safety benchmark
XSTest Leaderboard
XSTest is a test suite for identifying exaggerated safety behaviours in large language models.
Updated Sep 5, 2026
Models4
Model coverage4
MetricScore
EvidenceB
XSTest Ranking
Higher score ranks better on this benchmark.
Sort by
Rank | Model | Score | Percentile | Participants | Evidence | Evaluated |
|---|
| Rank01 | ModelGO | Score98.80% | Percentile100.00% | Participants4 | EvidenceC | Evaluated |
| Rank02 | ModelGO | Score97.00% | Percentile66.67% | Participants4 | EvidenceC | Evaluated |
| Rank03 | ModelMA | Score94.60% | Percentile33.33% | Participants4 | EvidenceC | Evaluated |
| Rank04 | ModelGO | Score92.60% | Percentile0.00% | Participants4 | EvidenceC | Evaluated |
XSTest Highlights
The leading models and scores on this benchmark.
XSTest Score Distribution
A closer view of the leading scores on this benchmark.
The Top AI Models for XSTest
The first five results on this benchmark, with official price and output speed added where the model identity can be matched.
What is XSTest?
What XSTest measures and how its scores work.
XSTest comprises 450 prompts: 250 safe prompts across ten prompt types that well-calibrated models should not refuse to comply with, and 200 unsafe prompts that models should refuse.
It measures whether models refuse to respond to clearly safe prompts due to overly cautious safety mechanisms, using the Score metric reported as a ratio.
Scores are shown in ratio. This benchmark is not independently verified and has an evidence level of B.
- Family
- XSTest
- Modality
- text
- Primary category
- safety
- Score direction
- higher
- LLMBoard eligible
- No
- Evaluation key
- overall
LLM Stats. Benchmark scores retain their original unit. Overall score eligibility is shown separately.
FAQ
Common questions about XSTest.
Which model scores highest on XSTest?
Gemini 1.5 Pro is currently ranked first with 98.80%.
What are the top three models on XSTest?
The current leaders are Gemini 1.5 Pro (98.80%), Gemini 1.5 Flash (97.00%), and Shieldstral 1.0 (3B) (94.60%).
Which XSTest model has the lowest official input price?
No matched official input price is currently available.
Which models are fastest among XSTest results?
The fastest matched records are Gemini 1.5 Flash (150.00 tok/s via Google), Gemini 1.5 Flash 8B (150.00 tok/s via Google), and Gemini 1.5 Pro (85.00 tok/s via Google).
Does the highest score result prove overall model quality?
No. This benchmark measures one defined capability or task. The overall LLMBoard score uses a separate aggregation across eligible benchmark evidence.