Trip+ - User Simulation: leaderboard
Metric: Simulated traveler experience (0-100), a rate scaled by 100: median of four profile-conditioned LLM judges (Qwen, Claude, Gemini and GPT families) rating each activity of the final plan for comfort and preference fit, averaged over tasks, on multi-turn personalized travel planning with traveler profiles, request changes and environment disruptions, the same OpenAI-compatible function-calling scaffold over a fixed travel sandbox for every model, temperature 0 where supported; higher is better. Source: arxiv.org. Saturation forecast: Around 2033. 18 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | GPT-5.4 | 51.84 |
| 2 | Qwen 3.6 27B (Non-reasoning) | 51.67 |
| 3 | Kimi K2.6 | 51.64 |
| 4 | Qwen 3.6 35B A3B (Non-reasoning) | 51.41 |
| 5 | Seed 2.0 Pro | 51.28 |
| 6 | DeepSeek V4 Pro | 51 |
| 7 | GPT-5.4 Mini | 50.85 |
| 8 | Gemini 3.1 Pro (Preview) | 50.77 |
| 9 | GLM-5.1 | 50.14 |
| 10 | MiniMax-M2.7 | 49.92 |
| 11 | Gemma 4 31B | 49.23 |
| 12 | Gemma 4 26B A4B | 49.16 |
| 13 | Hy3-preview | 48.66 |
| 14 | Gemini 3 Flash (Preview) | 48.62 |
| 15 | Qwen 3.5 27B (Non-reasoning) | 48.21 |
Interactive version: theaggregate.ai/benchmark?slug=trip-plus-user-simulation · How It Works · Data refreshed daily, snapshot 2026-09-29.