ARC-AGI-2 Verified (Opus 4.6 System Card) — leaderboard
Metric: Score (%). Source: www-cdn.anthropic.com. 5 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Claude Opus 4.6 (Thinking) | 68.8 |
| 2 | GPT-5.2 | 54.2 |
| 3 | Gemini 3 Pro | 45.1 |
| 4 | Claude Opus 4.5 (Thinking) | 37.6 |
| 5 | Claude Sonnet 4.5 | 13.6 |
Interactive version: theaggregate.ai/benchmark?slug=arc-agi-2-verified-opus-4-6-system-card · How the rankings work · Data refreshed daily, snapshot 2026-07-22.