Legal Adjudication on Colorado Unemployment Insurance (Inconclusive)
89AccuracySPEC
Evaluation Results
| Method | Links | |
|---|---|---|
| SPECUnderlying Model=Sonnet 4.5, Prompting Strategy=SPEC pipeline2026.04 | 89 | |
| GPT 5.2Prompting Strategy=standard prompt2026.04 | 30 | |
| Gemini 3Prompting Strategy=standard prompt2026.04 | 15 | |
| Sonnet 4.5Prompting Strategy=standard prompt2026.04 | 8 | |
| NotebookLMPrompting Strategy=standard prompt2026.04 | 8 |