EgoDyn-Bench - Temporal F1: leaderboard
EgoDyn-Bench (2026) tests whether vision-language models understand the motion of the ego vehicle in driving video, through multiple-choice questions on speed, acceleration and turning answered from video alone. This board is macro-F1 in percent on the temporal questions about how the motion changes during a clip; higher is better.
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 October 2027. 16 models tracked. Updated 7 Oct 2026.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Gemini 3 Pro (Preview) | 45.2 | #119 |
| 2 | GPT-5.1 | 38.7 | #240 |
| 3 | Qwen 3 VL 2B | 37.5 | #2134 |
| 4 | Cosmos-Reason2-8B | 36.7 | #755 |
| 5 | Gemini 2.0 Flash | 35.1 | #723 |
| 6 | Qwen 3 VL 4B | 35.1 | #1151 |
| 7 | Claude Sonnet 4.5 | 34.9 | #261 |
| 8 | InternVL3.5-8B | 33.5 | #1604 |
| 9 | Qwen 3 VL 8B | 32.7 | #917 |
| 10 | RoboTron-Drive | 31.3 | |
| 11 | ImpromptuVLA (EgoDyn-Bench checkpoint unspecified) | 29.2 | |
| 12 | InternVL3.5-4B | 28.7 | #1930 |
| 13 | CamReasoner-8B | 28.6 | |
| 14 | InternVL3.5-38B | 27 | #1021 |
| 15 | InternVL3-2B | 26.4 | #3290 |
No result here: #1 Claude Fable 5.2, #3 Gemini 4 Neon, #4 GPT-6.2 Astra.
Interactive version: theaggregate.ai/benchmark?slug=egodyn-bench-temporal-f1 · How It Works · Data refreshed daily, snapshot 2026-11-21.