SFI-Bench - Troubleshooting (Web Search): leaderboard

Causal hypothesis and troubleshooting questions about devices seen in the video from SFI-Bench (2026): four-option questions about egocentric videos of scanned indoor rooms, answered by models that may first retrieve external knowledge such as user manuals with a web search tool. Accuracy in percent; higher is better.

Metric: Accuracy (%) on the causal hypothesis and troubleshooting questions, 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 model may first retrieve external knowledge such as user manuals through its web search tool; higher is better. Source: arxiv.org. Saturation forecast: Around February 2027. 7 models tracked. Updated 7 Oct 2026.

Top models

#ModelSettingScoreOverall rank
1Gemini 3.1 Pro (Preview)72.1#102
2GPT-5.4High68.8#138
3Gemini 3.1 Flash Lite66.3#377
4O4 Mini60.4#372
5Gemini 2.5 Pro58.1#280
6GPT-558.1#185
7Gemini 2.5 Flash47.7#466

No result here: #2 Claude Fable 5.2, #3 Gemini 4 Neon, #4 GPT-6.2 Astra.

Interactive version: theaggregate.ai/benchmark?slug=sfi-bench-troubleshooting-web-search · How It Works · Data refreshed daily, snapshot 2026-11-22.