Tax Agent Bench — Controversy & Precedence All-Pass
Professional Work · 2026-09-23
All-rubric-item pass rate on the 30 controversy-and-precedence questions.
Top models (higher is better)
| Model | Score |
|---|---|
| Claude Opus 5.5 | 30.0 |
| Claude Fable 5.1 | 26.7 |
| Claude Opus 5 | 23.3 |
| GLM-5.3 | 20.0 |
| GPT-5.6 Sol | 20.0 |
| GPT-5.6 Terra | 16.7 |
| Grok 4.6 | 16.7 |
| Muse Spark 1.3 | 16.7 |
| GPT-6 Astra | 13.3 |
| Grok 4.7 | 13.3 |
| Kimi K3 | 13.3 |
| MiMo-V2.6-Pro | 13.3 |
| Sonnet 5 | 10.0 |
| GPT-5.5 | 10.0 |
| GPT-5.6 Luna | 10.0 |
| Inkling | 10.0 |
| DeepSeek V4 Pro 0813 | 6.7 |
| Gemini 3.7 Flash | 6.7 |
| Gemini 3.8 Flash | 6.7 |
| GPT-6 Luna | 6.7 |
| GPT-6 Sol | 6.7 |
| Hy4 Preview | 6.7 |
| MiniMax M3 | 6.7 |
| DeepSeek V4.1 Flash | 3.3 |
| Mercury 2.5 | 3.3 |
| MiMo-V2.6-Flash | 3.3 |