Expired60% confidenceFactExact time
Since the second half of 2024, the score improvements of mainstream large models on standard benchmarks such as MMLU and HumanEval have narrowed noticeably.
2
Sources
60%
Confidence
Medium-term (~90 days)
Relevance
7/2/2026
First Seen
Valid until: 9/30/2026(expired)
Sources
Java Developer's Guide to AI Application Development: Career Path, Skills, and Hands-On Strategy
bilibili程序员徐庶老师6/5/2026
Related Claims
UnverifiedBy mid-2024, top models had generally exceeded scores of 85–90% on MMLU, causing the benchmark's discriminative power to drop sharply.76% similarUnverifiedScale AI在2024年的分析显示，部分模型在MMLU上的分数膨胀可能高达5-10个百分点，因测试集已泄露到训练数据中76% similarUnverifiedSince the second half of 2024, the industry has broadly observed that the improvement margins of mainstream large models on standard evaluation benchmarks have narrowed significantly, a phenomenon referred to as 'Scaling Law deceleration.'75% similarUnverified基准污染（Benchmark Contamination）导致HumanEval、MMLU等主流基准区分度下降，部分模型HumanEval得分超过95%、MMLU超过90%但实际能力平庸72% similarUnverifiedOn mainstream evaluations such as MMLU, HumanEval, and GSM8K, the score gaps among leading large models are often only a few percentage points.71% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/52871API
curl https://kongchang.com/api/v1/knowledge/claims/52871MCP
get_claim(id=52871)