Unverified50% confidenceBenchmarkExact time
GLOBE achieves a 49.7% reduction in output tokens, a 51.0% reduction in end-to-end actual elapsed time (E2E), and an average accuracy of 80.58% across the five tasks, comparable to full CoT.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
10/20/2026
First Seen
Valid until: 1/18/2027
Sources
Related Entities
Related Claims
UnverifiedIn a benchmark on 50 synthetic chore scenarios, the fine-tuned SlothDistill, compared with the base Llama-3-8B, reduced p95 decision latency from 1,420 ms to 185 ms (a 7.6x improvement), cut average output tokens from 412 to 48 (an 88.3% saving), raised direct-action accuracy from 62.4% to 97.8%, and lowered API cost per thousand tasks from $1.85 to $0.22 (88.1% cheaper).74% similarUnverifiedGLOBE's probing branch executes in parallel with the main process, so the probing cost can be masked by the generation process, which is why the E2E reduction (51.0%) is slightly higher than the token reduction (49.7%).73% similarUnverifiedFor a task that sequentially calls 5 APIs, even if the success rate of each step is 95%, the overall success rate drops to approximately 77%.70% similarUnverifiedAccording to hands-on testing by Bilibili UP host "1024工程笔记," integrating Ponytail reduced code volume by 54%, lowered token consumption by approximately 20%, and kept security-related check items at 100% passing.69% similarUnverifiedOn the AppWorld benchmark, SMC reduces actual runtime by 7.7% compared to the SA baseline and by 44.9% compared to serial execution, with only a slight decrease in task completion rate.69% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1074055API
curl https://kongchang.com/api/v1/knowledge/claims/1074055MCP
get_claim(id=1074055)