Unverified50% confidenceBenchmarkExact time
Liquid AI's 3B action model achieved an average score of 82.9 on public benchmarks.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
10/10/2026
First Seen
Valid until: 1/8/2027
Sources
Related Entities
Related Claims
UnverifiedLiquid AI released a new generation of open-weight action models, including an approximately 3B parameter version and an Omni 600M version.76% similarUnverifiedLiquid AI has expanded its D1 decision model with visual capabilities, enabling it to accept images, text, or both, and return probabilities for yes/no judgments, multiple-choice, or scoring questions.75% similarUnverifiedA common characteristic of real cases of AI-assisted scientific discovery is that AI outputs specific predictions that can be directly tested by experiments and are verified through wet-lab experiments by independent laboratories.67% similarUnverifiedAn AI agent's confidence score is calculated by aggregating the probability distribution of output tokens from large language models (such as average log probability or entropy).66% similarUnverifiedThe principle of the AI judge mechanism is to input the image under evaluation into a language-vision multimodal model and require the model to output a written assessment and a quantified score based on given criteria.65% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/994993API
curl https://kongchang.com/api/v1/knowledge/claims/994993MCP
get_claim(id=994993)