Unverified50% confidenceBenchmarkExact time
Search-based baseline methods cost 3.8-7.4 times as much but still achieve lower accuracy than DiVR.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
11/13/2026
First Seen
Valid until: 2/11/2027
Sources
Related Entities
Related Claims
UnverifiedOn parallel search, the new method improves over the previous baseline by up to 1.4x.67% similarUnverifiedGPT-4o-mini scores about 18% accuracy on the same HS code benchmark; the best AI Agent with web search reaches 46.8%, but costs $1-10 per call and takes 10-30 seconds; human experts are about 95%.63% similarUnverifiedIn retrieval tasks, when the context is extended with neutral filler text, the retrieval accuracy of five open-source models (0.5B to 3B parameters) is almost unaffected, staying between 0.97 and 1.00.61% similarUnverifiedIn the scenario where the corner of the grid search already contains the answer, the best fixed configuration reaches 95% validation accuracy in only 317 ± 29 steps, whereas PBT needs an average of 2667 ± 2244 steps; on every seed, PBT is slower.61% similarUnverifiedIn the Terminal Bench 4.0 highest-accuracy test, Fable 5.1 achieved an accuracy of 55.8% at a cost of $19.50, while Astra achieved an accuracy of 56.7% at a cost of $10.35.61% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1166059API
curl https://kongchang.com/api/v1/knowledge/claims/1166059MCP
get_claim(id=1166059)