WorldTravel-Bench (Multimodal): leaderboard
WorldTravel-Bench in the multimodal setting (plans grounded in visual materials); feasibility rate %, human performance reference 77.9%.
Metric: Feasibility Rate (%). Source: humanlaya.com. Saturation forecast: Around September 2028. 7 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | GPT-5.2 | 19.33 | #115 |
| 2 | Claude Opus 4.5 | 14 | #87 |
| 3 | Gemini 3 Pro | 8 | #82 |
| 4 | Claude Sonnet 4.5 | 2.67 | #148 |
| 5 | GPT-5.1 | 2.67 | #145 |
| 6 | Gemini 2.5 Pro | 1.33 | #159 |
No result here: #3 Claude Opus 5.5, #6 GPT-6 Astra, #7 GPT-6.1 Sol.
Interactive version: theaggregate.ai/benchmark?slug=worldtravel-bench-multimodal · How It Works · Data refreshed daily, snapshot 2026-11-05.