URIAL-Bench - Humanities — leaderboard
Metric: Judge Score (0-10). Source: huggingface.co. 19 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | GPT-4 | 9.95 |
| 2 | Llama 2 70B Base | 9.75 |
| 3 | GPT-3.5 Turbo | 9.55 |
| 4 | DBRX | 9.32 |
| 5 | Mixtral 8x7B (v0.1) | 9.2 |
| 6 | Mistral-7B-v0.1 | 9.07 |
| 7 | Phi-2 | 8.85 |
| 8 | gemma-7B | 8.82 |
| 9 | Yi 6B (Base) | 8.78 |
| 10 | Yi 34B (Base) | 8.48 |
| 11 | Llama 2 13B Base | 8.3 |
| 12 | Llama 2 7B Base | 8.07 |
| 13 | gemma-2B | 5.65 |
| 14 | falcon-7B | 4.4 |
| 15 | mpt-7B | 1.75 |
Interactive version: theaggregate.ai/benchmark?slug=urial-bench-humanities · How the rankings work · Data refreshed daily, snapshot 2026-07-22.