# Finance Agent v2 — AI model rankings

Tests the AI on real financial-analysis work, like digging through reports and making sound decisions. Higher is better.

9 tracked models have a published Finance Agent v2 score. Higher is better. Scores come from published lab reports and benchmark sources; recorded sources appear beside the scores.

## Ranking

| Rank | Model | Developer | Score | Source | Released |
| --- | --- | --- | --- | --- | --- |
| 1 | Gemini 3.8 Flash | Google | 61.4% | Lab | Sep 2 2026 |
| 2 | Gemini 3.5 Flash | Google | 57.9% | Lab | May 19 2026 |
| 3 | Muse Spark 1.1 | Meta | 57.2% | Lab | Jul 9 2026 |
| 4 | Claude Opus 4.8 | Anthropic | 53.9% | Lab | May 28 2026 |
| 5 | GPT-5.5 | OpenAI | 51.8% | Lab | Apr 23 2026 |
| 6 | Claude Opus 4.7 | Anthropic | 51.5% | Lab | Apr 16 2026 |
| 7 | Claude Sonnet 4.6 | Anthropic | 51% | Lab | Feb 17 2026 |
| 8 | Gemini 3.1 Pro | Google | 43% | Lab | Feb 19 2026 |
| 9 | Gemini 3.0 Flash | Google | 42.6% | Lab | Dec 17 2025 |


---

Canonical page: https://aireleasetracker.com/benchmark/finance-agent-v2
Full dataset: https://aireleasetracker.com/llms-full.txt · JSON: https://aireleasetracker.com/models.json
Source: AI Release Tracker (https://aireleasetracker.com). Most benchmark scores come from lab launch material; gathered results identify the leaderboard that published them.