[KongchangAI]
Benchmark

SemBench

A benchmark for evaluating the performance of semantic query engines, covering text and tabular workloads. It measures model accuracy on structured data query tasks.

Timeline (last 90 days)

Oct 12

Among published results on SemBench, 21% of text results vary in quality across different executions, including engines whose query plans are themselves deterministic

Unverified50%

All Facts (1)

Source Articles