Benchmark
XSTest
XSTest is a test suite designed to identify exaggerated safety behaviours in large language models. It comprises 450 prompts: 250 safe prompts across ten…
- Modality
- text
- Categories
- safety
- Openness
- unknown
- Source
- llm_stats
- Reported scores
- 4
Reported scores
llm_stats
| Model | Organization | Reported value | Reported | Evidence |
|---|---|---|---|---|
| Gemini 1.5 Flash | 0.97 | 2024-05-01 | evidence | |
| Gemini 1.5 Flash 8B | 0.926 | 2024-03-15 | evidence | |
| Gemini 1.5 Pro | 0.988 | 2024-05-01 | evidence | |
| Shieldstral 1.0 (3B) | Mistral | 0.946 | 2026-08-04 | evidence |
Scores are partitioned by the source that reported them and are never merged into a single cross-source ranking, because the sources measure different things and say so.