activeSafety
ToxiGen
Metric: Toxicity Classification Accuracy (higher is better)Introduced: 2022
274,000 machine-generated toxic and benign statements about 13 minority groups, using adversarial classifier-in-the-loop decoding for implicit hate speech evaluation.
Models ranked
0
tracked on this benchmark
Score band
—
no scores yet
Snapshot trend
—
need ≥2 snapshots
Leaderboard
Tracked models ranked by Toxicity Classification Accuracy (higher is better).
No leaderboard entries are tracked for this benchmark yet.
How to read this benchmark
This benchmark scores models where higher is better. Use scores for directional filtering and shortlisting, not universal quality ranking; then validate pricing, context window, provider availability, and fit for your workload.
Trust this score when
- There is a fresh timestamped snapshot (or multiple snapshots) for this benchmark.
- The model list covers the same version family you can actually deploy today.
- Top candidates overlap with your required routing and feature requirements.
Be cautious when
- There is only one benchmark snapshot or the dataset appears stale.
- The benchmark metric direction is opposite of your decision objective.
- The score difference between options is narrow and likely within implementation variance.
Related benchmarks
Last reviewed: Apr 15, 2026