SFI-Bench (Web Search): leaderboard
Metric: Macro-average accuracy (%) over the six tasks (global and conditional counting, cross-view path reasoning, layout inference, functional association, operation planning, troubleshooting), four-option multiple choice on egocentric indoor videos (ARKitScenes and ScanNet++ scans), zero-shot with the same prompt templates, models at their default configurations; the first four tasks are answered directly and, for the last two, the model may first retrieve external knowledge such as user manuals through its web search tool; higher is better. Source: arxiv.org. Saturation forecast: Around January 2027. 8 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Gemini 3.1 Pro (Preview) | 73.8 |
| 2 | GPT-5.4 (High) | 72.1 |
| 3 | GPT-5 | 69.4 |
| 4 | Gemini 3.1 Flash Lite | 69.4 |
| 5 | GPT-5.4 | 67.3 |
| 6 | Gemini 2.5 Pro | 67.1 |
| 7 | O4 Mini | 66.8 |
| 8 | Gemini 2.5 Flash | 55.3 |
Interactive version: theaggregate.ai/benchmark?slug=sfi-bench-web-search · How It Works · Data refreshed daily, snapshot 2026-10-07.