BARISTA - Activity Recognition: leaderboard
BARISTA (2026) is an egocentric benchmark of 185 coffee-preparation videos with verified per-frame scene graphs, from which zero-shot language tasks for vision-language models are derived. This board is accuracy in percent on 25-way multiple-choice activity recognition from short clips; higher is better.
Metric: Accuracy (%) of 25-way multiple-choice activity recognition on 500 four-frame clips on BARISTA, an egocentric coffee-preparation video dataset with verified per-frame scene graphs, zero-shot with shared task prompts, temperature 0.7 (GPT-5.4 mini at its fixed sampling), low thinking effort for the closed models, mean of three runs; higher is better. Source: arxiv.org. Saturation forecast: Around February 2027. 5 models tracked. Updated 7 Oct 2026.
Top models
| # | Model | Setting | Score | Overall rank |
|---|---|---|---|---|
| 1 | Qwen 3.5 27B | 77.8 | #380 | |
| 2 | Gemini 3 Flash | Low | 76.5 | #180 |
| 3 | Qwen 3.5 9B | 71.6 | #838 | |
| 4 | Gemma 4 31B | 68.4 | #390 | |
| 5 | GPT-5.4 Mini | Low | 63.1 | #409 |
No result here: #2 Claude Fable 5.2, #3 Gemini 4 Neon, #4 GPT-6.2 Astra.
Interactive version: theaggregate.ai/benchmark?slug=barista-activity-recognition · How It Works · Data refreshed daily, snapshot 2026-11-22.