Mixtral 8x7B Instruct is a pretrained generative Sparse Mixture of Experts, by Mistral AI, for chat and instruction use. Incorporates 8 experts (feed-forward networks) for a total of 47 billion...
Tested on 11 benchmarks with 57.8% average. Top scores: ARC AI2 (83.1%), HellaSwag (82.3%), TriviaQA (82.2%).
GPT-5.1-Codex-Mini scores 67.4 (101% as good) at $0.25/1M input · 54% cheaper
Grade school math word problems. 8,500 problems testing multi-step arithmetic reasoning. A foundational math benchmark.
Competition-level math from AMC, AIME, and olympiad problems. Level 5 is the hardest tier, requiring creative problem-solving.
AI2 Reasoning Challenge. Grade-school science questions requiring multi-step reasoning. Easy and Challenge sets test different difficulty levels.
Sentence completion requiring commonsense reasoning about physical and social situations. Tests real-world understanding.
Trivia questions sourced from trivia enthusiasts and quiz websites. Tests breadth of general knowledge.
- Typetext
- Context33K tokens (~16 books)
- ReleasedDec 2023
- LicenseOpen Source
- StatusActive
- Cost / Message~$0.002