LLM Stats (Finance Agent): leaderboard
Agentic financial analysis benchmark testing use of financial data, calculations, and written analysis across investment and business tasks.
Metric: Score (%). Source: llm-stats.com. Saturation forecast: Around January 2028. 8 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Claude Opus 4.7 | 64.4 | #49 |
| 2 | Claude Sonnet 4.6 | 63.3 | #90 |
| 3 | Claude Opus 4.6 | 60.7 | #63 |
| 4 | GPT-5.5 | 60 | #31 |
| 5 | Gemini 3.5 Flash | 57.9 | #60 |
| 6 | GPT-5.4 | 56 | #79 |
| 7 | Claude Opus 4.8 | 53.9 | #37 |
| 8 | Nemotron 3 Ultra | 53.7 | #235 |
No result here: #3 Claude Opus 5.5, #6 GPT-6 Astra, #7 GPT-6.1 Sol.
Interactive version: theaggregate.ai/benchmark?slug=llm-stats-finance-agent · How It Works · Data refreshed daily, snapshot 2026-10-20.