Anthropic Child Safety Single-Turn Harmful Requests - Harmless Rate (API): leaderboard
Percentage of harmless responses to single-turn harmful child-safety requests across tested languages, using the API without a system prompt. Higher is better. Source: Claude Opus 5.5 system card, Table 4.2.A; distinct from benign-request over-refusal.
Metric: Harmless Response Rate (%). Source: www-cdn.anthropic.com. Saturation forecast: Estimated already saturated. 4 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Claude Opus 5 | 100 | #12 |
| 2 | Claude Sonnet 5 | 99.95 | #55 |
| 3 | Claude Fable 5.1 | 99.9 | #9 |
| 4 | Claude Opus 5.5 | 99.14 | #3 |
No result here: #5 GPT-6 Astra, #7 Gemini 4 Argon, #8 GPT-6.1 Sol.
Interactive version: theaggregate.ai/benchmark?slug=anthropic-child-safety-single-turn-harmful-requests-harmless-rate-api · How It Works · Data refreshed daily, snapshot 2026-10-16.