SFI-Bench - Global and Conditional Counting: leaderboard
Counting questions (global counts and counts under a condition) 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 global and conditional counting 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: Around June 2027. 24 models tracked. Updated 7 Oct 2026.
Top models
| # | Model | Setting | Score | Overall rank |
|---|---|---|---|---|
| 1 | Gemini 3.1 Pro (Preview) | 59.1 | #102 | |
| 2 | GPT-5 | 58.4 | #185 | |
| 3 | GPT-5.4 | High | 58.4 | #138 |
| 4 | LLaVA-Video-72B | 57.9 | #1211 | |
| 5 | LLaVA-Video-7B | 55.4 | #2303 | |
| 6 | Gemini 3.1 Flash Lite | 55 | #377 | |
| 7 | Gemini 2.5 Pro | 54.4 | #280 | |
| 8 | Qwen 3 VL 235B A22B (Thinking) | 53.8 | #462 | |
| 9 | LLaVA-OneVision-72B | 52.8 | #1782 | |
| 10 | Qwen 3 VL 235B A22B Instruct | 52.3 | #541 | |
| 11 | Qwen 3 VL Plus | 51.3 | #514 | |
| 12 | O4 Mini | 51 | #372 | |
| 13 | Qwen 3 VL 32B Instruct | 50 | #607 | |
| 14 | Qwen 3 VL 32B (Thinking) | 49.5 | #577 | |
| 15 | InternVL3.5-30B-A3B | 48.5 | #1269 |
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-global-and-conditional-counting · How It Works · Data refreshed daily, snapshot 2026-11-22.