Llama-4-Behemoth-17B-128E-Instruct
Llama-4-Behemoth-17B-128E-Instruct is an AI model published by Facebook AI Research Lab, released on 2025-04-05, for Multimodal model, with 2T parameters, and 1000K context length, requiring about 4000GB storage, 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 (53 / 133, score 82.20), MATH-500 (25 / 44, score 95), GPQA Diamond (142 / 226, score 73.70). This page also consolidates core specs, context limits, and API pricing so you can evaluate the model from benchmark results and deployment constraints together.
Compare 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 Research Lab, released on 2025-04-05, for Multimodal model, with 2T parameters, and 1000K context length, requiring about 4000GB storage, with a 95.00 score on MATH-500.
DataLearner on WeChat
Follow DataLearner on WeChat for AI model updates and research notes.
