WorldCoder-Bench - Robust: leaderboard

Metric: Verification coverage (%) on WorldCoder-Robust, 615 perturbed variants of the WorldCoder-Core tasks (three per task, with randomized physical constants, object counts, initial states, prompt phrasing and asset filenames and rewritten contracts), same zero-shot protocol and StateProbe checks; higher is better. Source: arxiv.org. Saturation forecast: Around 2029. 5 models tracked.

Top models

#ModelScore
1GPT-5.419.9
2Gemini 3.1 Pro (Preview)19.1
3Kimi K2.515.6
4Claude Opus 4.613.9
5Qwen 3.6 Plus13.5

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