Data as of Jul 25, 2026 · Based on 2,718,867 AI responses across 9,511 prompts · See how Parse measures this
Mistral 8B Instructhuggingface.co · Low evidenceMistral AI's Ministral 8B Instruct is a dense transformer language model with 8 billion parameters, optimized for on-device and edge computing with a 128k context window. It outperforms similar-sized models on benchmarks for knowledge, code, math, and multilingual tasks, supporting function calling and the V3 Tekken tokenizer.
Parse Score