GroupTravelBench: leaderboard
Travel planning in the real world is overwhelmingly a group activity, yet existing LLM travel-planning benchmarks reduce it to a single user, where the field is approaching saturation. This single-user assumption sidesteps what makes group planning hard for an agent: discovering private preferences across multiple users, surfacing conflicts, and balancing utility against fairness. To bri
Metric: GU (Group Utility) (self-reported). Source: benchmarklist.com. Saturation forecast: Around August 2027. 9 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | DeepSeek V4 Pro | 10.47 | #102 |
| 2 | Qwen 3.6 Max | 9.66 | #96 |
| 3 | Qwen 3.5 Plus | 8.63 | #125 |
| 4 | GPT-5.1 | 7.21 | #135 |
| 5 | Qwen 3.5 Flash | 6.97 | #232 |
No result here: #3 Claude Opus 5.5, #6 GPT-6 Astra, #7 GPT-6.1 Sol.
Interactive version: theaggregate.ai/benchmark?slug=grouptravelbench · How It Works · Data refreshed daily, snapshot 2026-10-20.