WebForge-Bench - Content Moderation: leaderboard

WebForge-Bench (2026) tests browser agents on tasks set in automatically generated, reproducible websites with injected real-web noise, controlled for difficulty along seven dimensions. This board is task accuracy in percent on the content moderation and compliance domain with screenshot and DOM input; higher is better.

Metric: Accuracy (%) on the content moderation and compliance tasks of the 934 WebForge-Bench tasks on generated, self-contained websites with injected real-web noise, up to 50 browser actions in a Chromium GUI, final-state answer checking; multimodal setting: screenshot plus DOM; higher is better. Source: arxiv.org. Saturation forecast: Estimated already saturated. 10 models tracked. Updated 7 Oct 2026.

Top models

#ModelScoreOverall rank
1Claude Sonnet 4.570.4#261
2Gemini 3 Pro67.2#145
3Gemini 3 Flash61.6#175
4Kimi K2.561.6#266
5GPT-5.258.4#185
6GPT-5 Mini56.8#364
7Qwen 3 VL 235B A22B40.8#485
8GPT-5 Nano29.6#906
9Gemini 2.5 Flash Lite28.8#964
10qwen3-omni-30B9.6#1608

No result here: #1 Claude Fable 5.2, #3 Gemini 4 Neon, #4 GPT-6.2 Astra.

Interactive version: theaggregate.ai/benchmark?slug=webforge-bench-content-moderation · How It Works · Data refreshed daily, snapshot 2026-11-21.