Model comparison
GLM-5.2 vs QwQ-32B
GLM-5.2 is the stronger model overall, scoring 50.9 to 39.4 on the Noometry Index.
Last verified . 22 shared benchmarks.
Alibaba (Qwen)Summary
- They share 22 benchmarks with published results for both. GLM-5.2 scores higher in 7 categories and QwQ-32B in 1 category; 8 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where GLM-5.2 leads 57.1 to 37.2.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 86.4% for GLM-5.2 and 59.2% for QwQ-32B.
Side by side
| GLM-5.2 | QwQ-32B | |
|---|---|---|
| Provider | Z.ai (Zhipu) | Alibaba (Qwen) |
| Noometry Index | 50.9 | 39.4 |
| Released | 2026-06-13 | 2024-11-28 |
| Weights | Open | Open |
| Context window | 1M | — |
| Max output | 131K | — |
| Input $ / M tokens | $1.40 | — |
| Output $ / M tokens | $4.40 | — |
| Results tracked | 50 | 36 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding GLM-5.2 leads
GLM-5.2: 50.9 (#37), QwQ-32B: 34.9 (#220)
| Benchmark | GLM-5.2 | QwQ-32B |
|---|---|---|
| LMArena Coding | 1484 | 1333 |
| SWE-bench Verified | 78.7% | — |
| DeepSWE | 43.8% | — |
| FrontierCode | 24.5% | — |
| Aider Polyglot | — | 20.9% |
| LMArena WebDev | 1604 | — |
| SciCode | 50.5% | — |
| WeirdML | 70.1% | — |
| BigCodeBench Instruct | — | 44.6% |
| LiveBench Coding | — | 72.2% |
| BigCodeBench Complete | — | 54.4% |
| ALE-Bench | 1,047 | — |
Agentic & Tool Use Not comparable
GLM-5.2: 31.6 (#63), QwQ-32B: —
| Benchmark | GLM-5.2 | QwQ-32B |
|---|---|---|
| τ²-bench Banking | 37.1% | — |
| PostTrainBench | 31.7% | — |
| GBAEval | 0% | — |
| Vending-Bench 2 | 8,314 | — |
Reasoning GLM-5.2 leads
GLM-5.2: 42.1 (#46), QwQ-32B: 22.9 (#171)
| Benchmark | GLM-5.2 | QwQ-32B |
|---|---|---|
| Chess Puzzles | 21% | 5% |
| LMArena Hard Prompts | 1480 | 1326 |
| Epoch Capabilities Index | 151.76 | 137.6 |
| ARC-AGI-2 | 22.8% | — |
| SimpleBench | 58.8% | — |
| Kagi LLM Benchmark | 62.6% | — |
| NYT Connections (extended) | 74.3% | — |
| ARC-AGI-1 | 77% | — |
| CritPt | 20.9% | — |
| EBR-Bench | 9.5% | — |
| LiveBench Reasoning | — | 83.5% |
| Mystery Game Puzzles | 19% | — |
| DTBench | 93.6% | — |
| LiveBench Data Analysis | — | 65% |
| LMCA | 45.8% | — |
| Surface Evolver Bench | 55.6% | — |
| ForecastBench | — | 58.3 |
| LiveBench | — | 72% |
Math GLM-5.2 leads
GLM-5.2: 55.4 (#35), QwQ-32B: 36.2 (#123)
| Benchmark | GLM-5.2 | QwQ-32B |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 86.4% | 59.2% |
| LMArena Math | 1482 | 1359 |
| FrontierMath (Tiers 1-3) | 59.2% | — |
| FrontierMath Tier 4 | 29.3% | — |
| MathArena Final-Answer Competitions | 67.6% | — |
| ProofBench | 35% | — |
| LiveBench Math | — | 77.8% |
Knowledge GLM-5.2 leads
GLM-5.2: 57.1 (#36), QwQ-32B: 37.2 (#150)
| Benchmark | GLM-5.2 | QwQ-32B |
|---|---|---|
| GPQA Diamond | 91.9% | 65.3% |
| LMArena Expert | 1484 | 1323 |
| SimpleQA Verified | 34.2% | — |
| Confabulations | — | 15.6% |
Multilingual GLM-5.2 leads
GLM-5.2: 56.0 (#25), QwQ-32B: 45.0 (#171)
| Benchmark | GLM-5.2 | QwQ-32B |
|---|---|---|
| LMArena Non-English | 1459 | 1306 |
| LMArena Chinese | 1518 | 1378 |
| LMArena French | 1476 | 1337 |
| LMArena German | 1470 | 1313 |
| LMArena Japanese | 1451 | 1263 |
| LMArena Korean | 1445 | 1278 |
| LMArena Russian | 1467 | 1297 |
| LMArena Spanish | 1477 | 1353 |
Instruction Following GLM-5.2 leads
GLM-5.2: 77.1 (#32), QwQ-32B: 72.8 (#131)
| Benchmark | GLM-5.2 | QwQ-32B |
|---|---|---|
| LMArena Instruction Following | 1465 | 1297 |
| LiveBench Instruction Following | — | 81.8% |
Long Context QwQ-32B leads
GLM-5.2: 45.3 (#43), QwQ-32B: 49.0 (#11)
| Benchmark | GLM-5.2 | QwQ-32B |
|---|---|---|
| LMArena Longer Query | 1479 | 1308 |
| Fiction.LiveBench | — | 83.3% |
Writing & Preference GLM-5.2 leads
GLM-5.2: 70.7 (#20), QwQ-32B: 50.9 (#175)
| Benchmark | GLM-5.2 | QwQ-32B |
|---|---|---|
| LMArena Text | 1470 | 1329 |
| LMArena Creative Writing | 1465 | 1288 |
| EQ-Bench Creative Writing | 1757 | 1257 |
| LMArena Multi-Turn | 1468 | 1314 |
| Short-Story Creative Writing | — | 80.2% |
| EQ-Bench 4 | 1222 | — |
| LiveBench Language | — | 51.4% |
Frequently asked questions
Is GLM-5.2 better than QwQ-32B?
GLM-5.2 is the stronger model overall, scoring 50.9 to 39.4 on the Noometry Index.
Is GLM-5.2 or QwQ-32B better for coding?
GLM-5.2 scores higher on coding benchmarks: 50.9 versus 34.9 in the Noometry coding category.
How many benchmarks do GLM-5.2 and QwQ-32B share?
22 benchmarks have published results for both models. GLM-5.2 has 50 scored results on Noometry and QwQ-32B has 36.