WebArena Average@5 (Opus 4.6 System Card) — leaderboard
Metric: Score (%). Source: www-cdn.anthropic.com. 4 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Claude Opus 4.6 (Thinking) | 68 |
| 2 | Claude Opus 4.5 (Thinking) | 65.3 |
| 3 | Claude Sonnet 4.5 | 58.5 |
| 4 | Claude Haiku 4.5 | 53.1 |
Interactive version: theaggregate.ai/benchmark?slug=webarena-average-5-opus-4-6-system-card · How the rankings work · Data refreshed daily, snapshot 2026-07-22.