OpenAI Frontier Evals (PaperBench, SWE-Lancer, MLE-bench...)

Evals

Benchmark / dataset

Preparedness-framework capability evals. openai/preparedness mirrors.

Category
Autonomy, R&D & self-replication
Insurance exposure
Unmapped
Publisher
OpenAI
Publisher type
Frontier lab
License
MIT
Status
Active (<90d)
Last commit
2026-10-12
Stars
1317

View source on GitHub →

Wanich Risk Lab, 2026.