Checked fact 509016 Nov 2026Safety and security
Anthropic says that on its API, the current aggregate harmless response rates for its single-turn evaluations are between 94% and 98% for every recent model, whereas response rates for multi-turn tasks range much more widely.
The exact words it rests on
the current aggregate harmless response rates for our single-turn evaluations are between 94% and 98% for every recent model; the response rates for multi-turn tasks range much more widely
What the source said when we opened it, on 15 Nov 2026.
The source
Building strong safety evaluations (Anthropic Engineering)
Checked
Checked by the notis newsroom on , against the source above.
In the story
Anthropic says single-turn safety evals are saturated at 94% to 98% on its API 16 Nov 2026
Cite this fact
Anyone may quote this address. It does not change; if we correct the story, this page says so.