ParseBench - Content Faithfulness: leaderboard
Metric: Content Faithfulness Score. Source: parsebench.ai. Saturation forecast: Around May 2028. 78 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Claude Opus 5.5 | 91.81 |
| 2 | Claude Fable 5.1 | 91.19 |
| 3 | Gemini 3 Flash (High) | 90.87 |
| 4 | Qwen 3.6 35B A3B | 90.7 |
| 5 | Qwen 3.5 9B | 90.5 |
| 6 | Claude Opus 4.7 | 90.26 |
| 7 | Gemini 3.5 Flash (Medium) | 90.19 |
| 8 | Gemini 3.1 Pro (Preview) | 90.16 |
| 9 | Claude Fable 5 | 90.02 |
| 10 | Gemma 4 31B (IT) | 89.9 |
| 11 | Claude Opus 4.6 | 89.7 |
| 12 | Gemini 3.8 Flash (High) | 89.68 |
| 13 | Gemini 3.1 Flash Lite | 89.46 |
| 14 | Claude Opus 4.8 | 89.02 |
| 15 | Qwen 3.5 4B | 88.9 |
Interactive version: theaggregate.ai/benchmark?slug=parsebench-content-faithfulness · How It Works · Data refreshed daily, snapshot 2026-09-24.