Rogo Big Finance Bench — leaderboard

Vendor-reported 928-question finance-agent benchmark spanning vertical-specific skills, metrics, financial-statement analysis, and forecasting workflows.

Metric: Rubric Score (self-reported). Source: benchmarklist.com. Status: saturation imminent. 10 models tracked.

Top models

#ModelScore
1Claude Sonnet 4.659
2GPT-5.559
3Claude Opus 4.759
4GLM-5.155
5Qwen 3.6 27B47
6Gemini 3 Flash (Preview)43
7Gemini 3.1 Pro (Preview)41
8GPT-5.4 Mini22

Interactive version: theaggregate.ai/benchmark?slug=rogo-big-finance-bench · How the rankings work · Data refreshed daily, snapshot 2026-07-22.