Unverified50% confidenceReleaseExact time
OpenAI发布GeneBench Pro研究基准测试，包含129个评估任务，涵盖10个主要领域和21个细分方向，前沿模型最高得分31.5%
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
7/19/2026
First Seen
Valid until: 10/17/2026
Sources
Related Claims
Unverified字节跳动发布EdgeBench基准测试，用于评估自主AI Agent的长期学习能力，涵盖134个跨6大类别任务，已公开51个任务71% similarUnverifiedGeneBench-Pro is a newly released benchmark designed to systematically evaluate the real-world performance of AI in genomics, biology, and scientific research scenarios.69% similarUnverifiedOrganizations such as OpenAI and Anthropic have begun adopting Dynamic Benchmarks strategies, periodically updating test sets and introducing adversarial samples to maintain evaluation validity66% similarUnverifiedAISI的评估采用多层次测试框架，参照CVE数据库中的真实案例，同时设计全新挑战场景测试模型泛化能力66% similarUnverifiedStandard AI benchmarks include MMLU (a comprehensive knowledge test covering 57 subjects), GPQA (graduate-level professional question answering), SWE-bench (real-world software engineering tasks), HumanEval and MBPP (programming ability), and MATH and GSM8K (mathematical reasoning)66% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/561863API
curl https://kongchang.com/api/v1/knowledge/claims/561863MCP
get_claim(id=561863)