ScratchWorld - Extend — leaderboard
Metric: Success Rate (%). Source: huggingface.co. 8 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Claude Sonnet 4.5 | 83.33 |
| 2 | Gemini 2.5 Pro | 72.22 |
| 3 | GPT-5 | 66.67 |
| 4 | DeepSeek V3.2 | 66.67 |
| 5 | Qwen 3 VL 32B Instruct | 0 |
| 6 | Qwen 2.5 Coder 7B Instruct | 0 |
| 7 | Qwen 3 Coder 30B A3B Instruct | 0 |
| 8 | uitars-1.5-7B | 0 |
Interactive version: aibenchmarks.dev/benchmark?slug=scratchworld-extend · How the rankings work · Data refreshed daily, snapshot 2026-07-17.