Expired80% confidenceFactTime unknown
In a Chinese character count control test requiring exactly 40 characters, Claude Sonnet 4.5 completed exactly 40 characters, while GPT 5.1 wrote 37 characters.
1
Sources
80%
Confidence
Medium-term (~90 days)
Relevance
6/3/2026
First Seen
This claim has expired. It is kept for the record and no longer describes the current state.
Valid until: 9/1/2026(expired)
Sources
Related Entities
Related Claims
UnverifiedSonnet 5 switched to the Opus 4.7 tokenizer, causing the same text to be tokenized into approximately 1.1 to 1.3 times as many tokens.67% similarUnverifiedSonnet 4.8更新后的分词器在相同提示词下可能会多消耗约30%的token65% similarUnverifiedIn tests covering context lengths of 512–4096, increasing the draft length from 4 tokens to 16 tokens resulted in only a 0.2%–1.3% increase in overall inference latency.61% similarUnverifiedIn the hard question, Claude Sonnet 4.6 achieved the highest score of 93 in the entire field, with the most complete comments and most rigorous tests.61% similarUnverifiedIn SWE-bench testing, the early GPT-4 resolution rate was below 2%, while Claude 3.5 Sonnet broke through 49%.60% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/40339API
curl https://kongchang.com/api/v1/knowledge/claims/40339MCP
get_claim(id=40339)