FinanceQA
Finance & Accounting · 2025-01-29
AfterQuery's FinanceQA tests financial analysis of the kind done at hedge funds, private-equity firms and investment banks on 148 public test questions: 38 basic tactical and 46 assumption-based tactical questions answered from a company's financial statements and notes, and 64 conceptual questions on accounting and valuation conventions asked without documents. Each answer is graded as an exact correct match, with no partial credit. The score is accuracy over all 148 questions, as published on AfterQuery's FinanceArena leaderboard.
Top models (higher is better)
| Model | Score |
|---|---|
| o3 | 54.1 |
| Grok 4 | 49.3 |
| O4 Mini | 48.6 |
| Gemini 2.5 Pro | 45.3 |
| Llama 4 Maverick Instruct | 44.6 |
| Opus 4 | 44.6 |
| Grok 3 (API) | 44.6 |
| Sonnet 4 | 43.9 |
| Phi-4-reasoning-plus | 43.2 |
| DeepSeek-R1-0528 | 42.9 |
| QwQ-32B | 42.6 |
| GPT-4.1 Mini | 41.9 |
| Llama 3.1 Nemotron Ultra 253B V1 | 41.9 |
| Qwen3-30B-A3B | 37.2 |
| Kimi K2 Instruct | 33.8 |
| Gemini 2.5 Flash | 32.4 |
| Magistral Medium 1.0 | 31.8 |
| Command A | 27.7 |
| Nova Pro | 20.3 |