Benchmark
AIR-Bench
What is 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…
- Released
- 2024-07-11
- Modality
- text
- Evaluates
- safety
- Openness
- unknown
- Importer
- LLM Stats
- Reported scores
- 1
Source provenance
- Original evidence https://api.zeroeval.com/leaderboard/benchmarks/air-bench?top_n=500
AIR-Bench results and reported scores
LLM Stats
| Model | Organization | Reported value | Reported | Evidence |
|---|---|---|---|---|
| MAI-Thinking-1 | Microsoft | 0.88 | 2026-06-02 | 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.