Model comparison
Qwen1.5-32B vs Qwen2-72B
Qwen1.5-32B and Qwen2-72B score almost the same on the Noometry Index (30.5 vs 30.0), so choose on price, context window or the category you care about most.
Last verified . 21 shared benchmarks.
Alibaba (Qwen)Summary
- They share 21 benchmarks with published results for both. Qwen1.5-32B scores higher in 2 categories and Qwen2-72B in 6 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Qwen2-72B leads 21.2 to 13.5.
- The biggest single-benchmark swing is BigCodeBench Complete: 42% for Qwen1.5-32B and 54% for Qwen2-72B.
Side by side
| Qwen1.5-32B | Qwen2-72B | |
|---|---|---|
| Provider | Alibaba (Qwen) | Alibaba (Qwen) |
| Noometry Index | 30.5 | 30.0 |
| Released | 2024-02-04 | 2024-06-07 |
| Weights | Open | Open |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 21 | 26 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Qwen1.5-32B leads
Qwen1.5-32B: 31.7 (#282), Qwen2-72B: 29.1 (#310)
| Benchmark | Qwen1.5-32B | Qwen2-72B |
|---|---|---|
| BigCodeBench Instruct | 32.3% | 38.5% |
| LMArena Coding | 1155 | 1196 |
| BigCodeBench Complete | 42% | 54% |
| WeirdML | — | 11.3% |
Agentic & Tool Use Not comparable
Qwen1.5-32B: —, Qwen2-72B: 17.0 (#146)
| Benchmark | Qwen1.5-32B | Qwen2-72B |
|---|---|---|
| TheAgentCompany | — | 1.1% |
| METR Time Horizons | — | 29.9% |
Reasoning Qwen2-72B leads
Qwen1.5-32B: 21.8 (#212), Qwen2-72B: 23.2 (#181)
| Benchmark | Qwen1.5-32B | Qwen2-72B |
|---|---|---|
| LMArena Hard Prompts | 1130 | 1191 |
| Epoch Capabilities Index | — | 125.28 |
Math Qwen1.5-32B leads
Qwen1.5-32B: 33.0 (#207), Qwen2-72B: 30.2 (#236)
| Benchmark | Qwen1.5-32B | Qwen2-72B |
|---|---|---|
| LMArena Math | 1155 | 1235 |
| MATH Level 5 | — | 39.1% |
Knowledge Qwen2-72B leads
Qwen1.5-32B: 13.5 (#296), Qwen2-72B: 21.2 (#275)
| Benchmark | Qwen1.5-32B | Qwen2-72B |
|---|---|---|
| GPQA Diamond | 30.7% | 40.8% |
| LMArena Expert | 1126 | 1171 |
| MMLU | 74.4% | 82.4% |
Multilingual Qwen2-72B leads
Qwen1.5-32B: 31.4 (#259), Qwen2-72B: 35.9 (#244)
| Benchmark | Qwen1.5-32B | Qwen2-72B |
|---|---|---|
| LMArena Non-English | 1106 | 1176 |
| LMArena Chinese | 1177 | 1240 |
| LMArena French | 1101 | 1170 |
| LMArena German | 1058 | 1151 |
| LMArena Japanese | 1027 | 1111 |
| LMArena Korean | 1008 | 1083 |
| LMArena Russian | 1073 | 1169 |
| LMArena Spanish | 1089 | 1169 |
Instruction Following Qwen2-72B leads
Qwen1.5-32B: 57.7 (#265), Qwen2-72B: 61.7 (#241)
| Benchmark | Qwen1.5-32B | Qwen2-72B |
|---|---|---|
| LMArena Instruction Following | 1116 | 1181 |
Long Context Qwen2-72B leads
Qwen1.5-32B: 34.7 (#246), Qwen2-72B: 36.1 (#235)
| Benchmark | Qwen1.5-32B | Qwen2-72B |
|---|---|---|
| LMArena Longer Query | 1146 | 1192 |
Writing & Preference Qwen2-72B leads
Qwen1.5-32B: 34.2 (#271), Qwen2-72B: 40.8 (#241)
| Benchmark | Qwen1.5-32B | Qwen2-72B |
|---|---|---|
| LMArena Text | 1137 | 1203 |
| LMArena Creative Writing | 1083 | 1181 |
| LMArena Multi-Turn | 1140 | 1196 |
Frequently asked questions
Is Qwen1.5-32B better than Qwen2-72B?
Qwen1.5-32B and Qwen2-72B score almost the same on the Noometry Index (30.5 vs 30.0), so choose on price, context window or the category you care about most.
Is Qwen1.5-32B or Qwen2-72B better for coding?
Qwen1.5-32B scores higher on coding benchmarks: 31.7 versus 29.1 in the Noometry coding category.
How many benchmarks do Qwen1.5-32B and Qwen2-72B share?
21 benchmarks have published results for both models. Qwen1.5-32B has 21 scored results on Noometry and Qwen2-72B has 26.