NYT Connections Original — leaderboard
Original version: 436 standard NYT Connections puzzles without modifications. Models get one attempt (humans get four). ~71% average human solve rate.
Metric: Score (%). Source: github.com. Status: saturation imminent. 29 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Human Expert | 100 |
| 2 | O1 | 90.7 |
| 3 | O1 Preview | 87.1 |
| 4 | O3 Mini | 72.4 |
| 5 | Median Human | 71 |
| 6 | DeepSeek R1 | 54.4 |
| 7 | O1 Mini | 42.2 |
| 8 | Gemini 2.0 Flash (01-21) (Thinking) | 37 |
| 9 | GPT-4 Turbo | 28.3 |
| 10 | GPT-4o (2024-11-20) | 27.9 |
| 11 | GPT-4o (2024-08-06) | 26.5 |
| 12 | Llama 3.1 405B | 26.3 |
| 13 | Claude 3.5 Sonnet (20241022) | 25.9 |
| 14 | Claude 3 Opus | 24.8 |
| 15 | Llama 3.3 70B | 23.7 |
Interactive version: theaggregate.ai/benchmark?slug=nyt-connections-original · How the rankings work · Data refreshed daily, snapshot 2026-07-22.