Llama-4-Behemoth-17B-128E-Instruct
Llama-4-Behemoth-17B-128E-Instruct is an AI model published by Facebook AI研究实验室, released on 2025-04-05, for Multimodal model, with 2T parameters, and 1000K context length, requiring about 4000GB storage, under the Llama4 License license, with a 95.00 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
Benchmark Results
Llama 4 Behemoth Instruct currently shows benchmark results led by MMLU Pro (49 / 126, score 82.20), GPQA Diamond (98 / 179, score 73.70), MATH-500 (25 / 44, score 95). 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
2 evaluationsCompare with other models
No curated comparisons for this model yet.
Want a custom combination? Open the compare tool
Publisher
Model Overview
Llama-4-Behemoth-17B-128E-Instruct is an AI model published by Facebook AI研究实验室, released on 2025-04-05, for Multimodal model, with 2T parameters, and 1000K context length, requiring about 4000GB storage, under the Llama4 License license, with a 95.00 score on MATH-500.
DataLearner on WeChat
Follow DataLearner on WeChat for AI model updates and research notes.
