Model comparison
GLM-4.5-Air vs Qwen1.5-32B
GLM-4.5-Air is the stronger model overall, scoring 38.9 to 30.5 on the Noometry Index.
Last verified . 17 shared benchmarks.
Alibaba (Qwen)Summary
- They share 17 benchmarks with published results for both. GLM-4.5-Air scores higher in 8 categories and Qwen1.5-32B in 0 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where GLM-4.5-Air leads 55.9 to 34.2.
Side by side
| GLM-4.5-Air | Qwen1.5-32B | |
|---|---|---|
| Provider | Z.ai (Zhipu) | Alibaba (Qwen) |
| Noometry Index | 38.9 | 30.5 |
| Released | 2025-07-20 | 2024-02-04 |
| Weights | Open | Open |
| Context window | 131K | — |
| Max output | 98K | — |
| Input $ / M tokens | $0.20 | — |
| Output $ / M tokens | $1.10 | — |
| Results tracked | 27 | 21 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding GLM-4.5-Air leads
GLM-4.5-Air: 33.3 (#259), Qwen1.5-32B: 31.7 (#282)
| Benchmark | GLM-4.5-Air | Qwen1.5-32B |
|---|---|---|
| LMArena Coding | 1397 | 1155 |
| GSO | 2.9% | — |
| BigCodeBench Instruct | — | 32.3% |
| BigCodeBench Complete | — | 42% |
Reasoning GLM-4.5-Air leads
GLM-4.5-Air: 24.1 (#166), Qwen1.5-32B: 21.8 (#212)
| Benchmark | GLM-4.5-Air | Qwen1.5-32B |
|---|---|---|
| LMArena Hard Prompts | 1379 | 1130 |
| Kagi LLM Benchmark | 43% | — |
| ForecastBench | 59.2 | — |
Math GLM-4.5-Air leads
GLM-4.5-Air: 36.2 (#170), Qwen1.5-32B: 33.0 (#207)
| Benchmark | GLM-4.5-Air | Qwen1.5-32B |
|---|---|---|
| LMArena Math | 1396 | 1155 |
| Omni-MATH | 39.1% | — |
Knowledge GLM-4.5-Air leads
GLM-4.5-Air: 35.0 (#191), Qwen1.5-32B: 13.5 (#296)
| Benchmark | GLM-4.5-Air | Qwen1.5-32B |
|---|---|---|
| LMArena Expert | 1370 | 1126 |
| GPQA Diamond | — | 30.7% |
| Humanity's Last Exam | 8.1% | — |
| MMLU-Pro | 76.2% | — |
| Vectara Hallucination Rate | 9.3% | — |
| GPQA (HELM) | 59.4% | — |
| MMLU | — | 74.4% |
Multilingual GLM-4.5-Air leads
GLM-4.5-Air: 49.1 (#135), Qwen1.5-32B: 31.4 (#259)
| Benchmark | GLM-4.5-Air | Qwen1.5-32B |
|---|---|---|
| LMArena Non-English | 1366 | 1106 |
| LMArena Chinese | 1426 | 1177 |
| LMArena French | 1399 | 1101 |
| LMArena German | 1377 | 1058 |
| LMArena Japanese | 1348 | 1027 |
| LMArena Korean | 1308 | 1008 |
| LMArena Russian | 1373 | 1073 |
| LMArena Spanish | 1386 | 1089 |
Instruction Following GLM-4.5-Air leads
GLM-4.5-Air: 69.6 (#171), Qwen1.5-32B: 57.7 (#265)
| Benchmark | GLM-4.5-Air | Qwen1.5-32B |
|---|---|---|
| LMArena Instruction Following | 1354 | 1116 |
| IFEval | 81.2% | — |
Long Context GLM-4.5-Air leads
GLM-4.5-Air: 41.6 (#135), Qwen1.5-32B: 34.7 (#246)
| Benchmark | GLM-4.5-Air | Qwen1.5-32B |
|---|---|---|
| LMArena Longer Query | 1366 | 1146 |
Writing & Preference GLM-4.5-Air leads
GLM-4.5-Air: 55.9 (#139), Qwen1.5-32B: 34.2 (#271)
| Benchmark | GLM-4.5-Air | Qwen1.5-32B |
|---|---|---|
| LMArena Text | 1384 | 1137 |
| LMArena Creative Writing | 1343 | 1083 |
| LMArena Multi-Turn | 1371 | 1140 |
| WildBench | 78.9% | — |
Frequently asked questions
Is GLM-4.5-Air better than Qwen1.5-32B?
GLM-4.5-Air is the stronger model overall, scoring 38.9 to 30.5 on the Noometry Index.
Is GLM-4.5-Air or Qwen1.5-32B better for coding?
GLM-4.5-Air scores higher on coding benchmarks: 33.3 versus 31.7 in the Noometry coding category.
How many benchmarks do GLM-4.5-Air and Qwen1.5-32B share?
17 benchmarks have published results for both models. GLM-4.5-Air has 27 scored results on Noometry and Qwen1.5-32B has 21.