Diligence Stack Agent — Source Grounding
Professional Work · 2026-07-09
Diligence Stack Agent Source Grounding is the normalized percentage of available rubric points earned for relevant evidence, attribution, and traceability, averaged across evaluated work.
Top models (higher is better)
| Model | Score |
|---|---|
| Sonnet 5 | 91.5 |
| GPT-5.6 Luna | 90.8 |
| GPT-5.6 Sol | 90.2 |
| Claude Fable 5 | 89.1 |
| GPT-5.5 | 88.3 |
| Muse Spark 1.1 | 82.5 |
| GPT-5.6 Terra | 82.0 |
| Opus 4.8 | 80.8 |
| Grok 4.5 | 80.0 |
| Kimi K3 | 80.0 |
| Grok 4.3 | 65.0 |
| Gemini 3.5 Flash | 58.8 |
| DeepSeek-V4-Pro | 57.8 |
| Kimi K2.6 | 55.0 |