Unverified50% confidenceBenchmarkExact time
The author measured 2,000 support tickets using Anthropic's count_tokens endpoint and found the average input tokens per request increased from 1,180 to 1,461, a 24% increase.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
10/12/2026
First Seen
Valid until: 1/10/2027
Sources
Related Entities
Related Claims
UnverifiedIn a test-paper grading case, Cowork generated an analysis and HTML report containing an average score of approximately 72%, a minimum of 30 points, and a maximum of 100 points through a single instruction.62% similarUnverified研究数据显示，在复杂代码生成任务中，将thinking budget从1024 tokens提升到8192 tokens可以带来15-30%的准确率提升，但推理成本增加4-8倍60% similarUnverifiedIn the DeepSWE benchmark, the ratio of input tokens to output tokens during agent execution reached 174 to 1.60% similarUnverifiedOn the author's internal document corpus, the median Top-1 score for questions with true answers using the ada-002 model is approximately 0.84, while between random unrelated chunks it is approximately 0.72.59% similarUnverifiedAccording to data from Artificial Analysis, the number of reasoning tokens per task doubled from approximately 42,000 in Opus 5 to 84,000 in Opus 5.5, while output tokens only increased from 30,000 to 35,000.58% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1003233API
curl https://kongchang.com/api/v1/knowledge/claims/1003233MCP
get_claim(id=1003233)