Unverified50% confidenceFactExact time
MLE-bench is a standardized benchmark released by OpenAI in 2024, curating 75 historical competition tasks from Kaggle spanning tabular data, computer vision, natural language processing, and other domains, with scoring benchmarked against the Kaggle medal system.
1
Sources
50%
Confidence
Long-term
Relevance
10/12/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedBrowseComp is a specialized benchmark proposed by OpenAI in early 2025, used to evaluate the performance of models equipped with web search tools in multi-hop reasoning scenarios69% similarUnverifiedIn 2024, Anthropic proposed the Tool Use specification and OpenAI updated its Structured Outputs capability, improving the reliability of tool calls.63% similarUnverifiedOpenAI open-sourced its Evals framework in 2023, categorizing evaluation into three major types: fact-based exact matching, model-based judgment, and human-annotation-based evaluation.63% similarVerifiedOpenAI's Preparedness Framework was released at the end of 2023, covering four high-risk domains—cybersecurity, CBRN, deceptive alignment, and autonomous replication—with each dimension rated at one of four levels (low, medium, high, critical), and models reaching the critical level are in principle not permitted to be released.62% similarUnverifiedAlbumentations库由Buslaev等人于2018年开源，最初为Kaggle竞赛场景优化61% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1001133API
curl https://kongchang.com/api/v1/knowledge/claims/1001133MCP
get_claim(id=1001133)