Trip+ - User Simulation: leaderboard
Trip+ (2026) has tool-using LLM agents plan and revise minute-level travel itineraries over multi-turn conversations with profiled travelers, changing requests and environment disruptions, in a fixed travel sandbox. This board is the simulated traveler experience, the median rating of four LLM judges playing the profiled traveler. Scores are on a 0 to 100 scale; higher is better.
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: Not forecast. 18 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | GPT-5.4 | 51.84 | #123 |
| 2 | Qwen 3.6 27B (Non-reasoning) | 51.67 | #341 (Qwen 3.6 27B) |
| 3 | Kimi K2.6 | 51.64 | #178 |
| 4 | Qwen 3.6 35B A3B (Non-reasoning) | 51.41 | #462 (Qwen 3.6 35B A3B) |
| 5 | Seed 2.0 Pro | 51.28 | #211 |
| 6 | DeepSeek V4 Pro | 51 | #188 |
| 7 | GPT-5.4 Mini | 50.85 | #389 |
| 8 | Gemini 3.1 Pro (Preview) | 50.77 | #94 |
| 9 | GLM-5.1 | 50.14 | #179 |
| 10 | MiniMax-M2.7 | 49.92 | #518 |
| 11 | Gemma 4 31B | 49.23 | #394 |
| 12 | Gemma 4 26B A4B | 49.16 | #615 |
| 13 | Hy3-preview | 48.66 | #316 |
| 14 | Gemini 3 Flash (Preview) | 48.62 | #144 |
| 15 | Qwen 3.5 27B (Non-reasoning) | 48.21 | #359 (Qwen 3.5 27B) |
No result here: #1 Claude Fable 5.2, #2 Gemini 4 Carbon, #5 Claude Opus 5.5.
Interactive version: theaggregate.ai/benchmark?slug=trip-plus-user-simulation · How It Works · Data refreshed daily, snapshot 2026-11-13.