Model comparison
GLM-4.5 vs QwQ-32B
GLM-4.5 is the stronger model overall, scoring 41.4 to 39.4 on the Noometry Index.
Last verified . 21 shared benchmarks.
Alibaba (Qwen)Summary
- They share 21 benchmarks with published results for both. GLM-4.5 scores higher in 6 categories and QwQ-32B in 2 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in long context, where QwQ-32B leads 49.0 to 38.2.
- The biggest single-benchmark swing is Fiction.LiveBench: 58.3% for GLM-4.5 and 83.3% for QwQ-32B.
Side by side
| GLM-4.5 | QwQ-32B | |
|---|---|---|
| Provider | Z.ai (Zhipu) | Alibaba (Qwen) |
| Noometry Index | 41.4 | 39.4 |
| Released | 2025-07-27 | 2024-11-28 |
| Weights | Open | Open |
| Context window | 131K | — |
| Max output | 98K | — |
| Input $ / M tokens | $0.60 | — |
| Output $ / M tokens | $2.20 | — |
| Results tracked | 27 | 36 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding GLM-4.5 leads
GLM-4.5: 41.1 (#121), QwQ-32B: 34.9 (#220)
| Benchmark | GLM-4.5 | QwQ-32B |
|---|---|---|
| LMArena Coding | 1434 | 1333 |
| SWE-bench Verified (bash only) | 54.2% | — |
| Aider Polyglot | — | 20.9% |
| WeirdML | 40.6% | — |
| BigCodeBench Instruct | — | 44.6% |
| LiveBench Coding | — | 72.2% |
| BigCodeBench Complete | — | 54.4% |
| ALE-Bench | 344.82 | — |
| AlgoTune | 1.52 | — |
Reasoning GLM-4.5 leads
GLM-4.5: 27.7 (#99), QwQ-32B: 22.9 (#171)
| Benchmark | GLM-4.5 | QwQ-32B |
|---|---|---|
| LMArena Hard Prompts | 1430 | 1326 |
| Kagi LLM Benchmark | 57.9% | — |
| Chess Puzzles | — | 5% |
| LiveBench Reasoning | — | 83.5% |
| LiveBench Data Analysis | — | 65% |
| Epoch Capabilities Index | — | 137.6 |
| ForecastBench | — | 58.3 |
| LiveBench | — | 72% |
Math Too close to call
GLM-4.5: 36.3 (#119), QwQ-32B: 36.2 (#123)
| Benchmark | GLM-4.5 | QwQ-32B |
|---|---|---|
| LMArena Math | 1427 | 1359 |
| OTIS Mock AIME 2024-2025 | — | 59.2% |
| LiveBench Math | — | 77.8% |
Knowledge QwQ-32B leads
GLM-4.5: 35.5 (#172), QwQ-32B: 37.2 (#150)
| Benchmark | GLM-4.5 | QwQ-32B |
|---|---|---|
| Confabulations | 11.3% | 15.6% |
| LMArena Expert | 1433 | 1323 |
| GPQA Diamond | — | 65.3% |
| Humanity's Last Exam | 8.3% | — |
Multilingual GLM-4.5 leads
GLM-4.5: 53.0 (#74), QwQ-32B: 45.0 (#171)
| Benchmark | GLM-4.5 | QwQ-32B |
|---|---|---|
| LMArena Non-English | 1417 | 1306 |
| LMArena Chinese | 1465 | 1378 |
| LMArena French | 1423 | 1337 |
| LMArena German | 1406 | 1313 |
| LMArena Japanese | 1416 | 1263 |
| LMArena Korean | 1382 | 1278 |
| LMArena Russian | 1414 | 1297 |
| LMArena Spanish | 1454 | 1353 |
Instruction Following GLM-4.5 leads
GLM-4.5: 74.3 (#100), QwQ-32B: 72.8 (#131)
| Benchmark | GLM-4.5 | QwQ-32B |
|---|---|---|
| LMArena Instruction Following | 1405 | 1297 |
| LiveBench Instruction Following | — | 81.8% |
Long Context QwQ-32B leads
GLM-4.5: 38.2 (#196), QwQ-32B: 49.0 (#11)
| Benchmark | GLM-4.5 | QwQ-32B |
|---|---|---|
| Fiction.LiveBench | 58.3% | 83.3% |
| LMArena Longer Query | 1413 | 1308 |
Writing & Preference GLM-4.5 leads
GLM-4.5: 57.7 (#121), QwQ-32B: 50.9 (#175)
| Benchmark | GLM-4.5 | QwQ-32B |
|---|---|---|
| LMArena Text | 1430 | 1329 |
| LMArena Creative Writing | 1395 | 1288 |
| Short-Story Creative Writing | 73.4% | 80.2% |
| EQ-Bench Creative Writing | 1343 | 1257 |
| LMArena Multi-Turn | 1415 | 1314 |
| LiveBench Language | — | 51.4% |
Frequently asked questions
Is GLM-4.5 better than QwQ-32B?
GLM-4.5 is the stronger model overall, scoring 41.4 to 39.4 on the Noometry Index.
Is GLM-4.5 or QwQ-32B better for coding?
GLM-4.5 scores higher on coding benchmarks: 41.1 versus 34.9 in the Noometry coding category.
How many benchmarks do GLM-4.5 and QwQ-32B share?
21 benchmarks have published results for both models. GLM-4.5 has 27 scored results on Noometry and QwQ-32B has 36.