Model comparison
GLM-5.1 vs Qwen2.5-Coder-32B
GLM-5.1 is the stronger model overall, scoring 47.8 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-5.1's lead doesn't matter for your workload.
Last verified . 13 shared benchmarks.
Summary
- They share 13 benchmarks with published results for both. GLM-5.1 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 coding, where GLM-5.1 leads 48.7 to 22.6.
- Qwen2.5-Coder-32B is cheaper at $0.66 / $1 per million input/output tokens, against $1.40 / $4.40 for GLM-5.1.
- GLM-5.1 accepts more context: 200K tokens versus 33K.
Side by side
| GLM-5.1 | Qwen2.5-Coder-32B | |
|---|---|---|
| Provider | Z.ai (Zhipu) | Alibaba (Qwen) |
| Noometry Index | 47.8 | 33.4 |
| Released | 2026-04-07 | 2024-09-18 |
| Weights | Open | Open |
| Context window | 200K | 33K |
| Max output | 131K | 29K |
| Input $ / M tokens | $1.40 | $0.66 |
| Output $ / M tokens | $4.40 | $1 |
| Results tracked | 41 | 31 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding GLM-5.1 leads
GLM-5.1: 48.7 (#55), Qwen2.5-Coder-32B: 22.6 (#333)
| Benchmark | GLM-5.1 | Qwen2.5-Coder-32B |
|---|---|---|
| LMArena Coding | 1485 | 1276 |
| SWE-bench Verified | 74.2% | — |
| SWE-bench Verified (bash only) | — | 9% |
| Aider Polyglot | — | 16.4% |
| LMArena WebDev | 1508 | — |
| SciCode | 43.8% | — |
| WeirdML | 57.1% | — |
| BigCodeBench Instruct | — | 49% |
| LiveBench Coding | — | 56.9% |
| BigCodeBench Complete | — | 58% |
| ALE-Bench | 887.1 | — |
| HumanEval+ | — | 87.2% |
| MBPP+ | — | 77% |
Agentic & Tool Use Not comparable
GLM-5.1: 24.9 (#113), Qwen2.5-Coder-32B: —
| Benchmark | GLM-5.1 | Qwen2.5-Coder-32B |
|---|---|---|
| APEX-Agents | 40.9% | — |
| ExploitBench | 18.1% | — |
| GBAEval | 0% | — |
| Vending-Bench 2 | 5,634 | — |
Reasoning GLM-5.1 leads
GLM-5.1: 39.1 (#60), Qwen2.5-Coder-32B: 21.2 (#225)
| Benchmark | GLM-5.1 | Qwen2.5-Coder-32B |
|---|---|---|
| LMArena Hard Prompts | 1472 | 1251 |
| Epoch Capabilities Index | 149.84 | 119.49 |
| SimpleBench | 55.1% | — |
| NYT Connections (extended) | 77.7% | — |
| CritPt | 4.6% | — |
| Chess Puzzles | 19% | — |
| Thematic Generalization | 69.8% | — |
| LiveBench Reasoning | — | 42.1% |
| LiveBench Data Analysis | — | 49.9% |
| HellaSwag | — | 83% |
| LiveBench | — | 46.2% |
| WinoGrande | — | 80.8% |
Math GLM-5.1 leads
GLM-5.1: 49.7 (#60), Qwen2.5-Coder-32B: 33.3 (#204)
| Benchmark | GLM-5.1 | Qwen2.5-Coder-32B |
|---|---|---|
| LMArena Math | 1473 | 1251 |
| FrontierMath (Tiers 1-3) | 36.8% | — |
| MathArena Final-Answer Competitions | 67.1% | — |
| OTIS Mock AIME 2024-2025 | 93.3% | — |
| ProofBench | 22.2% | — |
| LiveBench Math | — | 46.6% |
| FrontierMath (Feb 2025 set) | 33.4% | — |
| FrontierMath Tier 4 (v1) | 12.5% | — |
| GSM8K | — | 93% |
Knowledge GLM-5.1 leads
GLM-5.1: 54.9 (#50), Qwen2.5-Coder-32B: 33.4 (#203)
| Benchmark | GLM-5.1 | Qwen2.5-Coder-32B |
|---|---|---|
| LMArena Expert | 1476 | 1221 |
| GPQA Diamond | 89.9% | — |
| SimpleQA Verified | 34% | — |
| ARC (AI2) Challenge | — | 70.5% |
| MMLU | — | 79.1% |
Multilingual GLM-5.1 leads
GLM-5.1: 55.0 (#36), Qwen2.5-Coder-32B: 37.8 (#235)
| Benchmark | GLM-5.1 | Qwen2.5-Coder-32B |
|---|---|---|
| LMArena Non-English | 1447 | 1205 |
| LMArena Chinese | 1515 | 1222 |
| LMArena Russian | 1454 | 1228 |
| LMArena French | 1474 | — |
| LMArena German | 1465 | — |
| LMArena Japanese | 1434 | — |
| LMArena Korean | 1418 | — |
| LMArena Spanish | 1469 | — |
Instruction Following GLM-5.1 leads
GLM-5.1: 76.3 (#42), Qwen2.5-Coder-32B: 61.4 (#245)
| Benchmark | GLM-5.1 | Qwen2.5-Coder-32B |
|---|---|---|
| LMArena Instruction Following | 1451 | 1223 |
| LiveBench Instruction Following | — | 58.7% |
Long Context GLM-5.1 leads
GLM-5.1: 44.9 (#53), Qwen2.5-Coder-32B: 38.0 (#208)
| Benchmark | GLM-5.1 | Qwen2.5-Coder-32B |
|---|---|---|
| LMArena Longer Query | 1466 | 1251 |
Writing & Preference GLM-5.1 leads
GLM-5.1: 66.9 (#31), Qwen2.5-Coder-32B: 41.6 (#240)
| Benchmark | GLM-5.1 | Qwen2.5-Coder-32B |
|---|---|---|
| LMArena Text | 1461 | 1230 |
| LMArena Creative Writing | 1453 | 1174 |
| LMArena Multi-Turn | 1472 | 1222 |
| EQ-Bench Creative Writing | 1592 | — |
| LiveBench Language | — | 23.3% |
Frequently asked questions
Is GLM-5.1 better than Qwen2.5-Coder-32B?
GLM-5.1 is the stronger model overall, scoring 47.8 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-5.1's lead doesn't matter for your workload.
Which is cheaper, GLM-5.1 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-5.1 lists at $1.40 and $4.40.
Is GLM-5.1 or Qwen2.5-Coder-32B better for coding?
GLM-5.1 scores higher on coding benchmarks: 48.7 versus 22.6 in the Noometry coding category.
Which has the bigger context window?
GLM-5.1 does, with 200K tokens against 33K.
How many benchmarks do GLM-5.1 and Qwen2.5-Coder-32B share?
13 benchmarks have published results for both models. GLM-5.1 has 41 scored results on Noometry and Qwen2.5-Coder-32B has 31.