NYT Connections Older Models — leaderboard

Metric: Score (%). Source: github.com. 109 models tracked.

Top models

#ModelScore
1Grok 4 Fast (Reasoning)92.2
2Grok 491.8
3GPT-5 Pro83.9
4O3 (High)78.6
5GPT-5 (High)77.1
6O4 Mini (High)73.6
7O3 (Medium)73
8GPT-5 (Medium)72.2
9Median Human71
10O170.9
11GPT-5.1 (High)70
12O4 Mini (Medium)68.8
13GPT-5 Mini (Medium)67
14GPT-5 (Low)65.4
15GPT-5.1 (Medium)62.7

Interactive version: theaggregate.ai/benchmark?slug=nyt-connections-older-models · How the rankings work · Data refreshed daily, snapshot 2026-07-22.