WebMainBench - Hard: leaderboard
Metric: ROUGE-N F1 (N=5, %). Source: huggingface.co. Saturation forecast: Around December 2026. 4 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | GPT-5 | 86.38 |
| 2 | Gemini 2.5 Pro | 86.1 |
Interactive version: theaggregate.ai/benchmark?slug=webmainbench-hard · How It Works · Data refreshed daily, snapshot 2026-09-26.