Model comparison
GLM-5.2 vs Qwen3 32B
GLM-5.2 is the stronger model overall, scoring 51.1 to 39.2 on the Noometry Index. Qwen3 32B costs 1.8× less per token, which makes it the better buy when GLM-5.2's lead doesn't matter for your workload.
Last verified . 22 shared benchmarks.
Alibaba (Qwen)Summary
- They share 22 benchmarks with published results for both. GLM-5.2 scores higher in 8 categories and Qwen3 32B in 1 category; 8 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where GLM-5.2 leads 42.3 to 20.2.
- The biggest single-benchmark swing is LMCA: 45.8% for GLM-5.2 and 17.3% for Qwen3 32B.
- Qwen3 32B is cheaper at $0.70 / $2.80 per million input/output tokens, against $1.40 / $4.40 for GLM-5.2.
- GLM-5.2 accepts more context: 1M tokens versus 131K.
Side by side
| GLM-5.2 | Qwen3 32B | |
|---|---|---|
| Provider | Z.ai (Zhipu) | Alibaba (Qwen) |
| Noometry Index | 51.1 | 39.2 |
| Released | 2026-06-13 | 2025-04 |
| Weights | Open | Open |
| Context window | 1M | 131K |
| Max output | 131K | 16K |
| Input $ / M tokens | $1.40 | $0.70 |
| Output $ / M tokens | $4.40 | $2.80 |
| Results tracked | 51 | 26 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding GLM-5.2 leads
GLM-5.2: 51.3 (#41), Qwen3 32B: 37.7 (#190)
| Benchmark | GLM-5.2 | Qwen3 32B |
|---|---|---|
| SciCode | 50.5% | 35.4% |
| LMArena Coding | 1485 | 1358 |
| SWE-bench Verified | 78.7% | — |
| DeepSWE | 43.8% | — |
| FrontierCode | 24.5% | — |
| Aider Polyglot | — | 40% |
| LMArena WebDev | 1603 | — |
| WeirdML | 70.1% | — |
| ALE-Bench | 1,047 | — |
Agentic & Tool Use Too close to call
GLM-5.2: 32.4 (#63), Qwen3 32B: 32.6 (#62)
| Benchmark | GLM-5.2 | Qwen3 32B |
|---|---|---|
| APEX-Agents | 45.2% | — |
| Berkeley Function Calling Leaderboard | — | 48.7% |
| τ²-bench Banking | 37.1% | — |
| PostTrainBench | 31.7% | — |
| GBAEval | 0% | — |
| Vending-Bench 2 | 8,314 | — |
Reasoning GLM-5.2 leads
GLM-5.2: 42.3 (#52), Qwen3 32B: 20.2 (#241)
| Benchmark | GLM-5.2 | Qwen3 32B |
|---|---|---|
| Kagi LLM Benchmark | 62.6% | 54.9% |
| CritPt | 20.9% | 0.3% |
| Chess Puzzles | 21% | 5% |
| LMArena Hard Prompts | 1480 | 1334 |
| DTBench | 93.6% | 67.5% |
| LMCA | 45.8% | 17.3% |
| Epoch Capabilities Index | 151.78 | 138.51 |
| ARC-AGI-2 | 22.8% | — |
| SimpleBench | 58.8% | — |
| NYT Connections (extended) | 74.3% | — |
| ARC-AGI-1 | 77% | — |
| EBR-Bench | 9.5% | — |
| Mystery Game Puzzles | 19% | — |
| Surface Evolver Bench | 55.6% | — |
Math GLM-5.2 leads
GLM-5.2: 55.7 (#43), Qwen3 32B: 39.7 (#99)
| Benchmark | GLM-5.2 | Qwen3 32B |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 86.4% | 66.9% |
| LMArena Math | 1482 | 1399 |
| FrontierMath (Tiers 1-3) | 59.2% | — |
| FrontierMath Tier 4 | 29.3% | — |
| MathArena Final-Answer Competitions | 67.6% | — |
| ProofBench | 35% | — |
Knowledge GLM-5.2 leads
GLM-5.2: 57.1 (#40), Qwen3 32B: 40.0 (#125)
| Benchmark | GLM-5.2 | Qwen3 32B |
|---|---|---|
| GPQA Diamond | 91.9% | 65.7% |
| LMArena Expert | 1486 | 1362 |
| SimpleQA Verified | 34.2% | — |
| Vectara Hallucination Rate | — | 5.9% |
Multilingual GLM-5.2 leads
GLM-5.2: 55.8 (#26), Qwen3 32B: 45.6 (#167)
| Benchmark | GLM-5.2 | Qwen3 32B |
|---|---|---|
| LMArena Non-English | 1459 | 1317 |
| LMArena Chinese | 1519 | 1357 |
| LMArena German | 1468 | 1341 |
| LMArena Russian | 1466 | 1311 |
| LMArena French | 1479 | — |
| LMArena Japanese | 1451 | — |
| LMArena Korean | 1445 | — |
| LMArena Spanish | 1477 | — |
Instruction Following GLM-5.2 leads
GLM-5.2: 76.9 (#34), Qwen3 32B: 68.9 (#179)
| Benchmark | GLM-5.2 | Qwen3 32B |
|---|---|---|
| LMArena Instruction Following | 1465 | 1305 |
Long Context GLM-5.2 leads
GLM-5.2: 45.3 (#43), Qwen3 32B: 43.8 (#87)
| Benchmark | GLM-5.2 | Qwen3 32B |
|---|---|---|
| LMArena Longer Query | 1479 | 1327 |
| Fiction.LiveBench | — | 74.2% |
Writing & Preference GLM-5.2 leads
GLM-5.2: 70.4 (#21), Qwen3 32B: 52.9 (#163)
| Benchmark | GLM-5.2 | Qwen3 32B |
|---|---|---|
| LMArena Text | 1470 | 1340 |
| LMArena Creative Writing | 1462 | 1297 |
| LMArena Multi-Turn | 1469 | 1331 |
| EQ-Bench Creative Writing | 1757 | — |
| EQ-Bench 4 | 1222 | — |
Frequently asked questions
Is GLM-5.2 better than Qwen3 32B?
GLM-5.2 is the stronger model overall, scoring 51.1 to 39.2 on the Noometry Index. Qwen3 32B costs 1.8× less per token, which makes it the better buy when GLM-5.2's lead doesn't matter for your workload.
Which is cheaper, GLM-5.2 or Qwen3 32B?
Qwen3 32B is cheaper. It lists at $0.70 per million input tokens and $2.80 per million output tokens; GLM-5.2 lists at $1.40 and $4.40.
Is GLM-5.2 or Qwen3 32B better for coding?
GLM-5.2 scores higher on coding benchmarks: 51.3 versus 37.7 in the Noometry coding category.
Which has the bigger context window?
GLM-5.2 does, with 1M tokens against 131K.
How many benchmarks do GLM-5.2 and Qwen3 32B share?
22 benchmarks have published results for both models. GLM-5.2 has 51 scored results on Noometry and Qwen3 32B has 26.