NL2Scratch: leaderboard
Block-based programming environments such as Scratch are widely used in early programming education, yet natural-language-to-code (NL2Code) research has focused primarily on text-based languages. Scratch programs are event-driven, visually compositional, and distributed across concurrent scripts, making conventional NL2Code assumptions and evaluation insufficient. We introduce NL2Scratch, an execu
Metric: SAC_ref Avg (self-reported). Source: benchmarklist.com. Saturation forecast: Estimated already saturated. 11 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | GPT-4.1 | 99.1 | #248 |
| 2 | Qwen 2.5 7B Instruct | 97.9 | #862 |
| 3 | Llama 3.1 8B Instruct | 96.5 | #1035 |
| 4 | GPT-4o Mini | 78 | #599 |
No result here: #3 Claude Opus 5.5, #6 GPT-6 Astra, #7 GPT-6.1 Sol.
Interactive version: theaggregate.ai/benchmark?slug=nl2scratch · How It Works · Data refreshed daily, snapshot 2026-10-20.