Model comparison
GLM-4.6 vs Qwen2.5-Coder-32B
GLM-4.6 is the stronger model overall, scoring 40.9 to 32.9 on the Noometry Index.
Last verified . 13 shared benchmarks.
Alibaba (Qwen)Summary
- They share 13 benchmarks with published results for both. GLM-4.6 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-4.6 leads 61.3 to 41.8.
- The biggest single-benchmark swing is SWE-bench Verified (bash only): 55.4% for GLM-4.6 and 9% for Qwen2.5-Coder-32B.
- Qwen2.5-Coder-32B is cheaper at $0.66 / $1 per million input/output tokens, against $0.60 / $2.20 for GLM-4.6.
- GLM-4.6 accepts more context: 205K tokens versus 33K.
Side by side
| GLM-4.6 | Qwen2.5-Coder-32B | |
|---|---|---|
| Provider | Z.ai (Zhipu) | Alibaba (Qwen) |
| Noometry Index | 40.9 | 32.9 |
| Released | 2025-09-30 | 2024-09-18 |
| Weights | Open | Open |
| Context window | 205K | 33K |
| Max output | 131K | 29K |
| Input $ / M tokens | $0.60 | $0.66 |
| Output $ / M tokens | $2.20 | $1 |
| Results tracked | 29 | 31 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding GLM-4.6 leads
GLM-4.6: 39.9 (#137), Qwen2.5-Coder-32B: 22.4 (#328)
| Benchmark | GLM-4.6 | Qwen2.5-Coder-32B |
|---|---|---|
| SWE-bench Verified (bash only) | 55.4% | 9% |
| LMArena Coding | 1449 | 1276 |
| Aider Polyglot | — | 16.4% |
| LMArena WebDev | 1339 | — |
| SciCode | 38.4% | — |
| BigCodeBench Instruct | — | 49% |
| LiveBench Coding | — | 56.9% |
| BigCodeBench Complete | — | 58% |
| ALE-Bench | 340.82 | — |
| HumanEval+ | — | 87.2% |
| MBPP+ | — | 77% |
Agentic & Tool Use Not comparable
GLM-4.6: 32.1 (#60), Qwen2.5-Coder-32B: —
| Benchmark | GLM-4.6 | Qwen2.5-Coder-32B |
|---|---|---|
| Terminal-Bench | 24.5% | — |
| Berkeley Function Calling Leaderboard | 72.4% | — |
Reasoning GLM-4.6 leads
GLM-4.6: 23.1 (#168), Qwen2.5-Coder-32B: 20.4 (#220)
| Benchmark | GLM-4.6 | Qwen2.5-Coder-32B |
|---|---|---|
| LMArena Hard Prompts | 1440 | 1251 |
| Kagi LLM Benchmark | 47.4% | — |
| CritPt | 1.1% | — |
| LiveBench Reasoning | — | 42.1% |
| LiveBench Data Analysis | — | 49.9% |
| Epoch Capabilities Index | — | 119.41 |
| HellaSwag | — | 83% |
| LiveBench | — | 46.2% |
| WinoGrande | — | 80.8% |
Math GLM-4.6 leads
GLM-4.6: 36.4 (#115), Qwen2.5-Coder-32B: 30.8 (#203)
| Benchmark | GLM-4.6 | Qwen2.5-Coder-32B |
|---|---|---|
| LMArena Math | 1431 | 1251 |
| LiveBench Math | — | 46.6% |
| FrontierMath (Feb 2025 set) | 3.8% | — |
| FrontierMath Tier 4 (v1) | 2.1% | — |
| GSM8K | — | 93% |
Knowledge GLM-4.6 leads
GLM-4.6: 39.6 (#118), Qwen2.5-Coder-32B: 32.9 (#200)
| Benchmark | GLM-4.6 | Qwen2.5-Coder-32B |
|---|---|---|
| LMArena Expert | 1432 | 1221 |
| Vectara Hallucination Rate | 9.5% | — |
| ARC (AI2) Challenge | — | 70.5% |
| MMLU | — | 79.1% |
Multilingual GLM-4.6 leads
GLM-4.6: 53.6 (#62), Qwen2.5-Coder-32B: 38.0 (#230)
| Benchmark | GLM-4.6 | Qwen2.5-Coder-32B |
|---|---|---|
| LMArena Non-English | 1426 | 1205 |
| LMArena Chinese | 1500 | 1222 |
| LMArena Russian | 1418 | 1228 |
| LMArena French | 1459 | — |
| LMArena German | 1447 | — |
| LMArena Japanese | 1394 | — |
| LMArena Korean | 1401 | — |
| LMArena Spanish | 1436 | — |
Instruction Following GLM-4.6 leads
GLM-4.6: 74.5 (#93), Qwen2.5-Coder-32B: 61.6 (#240)
| Benchmark | GLM-4.6 | Qwen2.5-Coder-32B |
|---|---|---|
| LMArena Instruction Following | 1410 | 1223 |
| LiveBench Instruction Following | — | 58.7% |
Long Context GLM-4.6 leads
GLM-4.6: 43.4 (#91), Qwen2.5-Coder-32B: 37.9 (#204)
| Benchmark | GLM-4.6 | Qwen2.5-Coder-32B |
|---|---|---|
| LMArena Longer Query | 1423 | 1251 |
Writing & Preference GLM-4.6 leads
GLM-4.6: 61.3 (#86), Qwen2.5-Coder-32B: 41.8 (#235)
| Benchmark | GLM-4.6 | Qwen2.5-Coder-32B |
|---|---|---|
| LMArena Text | 1440 | 1230 |
| LMArena Creative Writing | 1411 | 1174 |
| LMArena Multi-Turn | 1427 | 1222 |
| EQ-Bench Creative Writing | 1411 | — |
| LiveBench Language | — | 23.3% |
Frequently asked questions
Is GLM-4.6 better than Qwen2.5-Coder-32B?
GLM-4.6 is the stronger model overall, scoring 40.9 to 32.9 on the Noometry Index.
Which is cheaper, GLM-4.6 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-4.6 lists at $0.60 and $2.20.
Is GLM-4.6 or Qwen2.5-Coder-32B better for coding?
GLM-4.6 scores higher on coding benchmarks: 39.9 versus 22.4 in the Noometry coding category.
Which has the bigger context window?
GLM-4.6 does, with 205K tokens against 33K.
How many benchmarks do GLM-4.6 and Qwen2.5-Coder-32B share?
13 benchmarks have published results for both models. GLM-4.6 has 29 scored results on Noometry and Qwen2.5-Coder-32B has 31.