Unverified50% confidenceBenchmarkExact time
In the Slop Code Bench benchmark, a certain frontier model scored only 14.8%.
1
Sources
50%
Confidence
Short-term (~14 days)
Relevance
10/17/2026
First Seen
Valid until: 10/31/2026
Sources
Related Entities
Related Claims
UnverifiedWithout validation, 12.8% of the fine-tuned model's invoices have validation-coverage field errors.68% similarUnverifiedModels' standard accuracy on the passage-level ranking task was only 0% to 13%.67% similarUnverifiedWhen sampling eight candidates without constraints from the model, 10.2% of inputs cannot produce any valid output under limited training data, and this proportion drops to 0.4% when using the full training data65% similarUnverifiedThe author's experience: reasoning models typically win on only 12% of tasks and lose on the economics of the remaining 88%.64% similarUnverifiedIn the ScopeBench evaluation, the raw capability of the 8 models ranged from 12.2% to 81.1%, and the scope compliance capability ranged from 34.4% to 86.7%.63% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1054680API
curl https://kongchang.com/api/v1/knowledge/claims/1054680MCP
get_claim(id=1054680)