Unverified50% confidenceBenchmarkExact time
In GPT Researcher's experiments, traditional embedding retrieval yielded only 46% relevant context.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
9/30/2026
First Seen
Valid until: 12/29/2026
Sources
Related Entities
Related Claims
UnverifiedIn 96% of levels, GPT-6 required fewer attempts to find the answer than the average person.68% similarUnverifiedIn GPT Researcher's experiments, the decision-based approach improved the proportion of effective context by approximately 27 percentage points compared to traditional embedding retrieval.68% similarUnverifiedGPT models perform poorly when recall ability is tested in isolation, correctly recalling only about 50% of facts across all categories including spatial information, transcription content, and physical experiments, with open-source models performing even worse.66% similarUnverifiedThe 73% vs. 46% data comes from a single-source experimental sharing, large-scale multi-scenario replication validation has not yet been observed, and the experimental setup has not been fully disclosed.62% similarUnverifiedJev and Neural-MCTS agreed on their top action only approximately 63% of the time.62% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/960483API
curl https://kongchang.com/api/v1/knowledge/claims/960483MCP
get_claim(id=960483)