BlogLLM Benchmark Scores as Published, Side by Side
AIR-Bench: Results as Published
Every result the catalog holds for AIR-Bench: 2 models from 2 developers, read from 1 page. Each number is as printed by the company named beside it; nothing is ranked or rescored. Models are listed by developer, newest first.
Area Safety and AlignmentMaintainer Yi Zeng, Yu Yang and co-authors (AIR 2024 team)Introduced 2024Data version 2026103001, as of 2026-10-30
AIR-Bench 2024 is a safety benchmark of 5,694 prompts across 314 granular risk categories, built from 8 government regulations and 16 company policies. A model's answers to the prompts are judged on how it handles each risk, and the aggregate is the reported score.
AIR-Bench 2024 (aggregate score)
aggregate score
| Model | Value | Printed by | Setup as printed |
|---|---|---|---|
| Claude Sonnet 4.6Anthropic, released 2026-02-17 | 88 | Microsoft, Microsoft AI: MAI-Thinking-1 technical reportchecked 2026-10-19 | Effort: max |
| MAI-Thinking-1Microsoft, released 2026-08-12 | 88 | Microsoft, Microsoft AI: MAI-Thinking-1 technical reportchecked 2026-10-19 | - |
Every number here is read from the same catalog file as the benchmark table, data version 2026103001, and is the number the table shows for that model and test. Where one page printed a model under several setups, each value is listed. The catalog is public in armanobosyan/sugra-llm-benchmarks; a wrong number can be reported from the table, with Report an error under the value, or as an issue in that repository.