no, sonnet 3.5 is #7 on LiveBench, even below DeepSeek V3.
The parent comment was talking about coding specifically, not the average score. I see o1 at 69.69, and Claude 3.5 Sonnet at 67.13.
alt Hacker News
The parent comment was talking about coding specifically, not the average score. I see o1 at 69.69, and Claude 3.5 Sonnet at 67.13.