SFI-Bench - Cross-View Path Reasoning: leaderboard
Cross-view multi-hop path reasoning questions from SFI-Bench (2026): four-option questions about egocentric videos of scanned indoor rooms, answered zero-shot from the video. Accuracy in percent; higher is better.
Metric: Accuracy (%) on the cross-view multi-hop path reasoning 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; answered directly with no tools; higher is better. Source: arxiv.org. Saturation forecast: Estimated already saturated. 24 models tracked. Updated 7 Oct 2026.
Top models
| # | Model | Setting | Score | Overall rank |
|---|---|---|---|---|
| 1 | Gemini 3.1 Pro (Preview) | 83.4 | #99 | |
| 2 | GPT-5 | 83 | #178 | |
| 3 | GPT-5.4 | High | 82.8 | #135 |
| 4 | Gemini 2.5 Pro | 80.7 | #276 | |
| 5 | Gemini 3.1 Flash Lite | 78.3 | #371 | |
| 6 | O4 Mini | 73.7 | #368 | |
| 7 | LLaVA-Video-72B | 70.3 | #1193 | |
| 8 | Gemini 2.5 Flash | 66.8 | #463 | |
| 9 | Qwen 3 VL 235B A22B Instruct | 66.6 | #532 | |
| 10 | Qwen 3 VL 32B Instruct | 64.3 | #606 | |
| 11 | Qwen 3 VL Plus | 64.3 | #512 | |
| 12 | LLaVA-OneVision-72B | 64.2 | #1771 | |
| 13 | Qwen 3 VL 32B (Thinking) | 64 | #573 | |
| 14 | InternVL3.5-14B | 63.6 | #1504 | |
| 15 | Qwen 3 VL 235B A22B (Thinking) | 62.4 | #459 |
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-cross-view-path-reasoning · How It Works · Data refreshed daily, snapshot 2026-11-21.