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. | 1B/3B/11B/90B | 1.5B/4B |
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 | 8k |
| API pricingUSD per 1M tokens · lower wins | ||
Cheapest inputLowest input rate across every provider on OpenRouter, the lab included. The cheapest endpoint may run a quantised build or a shorter context — see "Available from" on the model page. | $0.027Cloudflare | — |
Cheapest outputLowest output rate across every provider on OpenRouter, the lab included. May come from a different provider than the cheapest input. | $0.201Cloudflare | — |
| $15.45Cloudflare | — | |
| Benchmarks | ||
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. | 86% | 54.84% |
MATHReasoning — accuracy on the original competition mathematics test set | 68% | — |
MGSMMultilingual math — solving grade-school word problems translated into multiple languages | 86.9% | — |
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. | — | 54.89% |
MathVistaMultimodal reasoning — mathematical reasoning about visual information | 57.3% | — |
MMMUMultimodal — Tests the AI on understanding images and text together across many college subjects. Higher is better. | 60.3% | — |
| Overview | ||
| Company | Meta | Z.ai |
| Release date | Sep 25 2024 | Nov 29 2024 |
| Access | Open Weight | Open Weight |
| Model details | View model | View model |
Other comparisons
LLaMA 3.2vsClaude Fable 5.2GLM-EdgevsClaude Fable 5.2LLaMA 3.2vsGPT-6.2 AstraGLM-EdgevsGPT-6.2 AstraLLaMA 3.2vsGemini 4 HydrogenGLM-EdgevsGemini 4 HydrogenLLaMA 3.2vsGrok 4.7GLM-EdgevsGrok 4.7LLaMA 3.2vsDeepSeek-V4.1-Flash-1017GLM-EdgevsDeepSeek-V4.1-Flash-1017LLaMA 3.2vsMistral Large 4GLM-EdgevsMistral Large 4Frequently asked questions
LLaMA 3.2 leads GLM-Edge on 1 of the 1 benchmark they both report (MMLU). LLaMA 3.2 shipped 65 days before GLM-Edge, so benchmark comparisons should account for the intervening progress.
LLaMA 3.2 has 1B/3B/11B/90B parameters, while GLM-Edge has 1.5B/4B. Context windows are 128k (LLaMA 3.2) vs 8k (GLM-Edge).
On MMLU, LLaMA 3.2 leads at 86% vs GLM-Edge at 54.84%.