ERGeoBench - Common Sense: leaderboard
Metric: Accuracy (%) on the common sense diagnostic questions: single-view, dual-view and cross-view questions mapping user needs to points of interest, fuzzy-matched, averaged over the three sub-tasks; unified structured prompt with egocentric observations, action history and in-context examples, temperature 0.1, first valid JSON object parsed (invalid outputs count as failures); higher is better. Source: arxiv.org. Saturation forecast: Not forecast. 9 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Gemini 2.0 Flash | 60.72 |
| 2 | InternVL3-8B | 52.85 |
| 3 | Qwen 2.5 VL 7B | 50.55 |
| 4 | GPT-4o | 42.38 |
| 5 | Gemini 2.5 Pro | 38.24 |
| 6 | Gemini 3 Flash | 37.02 |
Interactive version: theaggregate.ai/benchmark?slug=ergeobench-common-sense · How It Works · Data refreshed daily, snapshot 2026-10-07.