Compare AI models
| Specifications | ||
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. | 32k | — |
| 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. | 45.1% | 72% |
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. | 81.2% | 81.5% |
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. | 81% | 87.6% |
MATHReasoning — accuracy on the original competition mathematics test set | — | 47.9% |
ARC-ChallengeReasoning — multiple-choice science questions from the AI2 Reasoning Challenge; unrelated to ARC-AGI | 94.2% | — |
HellaSwagReasoning — commonsense completion of short scenarios | 89.2% | — |
WinoGrandeReasoning — resolving ambiguous pronouns in context | 86.7% | — |
| Overview | ||
| Company | Mistral | Z.ai |
| Release date | Feb 26 2024 | Jan 16 2024 |
| Access | Closed | Closed |
| Model details | View model | View model |
Other comparisons
Mistral LargevsClaude Fable 5.2GLM-4vsClaude Fable 5.2Mistral LargevsGPT-6.2 AstraGLM-4vsGPT-6.2 AstraMistral LargevsGemini 4 HydrogenGLM-4vsGemini 4 HydrogenMistral LargevsMuse EmberGLM-4vsMuse EmberMistral LargevsGrok 4.7GLM-4vsGrok 4.7Mistral LargevsDeepSeek-V4.1-Flash-1017GLM-4vsDeepSeek-V4.1-Flash-1017Frequently asked questions
GLM-4 leads Mistral Large on 3 of the 3 benchmarks they both report (HumanEval, MMLU, GSM8K). GLM-4 shipped 41 days before Mistral Large, so benchmark comparisons should account for the intervening progress.
Published specifications for these two models are limited — see each model page for the latest details.
On HumanEval, GLM-4 leads at 72% vs Mistral Large at 45.1%. On MMLU, GLM-4 leads at 81.5% vs Mistral Large at 81.2%. On GSM8K, GLM-4 leads at 87.6% vs Mistral Large at 81%.