Trip+: leaderboard
Interactive travel planning has become a popular use case for language models. Agents are deployed to manage evolving preferences and unexpected disruptions over multiple turns. Such settings require models to make complex, profile-conditioned planning decisions. However, existing benchmarks often evaluate feasibility, personalization, or interaction in relatively isolated settings. We therefore i
Metric: Plan Avg. (self-reported). Source: benchmarklist.com. Saturation forecast: Around July 2027. 18 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Gemini 3.1 Pro (Preview) | 73.31 | #58 |
| 2 | GLM-5.1 | 68.96 | #97 |
| 3 | Kimi K2.6 | 67.5 | #104 |
| 4 | GPT-5.4 | 67.04 | #79 |
| 5 | Qwen 3.6 27B | 66.35 | #170 |
| 6 | DeepSeek V4 Pro | 66.22 | #102 |
| 7 | Seed 2.0 Pro | 64.74 | #118 |
| 8 | Qwen 3.5 27B | 64.61 | #187 |
| 9 | Gemma 4 31B | 64.28 | #200 |
| 10 | Gemini 3 Flash (Preview) | 63.28 | #82 |
| 11 | Gemma 4 26B A4B | 61.36 | #358 |
| 12 | Hy3-preview | 61.3 | #157 |
| 13 | DeepSeek V3.2 | 60.55 | #205 |
| 14 | GPT-5.4 Mini | 59.68 | #212 |
| 15 | MiniMax-M2.7 | 57.48 | #258 |
No result here: #3 Claude Opus 5.5, #6 GPT-6 Astra, #7 GPT-6.1 Sol.
Interactive version: theaggregate.ai/benchmark?slug=trip-plus · How It Works · Data refreshed daily, snapshot 2026-10-20.