FAM-Bench — leaderboard
Metric: Task 1 Acc. (self-reported). Source: benchmarklist.com. 5 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Gemini 2.5 Pro | 82.8 |
| 2 | GPT-5.4 | 82.4 |
| 3 | Claude Sonnet 4.6 | 81.2 |
| 4 | Qwen 3 VL 8B Instruct | 75.73 |
| 5 | Gemma 3 12B | 71.8 |
Interactive version: theaggregate.ai/benchmark?slug=fam-bench · How the rankings work · Data refreshed daily, snapshot 2026-07-22.