TurtleAI - Synthetic: leaderboard

Metric: Success rate (%) on the 619 TurtleAI-DSSyn tasks (generated from the real set and manually selected), symbolic comparison: the predicted Python turtle program is run in a canonicalizing emulator and succeeds when its normalized drawing matches the reference pixel by pixel (0.95 or 0.92 overlap threshold), greedy decoding, one fixed prompt with the task image; higher is better. Source: arxiv.org. Saturation forecast: Around 2028. 18 models tracked.

Top models

#ModelScore
1O4 Mini (Medium)10.5
2O3 (Medium)10.18
3GPT-5 (Medium)7.43
4GPT-4o (2024-11-20)5.82
5Qwen 2.5 VL 72B Instruct3.55
6InternVL3-78B3.23
7GPT-4 Turbo3.23
8Qwen 3 VL 30B A3B Instruct2.91
9Pixtral-12B0.97
10Qwen 2 VL 7B Instruct0

Interactive version: theaggregate.ai/benchmark?slug=turtleai-synthetic · How It Works · Data refreshed daily, snapshot 2026-09-29.