Expired50% confidenceBenchmarkExact time
Multiple studies in 2023, including experiments by the University of Oxford, found that LLMs equipped with Retrieval-Augmented Generation (RAG) technology achieved Brier scores in structured forecasting competitions approaching the level of human superforecasters
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
7/7/2026
First Seen
Valid until: 10/5/2026(expired)
Sources
AI超级预测者：机器能否超越人类专家的预测能力？
hackernewshackernews7/6/2026
Related Claims
Unverified2023年加州大学伯克利分校发布的MT-Bench基准测试发现，顶级大模型作为评判者与人类专家判断一致性可达80%以上63% similarUnverified斯坦福HAI研究所2023年报告显示，最新LLM在HumanEval等代码基准测试中正确率已超过85%，远超2021年的不足50%61% similarUnverifiedForrest & Simmons (2002)研究发现博彩公司发布的赔率经庄家精算调整后，对比赛结果的预测准确率在统计上显著优于随机猜测61% similarUnverifiedDomestic models such as GLM5.1 have achieved scores on standard programming benchmarks like HumanEval and MBPP that are close to or even surpass some international competitors.61% similarUnverified研究表明博彩赔率对赛事结果的预测准确率长期来看优于大多数个人专家预测61% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/180108API
curl https://kongchang.com/api/v1/knowledge/claims/180108MCP
get_claim(id=180108)