Unverified50% confidenceFactExact time
Compared with the Hugging Face implementation, the KV Cache implementation's maximum logit absolute error is about 6.1e-5.
1
Sources
50%
Confidence
Long-term
Relevance
10/18/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedOn the LongMemEval multi-hop task, strict recall@5 performs as follows: 78.8%->85.2% with 5 chunks, 87.2%->92.8% with 10 chunks, and flat at 20 chunks.64% similarUnverifiedTerminal-Bench 4.0 has a standard error of ±2.6 points, and Opus 5's 51.8% reproduced as 52.3%, which Anthropic calls noise.60% similarUnverifiedOn Terminal-Bench 4.0, Haiku 5.5 scores 39.2% versus Opus 5.5's 70.6%.59% similarUnverifiedAfter re-evaluating with non-overlapping anchors, the net advantage instead grew from +4.1pp to +5.5pp, but significance dropped from 2.4 standard errors to 1.4 standard errors; the inflation factor is about 2.4x, exactly equal to sqrt(912/163).59% similarUnverifiedGrok 4.6在UI设计测试中表现平庸，逊于Fable和5.6 Sol58% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1060681API
curl https://kongchang.com/api/v1/knowledge/claims/1060681MCP
get_claim(id=1060681)