Expired60% confidenceBenchmarkExact time
Token consumption for reasoning at the XHigh setting can reach 3–5 times that of the High setting, but the marginal accuracy improvement is typically only 5–15 percentage points.
2
Sources
60%
Confidence
Medium-term (~90 days)
Relevance
7/19/2026
First Seen
Valid until: 10/17/2026(expired)
Sources
Related Claims
UnverifiedIn benchmark testing, token usage surged by 1500% (approximately 15x) going from x-high to Max mode.71% similarUnverified高推理强度模式下单次请求的 Token 消耗可能是低强度模式的 5-20 倍69% similarUnverifiedIn the Skatebench test, from the x-high tier to the max tier, reasoning tokens per question spiked from approximately 330 to nearly 5,000 (more than 10x), while scores improved by only 1%.69% similarUnverifiedDoubling the thinking token budget from 8k to 16k brought only a 0.2% accuracy improvement, while changing the distribution of failed questions.69% similarUnverifiedThis approach reduces token usage by 58.3% and improves inference speed by 1.95×, with no loss in accuracy.69% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/565022API
curl https://kongchang.com/api/v1/knowledge/claims/565022MCP
get_claim(id=565022)