Expired50% confidenceFactExact time
In Max Reasoning mode, Soul consumes more tokens in exchange for better output, with the reasoning budget increasing from approximately 768 to nearly 1000.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
7/9/2026
First Seen
Valid until: 10/7/2026(expired)
Sources
Related Claims
UnverifiedBefore outputting a final answer, a reasoning model's internal chain of thought may consume 3,000 to 20,000 tokens, far exceeding the approximately 500 tokens of an ordinary model.63% similarUnverifiedSoul performs comparably to Mythos on advanced vulnerability research, but consumes only about one-third of the output tokens.62% 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61% similarUnverified端侧推理中吞吐量需达到5-10 token/s对应人类舒适阅读速度，低于此值输出显得一字一顿61% similarUnverified日常任务使用low或中等级别（智商约105-120）够用，仅在处理复杂逻辑时考虑extra high（智商可达135）60% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/394893API
curl https://kongchang.com/api/v1/knowledge/claims/394893MCP
get_claim(id=394893)