LLM-as-a-Judge Quality Evaluation on 92 Queries Qwen 80B Evaluation 1.0 (test)
7.83ComprehensivenessNotebookLM
Evaluation results
| Method | Links | ||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|
| NotebookLMTier=Pro2026.04 | 7.83 | 8.1 | 8.1 | 9.12 | 8.23 | 9.74 | 8.35 | 8.33 | 9.88 | 8.7 | |
| AVA AI2026.04 | 7.58 | 8.07 | 8.07 | 9.48 | 8.74 | 9.92 | 8.01 | 8.74 | 9.96 | 8.81 | |
| Perplexity AIVersion=Enterprise, Web-Search Status=Disabled2026.04 | 7.38 | 8.34 | 8.34 | 9.28 | 8.83 | 9.67 | 8.35 | 8.28 | 10 | 8.77 |