Model comparison
GLM-5.2 vs Qwen2.5-Coder-32B
GLM-5.2 is the stronger model overall, scoring 51.1 to 33.4 on the Noometry Index. Qwen2.5-Coder-32B costs 2.9× less per token, which makes it the better buy when GLM-5.2's lead doesn't matter for your workload.
Last verified . 13 shared benchmarks.
Alibaba (Qwen)Summary
- They share 13 benchmarks with published results for both. GLM-5.2 scores higher in 8 categories and Qwen2.5-Coder-32B in 0 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where GLM-5.2 leads 70.4 to 41.6.
- Qwen2.5-Coder-32B is cheaper at $0.66 / $1 per million input/output tokens, against $1.40 / $4.40 for GLM-5.2.
- GLM-5.2 accepts more context: 1M tokens versus 33K.
Side by side
| GLM-5.2 | Qwen2.5-Coder-32B | |
|---|---|---|
| Provider | Z.ai (Zhipu) | Alibaba (Qwen) |
| Noometry Index | 51.1 | 33.4 |
| Released | 2026-06-13 | 2024-09-18 |
| Weights | Open | Open |
| Context window | 1M | 33K |
| Max output | 131K | 29K |
| Input $ / M tokens | $1.40 | $0.66 |
| Output $ / M tokens | $4.40 | $1 |
| Results tracked | 51 | 31 |
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), Qwen2.5-Coder-32B: 22.6 (#333)
| Benchmark | GLM-5.2 | Qwen2.5-Coder-32B |
|---|---|---|
| LMArena Coding | 1485 | 1276 |
| SWE-bench Verified | 78.7% | — |
| DeepSWE | 43.8% | — |
| FrontierCode | 24.5% | — |
| SWE-bench Verified (bash only) | — | 9% |
| Aider Polyglot | — | 16.4% |
| LMArena WebDev | 1603 | — |
| SciCode | 50.5% | — |
| WeirdML | 70.1% | — |
| BigCodeBench Instruct | — | 49% |
| LiveBench Coding | — | 56.9% |
| BigCodeBench Complete | — | 58% |
| ALE-Bench | 1,047 | — |
| HumanEval+ | — | 87.2% |
| MBPP+ | — | 77% |
Agentic & Tool Use Not comparable
GLM-5.2: 32.4 (#63), Qwen2.5-Coder-32B: —
| Benchmark | GLM-5.2 | Qwen2.5-Coder-32B |
|---|---|---|
| APEX-Agents | 45.2% | — |
| 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), Qwen2.5-Coder-32B: 21.2 (#225)
| Benchmark | GLM-5.2 | Qwen2.5-Coder-32B |
|---|---|---|
| LMArena Hard Prompts | 1480 | 1251 |
| Epoch Capabilities Index | 151.78 | 119.49 |
| 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% | — |
| Chess Puzzles | 21% | — |
| EBR-Bench | 9.5% | — |
| LiveBench Reasoning | — | 42.1% |
| Mystery Game Puzzles | 19% | — |
| DTBench | 93.6% | — |
| LiveBench Data Analysis | — | 49.9% |
| LMCA | 45.8% | — |
| Surface Evolver Bench | 55.6% | — |
| HellaSwag | — | 83% |
| LiveBench | — | 46.2% |
| WinoGrande | — | 80.8% |
Math GLM-5.2 leads
GLM-5.2: 55.7 (#43), Qwen2.5-Coder-32B: 33.3 (#204)
| Benchmark | GLM-5.2 | Qwen2.5-Coder-32B |
|---|---|---|
| LMArena Math | 1482 | 1251 |
| FrontierMath (Tiers 1-3) | 59.2% | — |
| FrontierMath Tier 4 | 29.3% | — |
| MathArena Final-Answer Competitions | 67.6% | — |
| OTIS Mock AIME 2024-2025 | 86.4% | — |
| ProofBench | 35% | — |
| LiveBench Math | — | 46.6% |
| GSM8K | — | 93% |
Knowledge GLM-5.2 leads
GLM-5.2: 57.1 (#40), Qwen2.5-Coder-32B: 33.4 (#203)
| Benchmark | GLM-5.2 | Qwen2.5-Coder-32B |
|---|---|---|
| LMArena Expert | 1486 | 1221 |
| GPQA Diamond | 91.9% | — |
| SimpleQA Verified | 34.2% | — |
| ARC (AI2) Challenge | — | 70.5% |
| MMLU | — | 79.1% |
Multilingual GLM-5.2 leads
GLM-5.2: 55.8 (#26), Qwen2.5-Coder-32B: 37.8 (#235)
| Benchmark | GLM-5.2 | Qwen2.5-Coder-32B |
|---|---|---|
| LMArena Non-English | 1459 | 1205 |
| LMArena Chinese | 1519 | 1222 |
| LMArena Russian | 1466 | 1228 |
| LMArena French | 1479 | — |
| LMArena German | 1468 | — |
| LMArena Japanese | 1451 | — |
| LMArena Korean | 1445 | — |
| LMArena Spanish | 1477 | — |
Instruction Following GLM-5.2 leads
GLM-5.2: 76.9 (#34), Qwen2.5-Coder-32B: 61.4 (#245)
| Benchmark | GLM-5.2 | Qwen2.5-Coder-32B |
|---|---|---|
| LMArena Instruction Following | 1465 | 1223 |
| LiveBench Instruction Following | — | 58.7% |
Long Context GLM-5.2 leads
GLM-5.2: 45.3 (#43), Qwen2.5-Coder-32B: 38.0 (#208)
| Benchmark | GLM-5.2 | Qwen2.5-Coder-32B |
|---|---|---|
| LMArena Longer Query | 1479 | 1251 |
Writing & Preference GLM-5.2 leads
GLM-5.2: 70.4 (#21), Qwen2.5-Coder-32B: 41.6 (#240)
| Benchmark | GLM-5.2 | Qwen2.5-Coder-32B |
|---|---|---|
| LMArena Text | 1470 | 1230 |
| LMArena Creative Writing | 1462 | 1174 |
| LMArena Multi-Turn | 1469 | 1222 |
| EQ-Bench Creative Writing | 1757 | — |
| EQ-Bench 4 | 1222 | — |
| LiveBench Language | — | 23.3% |
Frequently asked questions
Is GLM-5.2 better than Qwen2.5-Coder-32B?
GLM-5.2 is the stronger model overall, scoring 51.1 to 33.4 on the Noometry Index. Qwen2.5-Coder-32B costs 2.9× 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 Qwen2.5-Coder-32B?
Qwen2.5-Coder-32B is cheaper. It lists at $0.66 per million input tokens and $1 per million output tokens; GLM-5.2 lists at $1.40 and $4.40.
Is GLM-5.2 or Qwen2.5-Coder-32B better for coding?
GLM-5.2 scores higher on coding benchmarks: 51.3 versus 22.6 in the Noometry coding category.
Which has the bigger context window?
GLM-5.2 does, with 1M tokens against 33K.
How many benchmarks do GLM-5.2 and Qwen2.5-Coder-32B share?
13 benchmarks have published results for both models. GLM-5.2 has 51 scored results on Noometry and Qwen2.5-Coder-32B has 31.