ItinBench (Tool Use, Route Optimization) - Total Distance Gap: leaderboard
Metric: Total distance gap (percent): extra travel distance of the proposed plan over the authors' optimized route for the whole trip, on 300 queries in which the model gathers candidates through ReAct-style tool calls (with spatial cluster information from a clustering tool), with a request to optimize daily routes; ItinBench's Yelp-based multi-day trip-itinerary requests with stated preferences (hotels, restaurants, attractions), one run at temperature 1; lower is better. Source: arxiv.org. Saturation forecast: Around April 2027. 4 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | O1 | 7.7 | #177 |
| 2 | GPT-4o (2024-11-20) | 14.7 | #369 |
No result here: #3 Claude Opus 5.5, #5 GPT-6 Astra, #8 Claude Fable 5.1.
Interactive version: theaggregate.ai/benchmark?slug=itinbench-tool-use-route-optimization-total-distance-gap · How It Works · Data refreshed daily, snapshot 2026-10-11.