MiniMax-M1-40k
MiniMax-M1-40k is an AI model published by MiniMaxAI, released on 2025-06-16, for Reasoning model, with 456B parameters, and 1000K context length, requiring about 912GB storage, with a 96.00 score on MATH-500.
Data sourced primarily from official releases (GitHub, Hugging Face, papers), then benchmark leaderboards, then third-party evaluators. Learn about our data methodology
Model basics
Open source & experience
Official resources
API details
| Type | Condition | Input | Output |
|---|---|---|---|
| Text | - | $1.30/ 1M tokens | $2.20/ 1M tokens |
“—” means the modality is not billed in that direction, or the vendor has not published a price for it.
Benchmark Results
MiniMax-M1-40k currently shows benchmark results led by MMLU Pro (60 / 176, score 80.60), AIME 2024 (23 / 62, score 83.30), LiveCodeBench (109 / 250, score 65.70). This page also consolidates core specs, context limits, and API pricing so you can evaluate the model from benchmark results and deployment constraints together.
General Knowledge
3 evaluationsGeneral Evaluation
2 evaluationsCoding and Software Engineer
3 evaluationsMath and Reasoning
4 evaluationsAgent Level Benchmark
2 evaluationsPublisher
Model Overview
MiniMax-M1-40k is an AI model published by MiniMaxAI, released on 2025-06-16, for Reasoning model, with 456B parameters, and 1000K context length, requiring about 912GB storage, with a 96.00 score on MATH-500.
DataLearner on WeChat
Follow DataLearner on WeChat for AI model updates and research notes.
