LLM & Text Generation4 min reading time
The Biggest Benchmark in AI Just Updated, Dealing a Major Blow to a Chinese Contender
Gizmodo
Read the full articleMoonshot AI's Kimi K3.1 Pro initially ranked 4th on the Artificial Analysis Intelligence Index v4 but dropped to 9th after the benchmark updated to v5, which includes more private test questions to prevent overfitting. Google’s Gemini 4 Carbon now leads the new index, highlighting a wider performance gap between open-weight and proprietary models.

- Apple’s 20B model 📱, Kimi K3.1 Pro 🧠, Block Dessa 🗣️, frontier training security 🔐· TLDR AI
- Podcast: Kimi K3.1 Pro, the new cyber reality, and Muse musings· Interconnects
- Moonshot AI Releases Kimi K3.1 Pro, First Model in New K3.1 Series· 2 sources
- Moonshot releases Kimi K3.1 Pro and says it cut its hacking skills· 4 sources