Unverified50% confidenceFactExact time
HLE (Humanity's Last Exam) is an extremely high-difficulty comprehensive knowledge test constructed by Scale AI in collaboration with numerous domain experts.
1
Sources
50%
Confidence
Long-term
Relevance
9/12/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedECI aims to address the problem of traditional benchmarks (such as MMLU, HumanEval, etc.) operating in silos and being difficult to compare horizontally, answering the question of what point in time a model's capabilities are equivalent to.67% similarVerifiedHumanEval, MBPP, and SWE-bench are industry-standard benchmarks in the field of AI programming evaluation.66% similarVerifiedCredible capability evaluation of models in the AI field relies on standardized benchmark tests; commonly used evaluation sets include MMLU, HumanEval, MATH, and GPQA.63% similarUnverifiedMMLU, HumanEval, and MT-Bench are standardized benchmark test sets widely recognized by the AI community.62% similarUnverified科大讯飞长期承接多省高考英语口语机考项目，其AI评测技术经过真实考试数据校验62% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/915233API
curl https://kongchang.com/api/v1/knowledge/claims/915233MCP
get_claim(id=915233)