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. | — | 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 |
| API pricingUSD per 1M tokens · lower wins | ||
Input priceWhat you pay for everything you send the model — your question, plus any documents or earlier conversation you include with it. | — | $0.1032B checkpoint |
Output priceWhat you pay for the text the model writes back. It is normally the dearer half: producing an answer costs more than reading one. | — | $0.10 |
| — | $25.00Z.ai list price | |
| Benchmarks | ||
SWE-Bench VerifiedCoding — Real coding tasks pulled from open-source projects — the AI has to find and fix actual bugs. A human-checked version of the original SWE-Bench. Higher is better. | 38% | 27.2% |
HumanEvalFunction synthesis — 164 small Python problems: the AI is given a function's description and has to write the working function. This was the coding benchmark of the GPT-3.5 and GPT-4 era, before the field moved to fixing real bugs in real repositories. Higher is better. | 88.6% | — |
IFEvalAgentic tasks — following verifiable instructions in generated responses | — | 87.6% |
MATH-500Reasoning — accuracy on the 500-problem MATH subset | 87.1% | — |
DROPReasoning — three-shot token F1 on questions requiring reasoning over paragraphs | 83.4 | — |
AIME 2024Reasoning — single-answer accuracy on the 2024 invitational mathematics exam without tools | 36.7% | — |
GPQA DiamondScience — Graduate-level science questions in biology, physics, and chemistry — hard enough that subject-matter PhDs score around 65%. Higher is better. | 69.5% | — |
SimpleQAKnowledge — accuracy on short, fact-seeking questions in the original SimpleQA set | 62.5% | — |
MMMLUKnowledge — average accuracy on multilingual translations of MMLU | 85.1% | — |
MMLUGeneral knowledge — A 57-subject multiple-choice exam — history, law, medicine, maths — that was the standard measure of how much a model knows from 2020 until roughly 2024, when frontier scores crowded into the high 80s and labs moved on to harder tests. The scores here were published years apart under different testing setups, so read them as a historical record rather than a like-for-like ranking. Higher is better. | 90.8% | — |
MGSMMultilingual math — solving grade-school word problems translated into multiple languages | 86.9% | — |
MMMUMultimodal — Tests the AI on understanding images and text together across many college subjects. Higher is better. | 74.4% | — |
| Overview | ||
| Company | OpenAI | Z.ai |
| Release date | Feb 27 2025 | Apr 14 2025 |
| Access | Closed | Open Weight |
| Model details | View model | View model |
Other comparisons
GPT-4.5vsClaude Fable 5.2GLM-4-0414vsClaude Fable 5.2GPT-4.5vsGemini 4 HydrogenGLM-4-0414vsGemini 4 HydrogenGPT-4.5vsMuse EmberGLM-4-0414vsMuse EmberGPT-4.5vsGrok 4.7GLM-4-0414vsGrok 4.7GPT-4.5vsDeepSeek-V4.1-Flash-1017GLM-4-0414vsDeepSeek-V4.1-Flash-1017GPT-4.5vsMistral Large 4GLM-4-0414vsMistral Large 4Frequently asked questions
GPT-4.5 leads GLM-4-0414 on 1 of the 1 benchmark they both report (SWE-Bench Verified). Only GLM-4-0414 has a verified first-party price for an available API: $0.10 per million input tokens and $0.10 per million output tokens. No currently available pay-as-you-go API rate is tracked for GPT-4.5. The listed GLM-4-0414 rates use the “32B checkpoint” pricing scope. GPT-4.5 shipped 46 days before GLM-4-0414, so benchmark comparisons should account for the intervening progress.
Context windows are 128k (GPT-4.5) vs 128k (GLM-4-0414). GPT-4.5 is closed, while GLM-4-0414 is open weight.
On SWE-Bench Verified, GPT-4.5 leads at 38% vs GLM-4-0414 at 27.2%.