Milestone
Aug 2024
MMLU Pro Leaderboard
KB
Aug 20, 2024
Arx-0.3, our first engineering prototype, currently holds the top spot on the leading AI benchmark MMLU-Pro, ahead of OpenAI, Meta, Anthropic, and Google
Arx-0.3, our first engineering prototype, currently holds the top spot on the leading AI benchmark MMLU-Pro, ahead of OpenAI, Meta, Anthropic, and Google