SFI-Bench (Web Search): leaderboard
SFI-Bench (2026) macro-average accuracy over its six tasks for models that may use a web search tool, for example to read a user manual, before answering the operation planning and troubleshooting questions; the other four tasks are answered directly. Percent; higher is better.
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 February 2027. 7 models tracked. Updated 7 Oct 2026.
Top models
| # | Model | Setting | Score | Overall rank |
|---|---|---|---|---|
| 1 | Gemini 3.1 Pro (Preview) | 73.8 | #99 | |
| 2 | GPT-5.4 | High | 72.1 | #135 |
| 3 | GPT-5 | 69.4 | #178 | |
| 4 | Gemini 3.1 Flash Lite | 69.4 | #371 | |
| 5 | Gemini 2.5 Pro | 67.1 | #276 | |
| 6 | O4 Mini | 66.8 | #368 | |
| 7 | Gemini 2.5 Flash | 55.3 | #463 |
No result here: #1 Claude Fable 5.2, #3 Gemini 4 Neon, #4 GPT-6.2 Astra.
Interactive version: theaggregate.ai/benchmark?slug=sfi-bench-web-search · How It Works · Data refreshed daily, snapshot 2026-11-21.