Unverified50% confidenceBenchmarkExact time
After the bug fix, schemagate ran all 19,624 records of Spider-ACL using Claude Sonnet 5.5, reaching a rejection F1 of 0.984.
1
Sources
50%
Confidence
Short-term (~14 days)
Relevance
10/17/2026
First Seen
Valid until: 10/31/2026
Sources
Related Entities
Related Claims
UnverifiedBased on past positioning, Sol should have been a competitor to Opus, but it is now priced the same as Sonnet and its performance has not comprehensively surpassed Sonnet 5.562% similarUnverifiedOn Spider, schemagate and the paper's best configuration both achieved an AC-F1 of 93.0, but schemagate's wrong-answer rate was 5.1%, slightly higher than the paper's 4.6%.60% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1053850API
curl https://kongchang.com/api/v1/knowledge/claims/1053850MCP
get_claim(id=1053850)