TravelEval - Daily Time Utilization: leaderboard
Metric: Daily Time Utilization (DTU): effective attraction time over the whole day from departure to return (%); Direct prompting (one pass, no tools), plans simulated in the TravelEval sandbox of 10 Chinese cities (real rail, flight, hotel and attraction data, queuing-time model, road-network distances) over 1,150 queries; higher is better. Source: arxiv.org. Saturation forecast: Around 2033. 7 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Gemini 2.0 Flash | 27.15 |
| 2 | Claude Sonnet 4.5 | 25.97 |
| 3 | DeepSeek V3.1 (Non-reasoning) | 25.51 |
| 4 | GPT-4o Mini (2024-07-18) | 23.63 |
| 5 | Qwen 3 8B | 23.46 |
| 6 | GPT-5 Chat | 22.17 |
| 7 | GPT-4o (2024-11-20) | 21.76 |
Interactive version: theaggregate.ai/benchmark?slug=traveleval-daily-time-utilization · How It Works · Data refreshed daily, snapshot 2026-09-29.