Verified80% confidenceBenchmarkExact time
MMLU contains approximately 15,000 multiple-choice questions across 57 subject areas; HumanEval, designed by OpenAI, contains 164 Python programming problems; MATH contains 12,500 competition math problems; and GPQA covers graduate-level science questions.
10
Sources
80%
Confidence
Long-term
Relevance
7/10/2026
First Seen
Sources
The Truth About "GPT-5.6": Debunking Fake Rumors and Third-Party Top-Up Scams
bilibili小小阿白6667/9/2026
Related Claims
UnverifiedMMLU contains more than 14,000 multiple-choice questions across 57 subjects, and current state-of-the-art models have already exceeded a score of 90%.74% similarUnverifiedHumanEval包含164道编程题，MBPP包含约500道编程题71% similarUnverifiedMBPP 收录了 500 道众包编程题，GSM8K 包含 8500 道小学数学应用题（需 2-8 个推理步骤）62% similarUnverifiedThe experiment covers 23 models from 11 vendor families, 5 tasks, and accumulated over 5,500 debate and control runs in total.60% similarUnverifiedMTEB ranks 162 embedding models on 58 datasets across 8 task types.60% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/472660API
curl https://kongchang.com/api/v1/knowledge/claims/472660MCP
get_claim(id=472660)