MortgageTax (Vals all 1,258 documents)
Professional Work · 2025-03-05
MortgageTax as displayed by Vals over values that align to all 1,258 documents: 20 public-validation, 300 private-validation, and 938 test documents. This explicit identity quarantines the published all-data cohort from the page's contradictory prose describing results as held-out-test-only.
Top models (higher is better)
| Model | Score |
|---|---|
| Claude Opus 5 | 72.1 |
| Opus 4.7 | 70.3 |
| Sonnet 5 | 70.0 |
| Opus 4.8 | 69.9 |
| Gemini 3.1 Pro Preview | 69.4 |
| Gemini 3 Pro Preview | 69.1 |
| Claude Fable 5 | 68.9 |
| Gemini 2.5 Pro | 68.9 |
| GPT-5.5 | 68.8 |
| Gemini 3 Flash Preview | 68.7 |
| Claude 3.7 Sonnet | 68.7 |
| Opus 4.5 | 68.7 |
| Gemini 3.5 Flash-Lite | 68.7 |
| Opus 4.6 | 68.5 |
| MiniMax M3 | 68.4 |
| GPT-5.4 | 68.3 |
| Qwen3.6 27B | 68.3 |
| Gemini 3.5 Flash | 68.1 |
| Gemini 3.1 Flash-Lite Preview | 68.0 |
| Qwen3.6 Plus (2026-04-02) | 68.0 |
| Sonnet 4.6 | 67.7 |
| Gemini 3.6 Flash | 67.6 |
| Qwen3.5-Flash | 67.4 |
| GPT-5.6 Terra | 67.3 |
| GPT-5.6 Luna | 67.3 |
| GPT-5.6 Sol | 67.3 |
| Gemini 2.5 Pro Experimental 03-25 | 67.2 |
| GPT-5.2 | 67.1 |
| GPT-5 Mini | 66.9 |
| Kimi K2.5 | 66.5 |
| Kimi K3 | 66.3 |
| Qwen3.7-Plus | 66.2 |
| Muse Spark 1.1 | 66.1 |
| GPT-4.1 | 65.9 |
| Kimi K2.6 | 65.8 |
| o3 | 65.7 |
| GPT-4.1 Mini | 65.5 |
| GPT-5 | 65.5 |
| O4 Mini | 64.8 |
| Claude 3.5 Sonnet (Oct 2024) | 64.1 |