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. | 70B | — |
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. | 16k | 128k |
| Benchmarks | ||
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. | 53% | 75.7% |
IFEvalAgentic tasks — following verifiable instructions in generated responses | — | 75.2% |
MATHReasoning — accuracy on the original competition mathematics test set | — | 57.9% |
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. | — | 81.9% |
GSM8KGrade-school math — Grade-school maths word problems that take a few steps of arithmetic to work through. It separated the models of 2022 and 2023 sharply, then saturated. One caveat on the historical numbers: OpenAI included part of the GSM8K training set in GPT-4's pre-training mix, so GPT-4's score is not a clean few-shot result. Higher is better. | — | 90.9% |
| Overview | ||
| Company | Meta | Z.ai |
| Release date | Jan 29 2024 | Jun 5 2024 |
| Access | Open Weight | Closed |
| Model details | View model | View model |
Other comparisons
Code Llama 70BvsClaude Fable 5.2GLM-4-AirvsClaude Fable 5.2Code Llama 70BvsGPT-6.2 AstraGLM-4-AirvsGPT-6.2 AstraCode Llama 70BvsGemini 4 HydrogenGLM-4-AirvsGemini 4 HydrogenCode Llama 70BvsGrok 4.7GLM-4-AirvsGrok 4.7Code Llama 70BvsDeepSeek-V4.1-Flash-1017GLM-4-AirvsDeepSeek-V4.1-Flash-1017Code Llama 70BvsMistral Large 4GLM-4-AirvsMistral Large 4Frequently asked questions
GLM-4-Air leads Code Llama 70B on 1 of the 1 benchmark they both report (HumanEval). Code Llama 70B shipped 128 days before GLM-4-Air, so benchmark comparisons should account for the intervening progress.
Context windows are 16k (Code Llama 70B) vs 128k (GLM-4-Air). Code Llama 70B is open weight, while GLM-4-Air is closed.
On HumanEval, GLM-4-Air leads at 75.7% vs Code Llama 70B at 53%.