IntentionNav - Grounded Success: leaderboard
IntentionNav (2026) tests intent-driven object navigation: an embodied agent receives an indirect human intent instead of a target name and must infer the object, find it in an Isaac Sim scene and stop near it, with the evaluated VLM inside a fixed reference agent. This board is the success rate in percent of stopping within 1 metre with the target visible in the final view; higher is better.
Metric: Grounded success rate (%): the agent stops within 1.0 m of the target with the target visible in the final frame, over IntentionNav's 2,000 episodes (500 implicit-intent instructions in four styles, 176 Isaac Sim scenes, 64 target categories, target name withheld), the VLM driving the benchmark's fixed reference active-navigation agent (RGB-D, open-vocabulary detection, map memory, 30-step budget); higher is better. Source: arxiv.org. Saturation forecast: Around 2029. 3 models tracked. Updated 7 Oct 2026.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Gemini 3.1 Flash Lite | 6.6 | #371 |
| 2 | GPT-5.4 | 5.1 | #135 |
| 3 | Qwen 3.6 Plus | 4.8 | #238 |
No result here: #1 Claude Fable 5.2, #3 Gemini 4 Neon, #4 GPT-6.2 Astra.
Interactive version: theaggregate.ai/benchmark?slug=intentionnav-grounded-success · How It Works · Data refreshed daily, snapshot 2026-11-21.