Compare AI models
| Specifications | ||
ParametersThe learned values that shape how a model responds. B means billion and T means trillion. For mixture-of-experts models, the total count is larger than the number active for each token. Parameter count alone does not measure quality. | 32B | 9B/32B |
Context windowHow much information the model can work with in one request, measured in tokens — pieces of words or other data. This includes your question, attachments, conversation and reply. Limits can vary by model variant and provider. | 128k | 128k |
| Benchmarks | ||
LiveCodeBenchCompetitive coding — Coding problems published so recently the AI can't have seen them in training — a contamination-free test of raw programming skill. Higher is better. | 63.4% | 59.1% |
IFEvalAgentic tasks — following verifiable instructions in generated responses | — | 84.5% |
AIME 2024Reasoning — single-answer accuracy on the 2024 invitational mathematics exam without tools | — | 80.8% |
AIME 2025Reasoning — single-answer accuracy on the 2025 invitational mathematics exam without tools | — | 63.6% |
| Overview | ||
| Company | Qwen | Z.ai |
| Release date | Mar 6 2025 | Apr 14 2025 |
| Access | Open Weight | Open Weight |
| Model details | View model | View model |
Other comparisons
QwQ-32BvsClaude Fable 5.2GLM-Z1-0414vsClaude Fable 5.2QwQ-32BvsGPT-6.2 AstraGLM-Z1-0414vsGPT-6.2 AstraQwQ-32BvsGemini 4 HydrogenGLM-Z1-0414vsGemini 4 HydrogenQwQ-32BvsMuse EmberGLM-Z1-0414vsMuse EmberQwQ-32BvsGrok 4.7GLM-Z1-0414vsGrok 4.7QwQ-32BvsDeepSeek-V4.1-Flash-1017GLM-Z1-0414vsDeepSeek-V4.1-Flash-1017Frequently asked questions
QwQ-32B leads GLM-Z1-0414 on 1 of the 1 benchmark they both report (LiveCodeBench). QwQ-32B shipped 39 days before GLM-Z1-0414, so benchmark comparisons should account for the intervening progress.
QwQ-32B has 32B parameters, while GLM-Z1-0414 has 9B/32B. Context windows are 128k (QwQ-32B) vs 128k (GLM-Z1-0414).
On LiveCodeBench, QwQ-32B leads at 63.4% vs GLM-Z1-0414 at 59.1%.