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. | 141B | 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. | 64k | — |
| 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. | $2.00Mistral | — |
Cheapest outputLowest output rate across every provider on OpenRouter, the lab included. May come from a different provider than the cheapest input. | $6.00Mistral | — |
| $700Mistral · zdr | — | |
| 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. | 45.1% | — |
ARC-ChallengeReasoning — multiple-choice science questions from the AI2 Reasoning Challenge; unrelated to ARC-AGI | 91.3% | — |
HellaSwagReasoning — commonsense completion of short scenarios | 88.5% | — |
WinoGrandeReasoning — resolving ambiguous pronouns in context | 84.7% | — |
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. | 77.75% | — |
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. | 78.6% | — |
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 | Mistral | Z.ai |
| Release date | Apr 10 2024 | Mar 14 2023 |
| Access | Open Weight | Closed |
| Model details | View model | View model |
Other comparisons
Mixtral 8×22BvsClaude Fable 5.2ChatGLM-130BvsClaude Fable 5.2Mixtral 8×22BvsGPT-6.2 AstraChatGLM-130BvsGPT-6.2 AstraMixtral 8×22BvsGemini 4 HydrogenChatGLM-130BvsGemini 4 HydrogenMixtral 8×22BvsMuse EmberChatGLM-130BvsMuse EmberMixtral 8×22BvsGrok 4.7ChatGLM-130BvsGrok 4.7Mixtral 8×22BvsDeepSeek-V4.1-Flash-1017ChatGLM-130BvsDeepSeek-V4.1-Flash-1017Frequently asked questions
Mixtral 8×22B 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 393 days before Mixtral 8×22B, so benchmark comparisons should account for the intervening progress.
Mixtral 8×22B has 141B parameters, while ChatGLM-130B has 130B. Mixtral 8×22B is open weight, while ChatGLM-130B is closed.
Direct benchmark comparisons are unavailable — Mixtral 8×22B and ChatGLM-130B don't publish scores on any of the same benchmarks.