safety benchmark
AIR-Bench Leaderboard
AIR-Bench 2024 is a safety benchmark for evaluating policy-grounded refusal across regulatory and policy-derived harm categories.
Updated Sep 5, 2026
Models1
Model coverage1
MetricScore
EvidenceB
AIR-Bench Ranking
Higher score ranks better on this benchmark.
Sort by
Rank | Model | Score | Percentile | Participants | Evidence | Evaluated |
|---|
| Rank01 | ModelMI | Score88.00% | Percentile100.00% | Participants1 | EvidenceC | Evaluated |
AIR-Bench Highlights
The leading models and scores on this benchmark.
The Top AI Models for AIR-Bench
The first five results on this benchmark, with official price and output speed added where the model identity can be matched.
Ranking basisThis air-bench AI model leaderboard uses descending score in the benchmark original unit. The leaderboard ranking keeps matched price and speed data separate from benchmark evidence.
- 01MIMicrosoft
- Score
- 88.00%
Strengths
- Ranks #1 of 1 compared models
- 100th percentile on this benchmark
- C evidence result
Considerations
- This result measures AIR-Bench, not total model capability
Selection summary
Best AI Models for AIR-Bench
MAI-Thinking-1 currently leads AIR-Bench with 88.00%. It is the top model on this specific benchmark, while the best LLM for the broader task should also be checked against other benchmarks, price, and runtime.
Use this leaderboard with the supporting benchmark results and coverage details above. A leaderboard position summarizes the selected ranking signal; it does not replace workload-specific testing.
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 measures policy-grounded refusal across a broad regulatory and policy-derived harm taxonomy using category-specific LLM-judge prompts, with results reported as a Score ratio.
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
- overall
LLM Stats. 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 88.00%.
What are the top three models on AIR-Bench?
The current leaders are MAI-Thinking-1 (88.00%).
Which AIR-Bench model has the lowest official input price?
No matched official input price is currently available.
Which models are fastest among AIR-Bench results?
No matched runtime record is currently available.
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.