Expired50% confidenceBenchmarkExact time
In the test, the cache hit rates for Ollama and OpenCode Go were 97.2% and 99.5%, respectively.
1
Sources
50%
Confidence
Short-term (~14 days)
Relevance
9/21/2026
First Seen
Valid until: 10/5/2026(expired)
Sources
Related Entities
Related Claims
UnverifiedAccording to official benchmark data from OpenViking, the reduction in input tokens ranges from 34% to 91%.64% similarUnverifiedIn the benchmark, using the open-source model GLM with TrueForge reduced costs by as much as 75% while maintaining accuracy.64% similarUnverifiedIn the controlled test, the cache hit rate increased from 76.1% to 85.4%.63% similarUnverifiedIn the same reproduction experiment, ResNet-20 achieved a test accuracy of 90.4% and ResNet-56 achieved a test accuracy of 91.7%, with training accuracies of 97.4% and 99.0% respectively.62% similarUnverifiedThe framework's prediction intervals achieve empirical coverage rates of 0.533, 0.831, and 0.958 at nominal confidence levels of 50%, 80%, and 95%, respectively.62% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/939357API
curl https://kongchang.com/api/v1/knowledge/claims/939357MCP
get_claim(id=939357)