GroupTravelBench - Hard: leaderboard
Metric: Group Utility (GU, unnormalized points per user, unbounded and can be negative: +2 or +1 for each satisfied must or prefer item, -2 or -1 for each violated reject or avoid item, minus K-1 for each split into K subgroups, divided by the group size) on the 200 hard tasks (25 rounds), on GroupTravelBench, multi-user multi-turn group travel planning in a group-chat sandbox with 10 cached travel tools (DeepSeek-V4-Flash user simulator at temperature 0, agent temperature 0.7, mean of 3 trials per task); GPT-5.1 in instruct mode, the other models with reasoning enabled; higher is better. Source: arxiv.org. Saturation forecast: Around June 2027. 9 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Qwen 3.6 Max (Preview) (Thinking) | 10.33 |
| 2 | Qwen 3.5 Plus (Thinking) | 9.2 |
| 3 | GPT-5.1 (Non-reasoning) | 7.78 |
| 4 | Qwen 3.5 Flash (Thinking) | 7.65 |
| 5 | Qwen 3 4B Instruct | 7.1 |
Interactive version: theaggregate.ai/benchmark?slug=grouptravelbench-hard · How It Works · Data refreshed daily, snapshot 2026-10-07.