Trip+ - Request Fulfillment: leaderboard
Metric: Request fulfillment (0-100), a rate scaled by 100: whether the response incorporates the new or revised constraints, preferences and environment conditions of the turn, averaged over all turns, 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 February 2027. 18 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Gemma 4 31B | 74.65 |
| 2 | Gemini 3.1 Pro (Preview) | 73.82 |
| 3 | GLM-5.1 | 72.14 |
| 4 | Gemini 3 Flash (Preview) | 68.85 |
| 5 | Seed 2.0 Pro | 68.11 |
| 6 | Kimi K2.6 | 67.27 |
| 7 | Hy3-preview | 67.08 |
| 8 | DeepSeek V4 Pro | 66.57 |
| 9 | Qwen 3.5 27B (Non-reasoning) | 63.09 |
| 10 | Gemma 4 26B A4B | 59.89 |
| 11 | MiniMax-M2.7 | 57.66 |
| 12 | GPT-5.4 | 55.85 |
| 13 | DeepSeek V3.2 | 54.18 |
| 14 | GPT-5.4 Mini | 48.79 |
| 15 | GLM-4 32B | 46.56 |
Interactive version: theaggregate.ai/benchmark?slug=trip-plus-request-fulfillment · How It Works · Data refreshed daily, snapshot 2026-09-29.