EgoGapBench - Four Options: leaderboard
Metric: Accuracy (%; zero-shot multiple choice on 382 four-option single-image items built from COCO multi-agent scenes: choose the action available from the given viewpoint, with distractors copying the singleton action of another visible agent, plus an off-vantage distractor that fits the activity but not the viewpoint; predicted option string-matched to the key; chance about 25%). Source: arxiv.org. Saturation forecast: Around March 2027. 9 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | GPT-5.4 (Medium) | 65.7 |
| 2 | GPT-5.4 (Low) | 57.3 |
| 3 | gemma-4-E4B-it | 49 |
| 4 | Gemini 3 Flash (Preview) (Low) | 33.5 |
| 5 | Qwen 2.5 VL 7B Instruct | 27 |
| 6 | Qwen 3.5 9B | 24.3 |
| 7 | InternVL3.5-8B | 22.5 |
| 8 | GPT-4o (2024-11-20) | 19.6 |
Interactive version: theaggregate.ai/benchmark?slug=egogapbench-four-options · How It Works · Data refreshed daily, snapshot 2026-09-29.