BloomBench - Arabic - Create: leaderboard
Metric: Accuracy (%) on the 685 Arabic BloomBench items at the Bloom level Create (choosing the synthesis that best meets creative constraints), four-option image-question multiple choice, zero-shot, temperature 0, the chosen letter parsed from the generated answer (Regex-based Answer Extraction; unparseable answers count as wrong); chance 25; higher is better. Source: arxiv.org. Saturation forecast: Around December 2026. 8 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Gemma 4 31B | 82 |
| 2 | Gemma 3 27B | 78 |
| 3 | Gemma 4 26B A4B | 78 |
| 4 | Gemma 3 12B | 75 |
| 5 | GPT-4o Mini | 69 |
| 6 | Qwen 2.5 VL 7B | 69 |
| 7 | Qwen 2 VL 7B | 67 |
| 8 | Gemma 3 4B | 65 |
Interactive version: theaggregate.ai/benchmark?slug=bloombench-arabic-create · How It Works · Data refreshed daily, snapshot 2026-09-29.