FineBench (Subset) - Object Manipulation: leaderboard
Metric: Accuracy (%; four-option multiple-choice questions on how a designated person handles objects; representative subset of 7 AVA movie clips, 20,143 questions). Source: arxiv.org. Saturation forecast: Estimated already saturated. 7 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Gemini 2.0 Flash | 86.3 |
| 2 | GPT-5 Mini | 85.3 |
| 3 | MiniCPM-V-2.6 | 84.8 |
| 4 | Gemini 1.5 Flash | 81.9 |
Interactive version: theaggregate.ai/benchmark?slug=finebench-subset-object-manipulation · How It Works · Data refreshed daily, snapshot 2026-09-26.