Unverified50% confidenceFactExact time
In real physical laboratory validation of molecular design, the model achieved a hit rate of nearly 50% across 12 targets, compared to the industry average of approximately 10% to 15%.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
9/4/2026
First Seen
Valid until: 12/3/2026
Sources
Related Entities
Related Claims
UnverifiedScale AI的研究团队发现，部分模型在被污染的基准上的表现比在新编写的同等难度题目上高出10-15个百分点71% similarUnverifiedIn multiple benchmarks, even the most advanced models can have hallucination rates of 15%–30% in specialized technical domains.68% similarUnverifiedOn cognitive tasks, humans can achieve approximately 80%, while SOTA multimodal models achieve only 30% to 50%, sometimes approaching random guessing63% similarUnverifiedExperimental data shows that when key information is located at the beginning and end of the input sequence, the model's retrieval accuracy can be as high as over 90%, but when located in the middle, it may drop sharply to below 60%.62% similarUnverifiedMid-tier models typically achieve more than 80% of flagship model scores on benchmarks such as MMLU and HumanEval, while requiring less than 30% of the inference cost.62% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/853046API
curl https://kongchang.com/api/v1/knowledge/claims/853046MCP
get_claim(id=853046)