Diligence Stack Agent — Artifact Quality
Professional Work · 2026-07-09
Diligence Stack Agent Artifact Quality is the normalized percentage of available rubric points earned for readable, usable, and reviewable files, averaged across evaluated work.
Top models (higher is better)
| Model | Score |
|---|---|
| GPT-5.6 Sol | 94.5 |
| GPT-5.6 Luna | 83.0 |
| Kimi K3 | 83.0 |
| Claude Fable 5 | 81.4 |
| Sonnet 5 | 80.4 |
| GPT-5.5 | 75.0 |
| GPT-5.6 Terra | 74.4 |
| Opus 4.8 | 73.4 |
| Grok 4.5 | 71.0 |
| Kimi K2.6 | 68.0 |
| Gemini 3.5 Flash | 67.5 |
| DeepSeek-V4-Pro | 61.9 |
| Muse Spark 1.1 | 48.0 |
| Grok 4.3 | 0.0 |