UGI Leaderboard — leaderboard
Metric: UGI Score. Source: huggingface.co. 1291 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Grok 4.20 Multi-Agent | 70 |
| 2 | Grok 4 | 67.83 |
| 3 | DeepSeek V3.2 Speciale | 65.37 |
| 4 | Grok 4.20 0309 (Reasoning) | 64.23 |
| 5 | Grok 3 | 63.47 |
| 6 | Grok 4.1 Fast (Reasoning) | 63.24 |
| 7 | Grok 4.5 | 62.32 |
| 8 | DeepSeek V4 Pro (Reasoning) | 62.26 |
| 9 | Grok 4.3 | 59.41 |
| 10 | Mistral Large 2 (Nov) Instruct (2411) | 59.23 |
| 11 | DeepSeek V4 Flash (Non-reasoning) | 59.21 |
| 12 | GLM-5.2 (Reasoning) | 58.91 |
| 13 | DeepSeek V3.2 (Thinking) | 57.78 |
| 14 | DeepSeek V3.1 Terminus | 57.58 |
| 15 | DeepSeek V3 | 56.96 |
Interactive version: theaggregate.ai/benchmark?slug=ugi-leaderboard · How the rankings work · Data refreshed daily, snapshot 2026-07-22.