#276)
| Benchmark | Qwen1.5-32B | Qwen1.5-7B |
|---|---|---|
| LMArena Coding | 1155 | 1107 |
| BigCodeBench Instruct | 32.3% | — |
| BigCodeBench Complete | 42% | — |
Reasoning Qwen1.5-32B leads
Qwen1.5-32B: 21.8 (#212), Qwen1.5-7B: 20.4 (#240)
| Benchmark | Qwen1.5-32B | Qwen1.5-7B |
|---|---|---|
| LMArena Hard Prompts | 1130 | 1065 |
Math Qwen1.5-32B leads
Qwen1.5-32B: 33.0 (#207), Qwen1.5-7B: 31.4 (#224)
| Benchmark | Qwen1.5-32B | Qwen1.5-7B |
|---|---|---|
| LMArena Math | 1155 | 1080 |
Knowledge Qwen1.5-7B leads
Qwen1.5-32B: 13.5 (#296), Qwen1.5-7B: 28.7 (#243)
| Benchmark | Qwen1.5-32B | Qwen1.5-7B |
|---|---|---|
| LMArena Expert | 1126 | 1055 |
| MMLU | 74.4% | 62.6% |
| GPQA Diamond | 30.7% | — |
Multilingual Qwen1.5-32B leads
Qwen1.5-32B: 31.4 (#259), Qwen1.5-7B: 28.5 (#271)
| Benchmark | Qwen1.5-32B | Qwen1.5-7B |
|---|---|---|
| LMArena Non-English | 1106 | 1058 |
| LMArena Chinese | 1177 | 1141 |
| LMArena Russian | 1073 | 1006 |
| LMArena French | 1101 | — |
| LMArena German | 1058 | — |
| LMArena Japanese | 1027 | — |
| LMArena Korean | 1008 | — |
| LMArena Spanish | 1089 | — |
Instruction Following Qwen1.5-32B leads
Qwen1.5-32B: 57.7 (#265), Qwen1.5-7B: 54.1 (#281)
| Benchmark | Qwen1.5-32B | Qwen1.5-7B |
|---|---|---|
| LMArena Instruction Following | 1116 | 1058 |
Long Context Qwen1.5-32B leads
Qwen1.5-32B: 34.7 (#246), Qwen1.5-7B: 33.1 (#266)
| Benchmark | Qwen1.5-32B | Qwen1.5-7B |
|---|---|---|
| LMArena Longer Query | 1146 | 1090 |
Writing & Preference Qwen1.5-32B leads
Qwen1.5-32B: 34.2 (#271), Qwen1.5-7B: 29.6 (#293)
| Benchmark | Qwen1.5-32B | Qwen1.5-7B |
|---|---|---|
| LMArena Text | 1137 | 1083 |
| LMArena Creative Writing | 1083 | 1035 |
| LMArena Multi-Turn | 1140 | 1062 |
Frequently asked questions
Is Qwen1.5-32B better than Qwen1.5-7B?
Qwen1.5-32B and Qwen1.5-7B score almost the same on the Noometry Index (30.5 vs 31.4), so choose on price, context window or the category you care about most.
Is Qwen1.5-32B or Qwen1.5-7B better for coding?
They score almost the same on coding (31.7 vs 32.2); test both on your own repository before choosing.
How many benchmarks do Qwen1.5-32B and Qwen1.5-7B share?
13 benchmarks have published results for both models. Qwen1.5-32B has 21 scored results on Noometry and Qwen1.5-7B has 13.