safety benchmark
AIR-Bench
AIR-Bench 2024 is a safety benchmark grounded in risk categories derived from government regulations and company policies. It evaluates policy-grounded refusal across a broad regulatory and policy-derived harm taxonomy, using category-specific LLM-judge prompts that reward safe engagement rather than only penalizing unsafe responses.
Updated Aug 11, 2026
Models1
Model coverage1
MetricScore
EvidenceB
AIR-Bench Ranking
Higher score ranks better on this benchmark.
| 1 | MI | 88.0% | 100.0% | 1 | C |
AIR-Bench Highlights
The leading models and scores on this benchmark.
What is AIR-Bench?
What AIR-Bench measures and how its scores work.
AIR-Bench 2024 is a safety benchmark grounded in risk categories derived from government regulations and company policies. It evaluates policy-grounded refusal across a broad regulatory and policy-derived harm taxonomy, using category-specific LLM-judge prompts that reward safe engagement rather than only penalizing unsafe responses.
Scores are shown in ratio. This benchmark is not independently verified and has an evidence level of B.
- Family
- AIR-Bench
- Modality
- text
- Primary category
- safety
- Score direction
- higher
- LLMBoard eligible
- No
- Evaluation key
- air-bench|llm-stats-current
Benchmark scores retain their original unit. Overall score eligibility is shown separately.
FAQ
Common questions about AIR-Bench.
Which model scores highest on AIR-Bench?
MAI-Thinking-1 is currently ranked first with 88.0%.
What does AIR-Bench measure?
AIR-Bench 2024 is a safety benchmark grounded in risk categories derived from government regulations and company policies. It evaluates policy-grounded refusal across a broad regulatory and policy-derived harm taxonomy, using category-specific LLM-judge prompts that reward safe engagement rather than only penalizing unsafe responses.
Is a higher score better?
Yes. Higher values rank better for this benchmark.
How many models are compared?
1 model results are currently shown.
Does this benchmark affect the overall score?
No. This benchmark is shown for reference but does not contribute to the overall score.