← Back to live feed · 1 stories across 1 day

Sunday, Jul 19, 2026

1 story
1
Kimi K3 Scores 85% on Vibe Code Bench to Rank Second in Open Model Coding Tests↩︎
topics 🤖 AI tags AIAI ModelsAI ResearchAI Open Source keywords

Kimi K3 secured second place on the in-house Vibe Code Bench with an 85% score and demonstrated top-tier cybersecurity capabilities in independent evaluations, positioning the 2.8 trillion-parameter model as a leading open-weight frontier system.

The Vibe Code Bench measures end-to-end task completion, while separate internal security tests align the model's performance with major U.S. rivals. The results expand earlier coverage of the model's launch, adding verified domain-specific benchmarks to the ongoing competition in large language models.

You're reading an older version of the story.
Continues from Saturday, Jul 18
Moonshot Launches Kimi K3, a 2.8 Trillion Parameter Model Ranking Third to Fable and GPT-5.6
121 tweets • 46 sources
See all 123 tweets →