Trip+ - Soft Preferences: leaderboard
Metric: Soft-preference satisfaction (0-100), a rate scaled by 100: profile-derived rule scores for pace, comfort, transport, budget and interests, averaged over the plans that pass the response-mode gate, 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 2031. 18 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Qwen 3.6 27B (Non-reasoning) | 66.26 |
| 2 | Gemini 3.1 Pro (Preview) | 63.89 |
| 3 | Kimi K2.6 | 63.8 |
| 4 | Qwen 3.5 27B (Non-reasoning) | 63.75 |
| 5 | DeepSeek V4 Pro | 62.58 |
| 6 | GPT-5.4 Mini | 62.07 |
| 7 | Gemini 3 Flash (Preview) | 61.72 |
| 8 | GLM-4 32B | 61.41 |
| 9 | GLM-5.1 | 61.36 |
| 10 | MiniMax-M2.7 | 60.76 |
| 11 | Seed 2.0 Pro | 60.31 |
| 12 | Hy3-preview | 59.57 |
| 13 | Gemma 4 26B A4B | 59.4 |
| 14 | GPT-5.4 | 58.54 |
| 15 | DeepSeek V3.2 | 58.42 |
Interactive version: theaggregate.ai/benchmark?slug=trip-plus-soft-preferences · How It Works · Data refreshed daily, snapshot 2026-09-29.