FinVerBench: leaderboard
We introduce FinVerBench, a benchmark and validity study for financial statement verification: determining whether a set of corporate financial statements is numerically consistent from the information shown to the model. FinVerBench is built from SEC 10-K XBRL filings for 43 S&P 500 companies and defines a four-category error taxonomy covering arithmetic, cross-statement linkage, year-over-year,
Metric: Accuracy (self-reported). Source: benchmarklist.com. Saturation forecast: Estimated already saturated. 15 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Claude Sonnet 4 | 100 | #199 |
| 2 | Qwen 3 235B A22B | 65.7 | #313 |
| 3 | Gemma 3 27B | 61.9 | #607 |
| 4 | GPT-4.1 | 61 | #248 |
| 5 | DeepSeek R1 | 60 | #251 |
| 6 | Llama 4 Maverick | 59 | #464 |
| 7 | Llama 4 Scout | 58.1 | #656 |
No result here: #3 Claude Opus 5.5, #6 GPT-6 Astra, #7 GPT-6.1 Sol.
Interactive version: theaggregate.ai/benchmark?slug=finverbench · How It Works · Data refreshed daily, snapshot 2026-10-20.