Model comparison
GLM-4.5-Air vs Qwen2.5-Max
Qwen2.5-Max is the stronger model overall, scoring 40.1 to 38.7 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 3 categories and Qwen2.5-Max in 5 categories; 4 gaps are clear of the uncertainty.
- The widest gap is in coding, where Qwen2.5-Max leads 41.2 to 34.5.
- GLM-4.5-Air has downloadable open weights; the other is API-only.
Side by side
| GLM-4.5-Air | Qwen2.5-Max | |
|---|---|---|
| Provider | Z.ai (Zhipu) | Alibaba (Qwen) |
| Noometry Index | 38.7 | 40.1 |
| Released | 2025-07-20 | 2025-01-25 |
| Weights | Open | Proprietary |
| Context window | 131K | — |
| Max output | 98K | — |
| Input $ / M tokens | $0.20 | — |
| Output $ / M tokens | $1.10 | — |
| Results tracked | 27 | 27 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Qwen2.5-Max leads
GLM-4.5-Air: 34.5 (#225), Qwen2.5-Max: 41.2 (#118)
| Benchmark | GLM-4.5-Air | Qwen2.5-Max |
|---|---|---|
| LMArena Coding | 1397 | 1359 |
| GSO | 2.9% | — |
| LiveBench Coding | — | 64.4% |
Reasoning Qwen2.5-Max leads
GLM-4.5-Air: 23.3 (#166), Qwen2.5-Max: 24.6 (#144)
| Benchmark | GLM-4.5-Air | Qwen2.5-Max |
|---|---|---|
| LMArena Hard Prompts | 1379 | 1360 |
| Kagi LLM Benchmark | 43% | — |
| LiveBench Reasoning | — | 51.4% |
| LiveBench Data Analysis | — | 67.9% |
| Epoch Capabilities Index | — | 132.54 |
| ForecastBench | 59.2 | — |
| LiveBench | — | 62.3% |
Math Too close to call
GLM-4.5-Air: 33.8 (#166), Qwen2.5-Max: 34.3 (#162)
| Benchmark | GLM-4.5-Air | Qwen2.5-Max |
|---|---|---|
| LMArena Math | 1396 | 1369 |
| Omni-MATH | 39.1% | — |
| LiveBench Math | — | 58.4% |
Knowledge Too close to call
GLM-4.5-Air: 34.6 (#184), Qwen2.5-Max: 34.8 (#181)
| Benchmark | GLM-4.5-Air | Qwen2.5-Max |
|---|---|---|
| LMArena Expert | 1370 | 1337 |
| Humanity's Last Exam | 8.1% | — |
| MMLU-Pro | 76.2% | — |
| Confabulations | — | 21.8% |
| Vectara Hallucination Rate | 9.3% | — |
| GPQA (HELM) | 59.4% | — |
Multilingual GLM-4.5-Air leads
GLM-4.5-Air: 49.4 (#130), Qwen2.5-Max: 48.3 (#140)
| Benchmark | GLM-4.5-Air | Qwen2.5-Max |
|---|---|---|
| LMArena Non-English | 1366 | 1352 |
| LMArena Chinese | 1427 | 1382 |
| LMArena French | 1399 | 1396 |
| LMArena German | 1376 | 1350 |
| LMArena Japanese | 1348 | 1299 |
| LMArena Korean | 1306 | 1304 |
| LMArena Russian | 1373 | 1353 |
| LMArena Spanish | 1385 | 1377 |
Instruction Following Qwen2.5-Max leads
GLM-4.5-Air: 69.8 (#165), Qwen2.5-Max: 71.5 (#147)
| Benchmark | GLM-4.5-Air | Qwen2.5-Max |
|---|---|---|
| LMArena Instruction Following | 1353 | 1335 |
| LiveBench Instruction Following | — | 75.3% |
| IFEval | 81.2% | — |
Long Context Too close to call
GLM-4.5-Air: 41.6 (#130), Qwen2.5-Max: 41.3 (#137)
| Benchmark | GLM-4.5-Air | Qwen2.5-Max |
|---|---|---|
| LMArena Longer Query | 1367 | 1358 |
Writing & Preference Too close to call
GLM-4.5-Air: 56.1 (#134), Qwen2.5-Max: 55.6 (#141)
| Benchmark | GLM-4.5-Air | Qwen2.5-Max |
|---|---|---|
| LMArena Text | 1384 | 1367 |
| LMArena Creative Writing | 1343 | 1339 |
| LMArena Multi-Turn | 1371 | 1364 |
| Short-Story Creative Writing | — | 72.9% |
| WildBench | 78.9% | — |
| LiveBench Language | — | 56.3% |
Frequently asked questions
Is GLM-4.5-Air better than Qwen2.5-Max?
Qwen2.5-Max is the stronger model overall, scoring 40.1 to 38.7 on the Noometry Index.
Is GLM-4.5-Air or Qwen2.5-Max better for coding?
Qwen2.5-Max scores higher on coding benchmarks: 41.2 versus 34.5 in the Noometry coding category.
How many benchmarks do GLM-4.5-Air and Qwen2.5-Max share?
17 benchmarks have published results for both models. GLM-4.5-Air has 27 scored results on Noometry and Qwen2.5-Max has 27.