DRInQ — leaderboard
Metric: Vanilla (self-reported). Source: benchmarklist.com. 13 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | O3 | 67 |
| 2 | Claude Sonnet 4.5 | 65 |
| 3 | Claude Haiku 4.5 | 64 |
| 4 | GPT-4o | 62 |
| 5 | GPT-5 | 62 |
| 6 | GPT-4.1 | 61 |
| 7 | DeepSeek V3 | 60 |
| 8 | Llama 3.3 70B Instruct | 58 |
| 9 | GPT-5 Mini | 56 |
| 10 | Qwen 2.5 72B Instruct | 56 |
| 11 | GPT-5 Nano | 45 |
Interactive version: theaggregate.ai/benchmark?slug=drinq · How the rankings work · Data refreshed daily, snapshot 2026-07-22.