Unverified50% confidenceFactExact time
Macro-average accuracy is a metric that first computes the accuracy of each task separately and then takes the arithmetic mean over tasks, giving each task equal weight.
1
Sources
50%
Confidence
Long-term
Relevance
10/20/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedExperiments show that the gated objective achieved the highest average accuracy on both datasets, verifying that objective reliability and evaluation priority can be optimized independently79% similarUnverifiedMeasuring tool-call efficiency typically involves key metrics such as call success rate (the proportion that pass validation on the first call), average number of call turns, end-to-end latency, and degree of parallelization.76% similarUnverifiedWhen evaluating document information extraction tasks, commonly used metrics include field-level exact match, recall, and end-to-end accuracy.75% similarVerifiedIntelligence level is typically evaluated through a series of task benchmarks, while power consumption can be measured directly.73% similarUnverifiedA robust embodied AI evaluation benchmark should consider sample efficiency and generalization across randomized scenarios, not just task completion rate and spatial accuracy.73% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1073922API
curl https://kongchang.com/api/v1/knowledge/claims/1073922MCP
get_claim(id=1073922)