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. | 3B | 6B |
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. | 256k | 8k |
| 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. | $0.10 | — |
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 | — |
Cached input priceA reduced rate for text you send over and over. If every request starts with the same instructions or the same document, the provider keeps a copy ready and charges less to read it again. | $0.01 | — |
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. | $0.10Mistral | — |
Cheapest outputLowest output rate across every provider on OpenRouter, the lab included. May come from a different provider than the cheapest input. | $0.10Mistral | — |
| $25.00Mistral list price | — | |
| Benchmarks | ||
MATHReasoning — accuracy on the original competition mathematics test set | 83% | 25.7% |
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. | — | 58.5% |
HellaSwagReasoning — commonsense completion of short scenarios | — | 79.7% |
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. | — | 61.4% |
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. | — | 72.3% |
| Overview | ||
| Company | Mistral | Z.ai |
| Release date | Dec 2 2025 | Oct 27 2023 |
| Access | Open Weight | Open Weight |
| Model details | View model | View model |
Other comparisons
Ministral 3 3B-25-12vsClaude Fable 5.2ChatGLM3-6BvsClaude Fable 5.2Ministral 3 3B-25-12vsGPT-6.2 AstraChatGLM3-6BvsGPT-6.2 AstraMinistral 3 3B-25-12vsGemini 4 HydrogenChatGLM3-6BvsGemini 4 HydrogenMinistral 3 3B-25-12vsMuse EmberChatGLM3-6BvsMuse EmberMinistral 3 3B-25-12vsGrok 4.7ChatGLM3-6BvsGrok 4.7Ministral 3 3B-25-12vsDeepSeek-V4.1-Flash-1017ChatGLM3-6BvsDeepSeek-V4.1-Flash-1017Frequently asked questions
Ministral 3 3B-25-12 leads ChatGLM3-6B on 1 of the 1 benchmark they both report (MATH). Only Ministral 3 3B-25-12 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 ChatGLM3-6B. ChatGLM3-6B shipped 767 days before Ministral 3 3B-25-12, so benchmark comparisons should account for the intervening progress.
Ministral 3 3B-25-12 has 3B parameters, while ChatGLM3-6B has 6B. Context windows are 256k (Ministral 3 3B-25-12) vs 8k (ChatGLM3-6B).
On MATH, Ministral 3 3B-25-12 leads at 83% vs ChatGLM3-6B at 25.7%.