Unverified50% confidenceFactExact time
The world model was trained on more than 50,000 real coding agent run records from SWE-bench Verified, spanning 25 different models.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
9/20/2026
First Seen
Valid until: 12/19/2026
Sources
Related Entities
Related Claims
UnverifiedxAI has built the Colossus 2000MW-class training cluster and is training Block5 versions with 6 trillion and 12 trillion parameters.66% similarUnverifiedA 70-billion-parameter model corresponds to approximately 1.4 trillion training tokens under the Chinchilla optimum65% similarUnverifiedCOCO 数据集包含约12万张训练图像、80个类别、超过150万个目标实例，由微软研究院发布63% similarUnverified训练与美国同等规模模型需要五万张顶级英伟达卡或二十万张华为95063% similarVerifiedThe MNIST dataset contains 60,000 training images and 10,000 test images, each a 28×28 pixel grayscale image of a handwritten digit.62% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/936633API
curl https://kongchang.com/api/v1/knowledge/claims/936633MCP
get_claim(id=936633)