Unverified50% confidenceFactExact time
MaxGraph has no public benchmarks, only the roughly 43% context token savings the author measured on his own project.
1
Sources
50%
Confidence
Short-term (~14 days)
Relevance
10/19/2026
First Seen
Valid until: 11/2/2026
Sources
Related Entities
Related Claims
UnverifiedThe 44% reduction in inference tokens is a self-reported figure from the author and has not been verified by third-party reproduction; the original materials do not disclose the data construction method, training algorithm, sampling scale, or benchmark test details.71% similarUnverifiedIn actual testing, the draft acceptance rate was only approximately 41%, with the draft model outputting 1,055 tokens but only approximately 438 being accepted.66% similarUnverifiedIn manually proofread samples, the character error rate was only 0.68% when the text was clearly legible, but approximately 45% of sampled passages were completely uncorrectable due to source quality issues.64% similarUnverifiedOn a test subset of 152 completely untouched questions, anchored hybrid retrieval achieved 42.11%, while the planner-guided method reached only 36.84%.63% similarUnverifiedThe 99.4% containment rate comes from the author's own testing and has not yet been independently verified by a third party.63% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1071241API
curl https://kongchang.com/api/v1/knowledge/claims/1071241MCP
get_claim(id=1071241)