LongEgoRefer - Temporal Grounding: leaderboard
Metric: Mean temporal IoU (%; predicted versus annotated time interval of the referred object interaction, 1,498 expressions over untrimmed Ego4D videos averaging 45 minutes; zero-shot VLM prompted for start and end times). Source: arxiv.org. Saturation forecast: Around February 2028. 19 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | GPT-5 | 16.19 |
| 2 | Gemini 2.5 Pro | 10.73 |
| 3 | GPT-4o | 8.71 |
| 4 | Gemini 2.5 Flash | 4.49 |
| 5 | Gemini 2.0 Flash | 2.29 |
| 6 | Qwen 3 VL 32B | 1.81 |
| 7 | InternVL3.5-8B | 1.5 |
Interactive version: theaggregate.ai/benchmark?slug=longegorefer-temporal-grounding · How It Works · Data refreshed daily, snapshot 2026-09-29.