TravelEval - Preference-Weighted Experience: leaderboard
Metric: Profit: mean over attractions of objective score times the preference-match weight (paper units, unbounded); 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 December 2026. 7 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | GPT-4o (2024-11-20) | 5.97 |
| 2 | GPT-4o Mini (2024-07-18) | 5.97 |
| 3 | Qwen 3 8B | 5.74 |
| 4 | DeepSeek V3.1 (Non-reasoning) | 5.72 |
| 5 | Gemini 2.0 Flash | 5.71 |
| 6 | GPT-5 Chat | 5.65 |
| 7 | Claude Sonnet 4.5 | 5.44 |
Interactive version: theaggregate.ai/benchmark?slug=traveleval-preference-weighted-experience · How It Works · Data refreshed daily, snapshot 2026-09-29.