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. | 7B/67B | 130B |
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. | 4k | — |
| These models have no shared benchmark scores. | ||
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. | 73.8% | — |
MATHReasoning — accuracy on the original competition mathematics test set | 32.6% | — |
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. | 71.1% | — |
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. | 84.1% | — |
Z-Bench (March 2023)Chinese-language evaluation — fully correct responses on ZhenFund’s 311-question evaluation of the March 2023 ChatGLM alpha | — | 40.2% |
| Overview | ||
| Company | DeepSeek | Z.ai |
| Release date | Nov 29 2023 | Mar 14 2023 |
| Access | Open Weight | Closed |
| Model details | View model | View model |
Other comparisons
DeepSeek-LLMvsClaude Fable 5.2ChatGLM-130BvsClaude Fable 5.2DeepSeek-LLMvsGPT-6.2 AstraChatGLM-130BvsGPT-6.2 AstraDeepSeek-LLMvsGemini 4 HydrogenChatGLM-130BvsGemini 4 HydrogenDeepSeek-LLMvsMuse EmberChatGLM-130BvsMuse EmberDeepSeek-LLMvsGrok 4.7ChatGLM-130BvsGrok 4.7DeepSeek-LLMvsMistral Large 4ChatGLM-130BvsMistral Large 4Frequently asked questions
DeepSeek-LLM and ChatGLM-130B don't publish scores on any of the same benchmarks, so there's no direct head-to-head comparison. ChatGLM-130B shipped 260 days before DeepSeek-LLM, so benchmark comparisons should account for the intervening progress.
DeepSeek-LLM has 7B/67B parameters, while ChatGLM-130B has 130B. DeepSeek-LLM is open weight, while ChatGLM-130B is closed.
Direct benchmark comparisons are unavailable — DeepSeek-LLM and ChatGLM-130B don't publish scores on any of the same benchmarks.