Unverified60% confidenceFactExact time
Traditional benchmarks such as MMLU and HumanEval have experienced benchmark saturation due to training data contamination; when GPT-4 was released, its MMLU score was approximately 86%, whereas multiple open-source models have now surpassed 90%
2
Sources
60%
Confidence
Long-term
Relevance
7/10/2026
First Seen
Sources
GPT-5.6 In-Depth Hands-On Review: How Do Soul, Tara, and Luna Really Perform?
bilibiliAI-seeker7/9/2026
Related Claims
Unverified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73% similarVerifiedBy mid-2024, top models had generally exceeded scores of 85–90% on MMLU, causing the benchmark's discriminative power to drop sharply.70% similarUnverified自2023年GPT-4发布以来，AI在HumanEval等主流编程基准测试上的通过率从不足50%跃升至90%以上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% similarUnverifiedWhen multiple models all achieve accuracy rates above 90% on benchmarks such as MMLU and HumanEval, user attention shifts to practical metrics such as inference latency, service availability, and total cost of ownership.69% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/461658API
curl https://kongchang.com/api/v1/knowledge/claims/461658MCP
get_claim(id=461658)