Unverified50% confidenceFactExact time
The score gap among multiple frontier models on MMLU has narrowed to the order of one percentage point, driving the emergence of more challenging benchmarks such as MMLU-Pro and ARC-AGI.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
9/8/2026
First Seen
Valid until: 12/7/2026
Sources
Related Entities
Related Claims
UnverifiedSince the second half of 2024, the score improvements of mainstream large models on standard benchmarks such as MMLU and HumanEval have narrowed noticeably.74% similarVerifiedOn mainstream evaluations such as MMLU, HumanEval, and GSM8K, the score gaps among leading large models are often only a few percentage points.72% similarUnverified斯坦福大学HAI研究所2024年度AI指数报告显示，顶级闭源模型在MMLU基准上的最高分与第五名之间的差距，已从2022年的约8个百分点收窄至不足2个百分点71% similarVerifiedBy mid-2024, top models had generally exceeded scores of 85–90% on MMLU, causing the benchmark's discriminative power to drop sharply.70% 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69% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/874512API
curl https://kongchang.com/api/v1/knowledge/claims/874512MCP
get_claim(id=874512)