CompliBench - Airline: leaderboard
CompliBench (2026) evaluates LLMs as judges of guideline compliance in task-oriented dialogue: synthesized multi-turn conversations carry injected, adversarially optimized violations, and the judge must name the governing guideline and violation status of every assistant turn. This board is conversation-level accuracy in percent in the airline domain, the share of conversations judged correctly at every turn, averaged over four runs; higher is better.
Metric: Conversation-level accuracy (%): share of airline conversations in which the judge predicts both the governing guideline and the violation label correctly at every assistant turn, of an LLM judge on CompliBench's synthesized multi-turn dialogues with injected, adversarially optimized guideline violations, mean of four runs at default reasoning effort; higher is better. Source: arxiv.org. Saturation forecast: Around February 2027. 15 models tracked. Updated 7 Oct 2026.
Top models
| # | Model | Setting | Score | Overall rank |
|---|---|---|---|---|
| 1 | Gemini 3 Pro | 49.09 | #145 | |
| 2 | GPT-5 | 47.26 | #178 | |
| 3 | DeepSeek V3.2 | Thinking | 42.07 | #419 |
| 4 | Qwen 3.5 Plus | 41.16 | #242 | |
| 5 | GLM-5 | 31.4 | #269 | |
| 6 | Kimi K2.5 | 25.91 | #266 | |
| 7 | Qwen 3 Max | 24.39 | #415 | |
| 8 | Qwen 3 30B A3B | 21.95 | #1156 | |
| 9 | Claude Sonnet 4.6 | 21.18 | #173 | |
| 10 | GPT-4o | 17.07 | #751 | |
| 11 | Qwen 3 32B | 8.54 | #972 | |
| 12 | Qwen 3 4B | 3.66 | #2348 | |
| 13 | GPT-4o Mini | 2.74 | #1667 | |
| 14 | Qwen 3 14B | 2.13 | #1269 | |
| 15 | Qwen 3 8B | 1.22 | #1873 |
No result here: #1 Claude Fable 5.2, #3 Gemini 4 Neon, #4 GPT-6.2 Astra.
Interactive version: theaggregate.ai/benchmark?slug=complibench-airline · How It Works · Data refreshed daily, snapshot 2026-11-21.