TAC (Travel Agent Compassion): leaderboard
Travel Agent Compassion (CaML, arXiv 2606.18142; inspect_evals/tac): an AI booking agent chooses activities for users in 13 ticket-booking scenarios where the obvious or best-reviewed option harms animals (bullfights, marine shows, animal rides and races) and the request never mentions welfare. Scoring is programmatic on what the agent books. Score: welfare rate, the share of runs (%) that avoid the harmful option; picking at random avoids it about 64.5% of the time and many models do worse. Higher is better. Source: https://compassionbench.com/tac
Metric: Welfare rate (%; ticket-booking scenarios in which the agent avoided the option that harms animals, nothing in the request mentioning welfare). Source: compassionbench.com. Saturation forecast: Not forecast. 26 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Claude Opus 4.8 | 64.7 | #36 |
| 2 | Claude Opus 5 | 59.6 | #12 |
| 3 | Claude Opus 5.5 | 59.6 | #3 |
| 4 | Claude Fable 5 | 55.8 | #15 |
| 5 | Claude Fable 5.1 | 54.5 | #9 |
| 6 | GPT-6 Astra | 47.4 | #6 |
| 7 | Claude Sonnet 5.5 | 42.3 | #11 |
| 8 | Gemini 2.5 Flash | 39.7 | #242 |
| 9 | Claude Sonnet 4.6 | 37.8 | #90 |
| 10 | GPT-4.1 | 37.2 | #245 |
| 11 | DeepSeek V3.2 | 36.5 | #201 |
| 12 | Gemini 3.8 Flash | 32.1 | #22 |
| 13 | GPT-5.6 Terra | 29.5 | #40 |
| 14 | Muse Spark 1.3 | 28.8 | #25 |
| 15 | GPT-5.2 | 26.3 | #109 |
No result here: #7 GPT-6.1 Sol, #8 Gemini 4 Argon, #10 Muse Wonder Full.
Interactive version: theaggregate.ai/benchmark?slug=tac-travel-agent-compassion · How It Works · Data refreshed daily, snapshot 2026-10-19.