SADU - Counting: leaderboard
SADU (2026) tests vision-language models on counting and retrieval questions about behavioral, structural and entity-relationship software architecture diagrams. This board is exact-match accuracy in percent on the counting questions across all diagram types; higher is better.
Metric: Exact-match accuracy (%) on the counting questions of SADU across all diagram types (154 software architecture diagrams (behavioral, structural and ER) with 2,431 counting and retrieval questions, temperature 0); higher is better. Source: arxiv.org. Saturation forecast: Around February 2027. 11 models tracked. Updated 7 Oct 2026.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Gemini 3 Flash (Preview) | 76 | #152 |
| 2 | Gemini 2.5 Flash | 72 | #463 |
| 3 | Gemini 3.1 Flash Lite (Preview) | 61 | #417 |
| 4 | Claude Sonnet 4.5 | 51 | #261 |
| 5 | GPT-5 Nano | 50 | #906 |
| 6 | Claude Haiku 4.5 | 44 | #583 |
| 7 | Qwen 2.5 VL 32B | 38 | #941 |
| 8 | Gemini 2.5 Flash Lite | 32 | #964 |
| 9 | Qwen 2.5 VL 7B | 31 | #1862 |
| 10 | GPT-4o Mini | 16 | #1667 |
| 11 | Qwen 2.5 VL 3B | 8 | #2639 |
No result here: #1 Claude Fable 5.2, #3 Gemini 4 Neon, #4 GPT-6.2 Astra.
Interactive version: theaggregate.ai/benchmark?slug=sadu-counting · How It Works · Data refreshed daily, snapshot 2026-11-21.