NUWA Evidence record
Claude 3.5 Sonnet · Template
AgentHarm · Evidence record
Original source charts and materials
Reported results
Source order · reported configurations
Select systems
Greedy harm score
0–100%
Claude 3.5 Sonnet · TemplateValues describe the measured outcome under the source protocol, not a general safety score.
Table 2: template attack, greedy sampling at temperature 0 versus mean and best-of-5 at temperature 1. These are different sampling conditions. Evaluation date not specified; publication / record dates are shown below.
Evaluation conditions and system configurations
- Claude 3.5 Sonnet · Template
- See the source protocol; no independent trial count inferred. · Table 2 · AgentHarm
- modelVersion: not specified · harness: not specified · tools: not specified · budget: not specified
| System / configuration | Greedy harm score | Mean harm score, T=1 | Best-of-5 harm score | Publication / verification |
|---|---|---|---|---|
| Claude 3.5 Sonnet · TemplateHarness not specified | 68.7% | 65.1%±1.3 (source-reported; see source definition) | 79.7% | Source checked2026-10-25 |
Method and scope
Harmful task completion and refusal under specified attacks.
- Evidence type
- Benchmark
- Assessment subject
- AI agent responding to harmful task requests
- Primary dimension
- Behavior
- Evidence snapshot
- 2026-10-29.1
General safety evidence retained for context; no defensible direct link to the six NUWA risk entries was found.
Source finding
Source-reported measurements for Claude 3.5 Sonnet · Template in Table 2; values are transcribed, not independently reproduced.
Limitations
Synthetic tools and task completion do not directly measure real-world harm.
Configuration, task and aggregation differences remain as reported. Source order is retained. Transcription is not independent replication; no cross-protocol ranking is supported.
Related research questions
References
Numerical results are reported by the cited authors.
- [1] Maksym Andriushchenko, Alexandra Souly, et al.. AgentHarm: A Benchmark for Measuring Harmfulness of LLM Agents. 2025-04-18. v3 [arXiv]; Author affiliations on the original paper title page; Table 2