EgoDyn-Bench - Temporal F1: leaderboard

Metric: Macro-F1 (%) of temporal ego-motion questions (how the vehicle's motion changes over the clip) from driving video alone; higher is better. Source: arxiv.org. Saturation forecast: Around April 2028. 16 models tracked.

Top models

#ModelScore
1Gemini 3 Pro (Preview)45.2
2GPT-5.138.7
3Gemini 2.0 Flash35.1
4Claude Sonnet 4.534.9

Interactive version: theaggregate.ai/benchmark?slug=egodyn-bench-temporal-f1 · How It Works · Data refreshed daily, snapshot 2026-10-07.