Expired50% confidenceBenchmarkExact time
Anthropic's "needle test" benchmark shows that Claude achieves a key information retrieval accuracy of over 99% within a 200,000-token range.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
7/6/2026
First Seen
Valid until: 10/4/2026(expired)
Sources
Claude Leads sqlite-utils 4.0 Development for $149: A Real-World Look at AI Programming
hackernewshackernews7/5/2026
Related Claims
UnverifiedThe accuracy data in the test has an error margin of approximately ±8–10 percentage points at n=100 sample size (based on a 95% confidence-level binomial confidence interval).70% similarUnverifiedOn the CLINC150 benchmark, 80 fine-tuning samples can bring vector routing to an accuracy of 85.9%, while a full fine-tune can exceed 96%.67% similarUnverified在某些测试中，文档中间段信息的检索准确率比首尾段低40%以上67% similarUnverifiedExperimental data shows that when key information is located at the beginning and end of the input sequence, the model's retrieval accuracy can be as high as over 90%, but when located in the middle, it may drop sharply to below 60%.67% similarUnverifiedThe system achieved a detection accuracy rate of over 85% on a validated sample of 50 CVEs.65% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/115315API
curl https://kongchang.com/api/v1/knowledge/claims/115315MCP
get_claim(id=115315)