Antistatic v2 is available to try at v2.antistatic.exchange
antistatic.exchange
Register Log in

OpenAI safety capability thresholds

By end of 2025
✗0.1%
By end of 2026 Happened 17 Nov 2026
✓4.0%
By end of 2027
✓30.8%
By end of 2028
✓56.9%
By end of 2029
✓70.8%
By end of 2030
✓77.6%
Everyone's forecast, 1 Nov 2026
Chance by end of 2026 4.0%
Opened 25 Mar 2026 Happened 17 Nov 2026

2 comments

Log in to comment.

1

OpenAI's GPT-Rosalind-6 addendum (October 30) uses GPT-6 Astra's weights with fewer dual-use bio refusals under trusted access. OpenAI treats it as High Bio/Chem, below Critical: none of the four Critical bio evals met its threshold. Cyber stays Critical, AI Self-Improvement below High. card

1

OpenAI's GPT-6 Cyber system card (November 5) likewise keeps Biological and Chemical at High (below Critical on all four bio benchmarks) and AI Self-Improvement below High (Internal Research Debugging 77.40%, KernelGen 46.12%). Under Critical cybersecurity safeguards, it scores 48.45% on ExploitGym (36.94% Hardened) and 11/11 on Irregular's CyScenarioBench.