Unverified50% confidenceFactExact time
Step 5's model size is significantly smaller than comparable flagship competing products.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
9/24/2026
First Seen
Valid until: 12/23/2026
Sources
Related Entities
Related Claims
UnverifiedIn tasks requiring more than 5 steps, the success rate of the strongest models drops sharply from over 80% at the first step to 40% or even lower at subsequent steps, exhibiting an exponential decline.68% similarUnverifiedThe study additionally introduced six deliberately weakened models with clearly inferior capabilities as positive controls.67% similarUnverifiedAn early iteration scored five percentage points lower than the Huihui base model on the IFEval instruction-following benchmark.67% similarUnverified在MATH数据集的Level 5竞赛级难题上，前沿模型准确率仍低于60%66% similarUnverifiedGLM5.2's inference speed is noticeably slower than models of the same tier, which is its biggest weakness.66% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/947144API
curl https://kongchang.com/api/v1/knowledge/claims/947144MCP
get_claim(id=947144)